Dr. Gabor Fichtinger

@article{zachmann2026,

title = {Extended reality for enhancing surgery: Research directions to transform the operating environment},

author = {Gabriel Zachmann and Peter Haddawy and Ron Kikinis and Anja Hennemuth and Philippe C. Cattin and Tanja Döring and Simon Drouin and Gábor Fichtinger and Tabea Flügge and Joaquim A. Jorge and Luv Kohli and Mario Lorenz and Rainer Malaka and Javier Pascau and Dirk Reiners and Anke V. Reinschluessel and Andrea Schenk and Falko Schmid and Siriwan Suebnukarn and Verena Uslar and Gregory F. Welch and René Weller and Dirk Weyhe and Myat Su Yin and Sudanthi Wijewickrema},

year  = {2026},

date = {2026-01-01},

journal = {Journal of Healthcare Informatics Research},

abstract = {Abstract In the past decade, virtual reality (VR) and augmented reality (AR) have seen a second wave of activity due to consumer-level availability of devices. In the medical realm, use of VR and AR has been investigated extensively and successfully for training, teaching, rehabilitation, and therapy. However, extended reality (XR) and its intraoperative use in the operating room has yet been underexplored and underdeveloped. Intelligent XR environments that integrate advanced visualization, intuitive interaction, and AI-assisted decision support have the potential to transform clinical care. Responsive, context-aware spaces could enhance medical teams’ capabilities by enabling real-time access to critical information, enhancing situation awareness, and supporting remote collaboration and access to clinical expertise across geographical boundaries—all while preserving the natural flow of procedures. But to realize the potential benefits of XR in the operating room requires a significant and focused effort by an interdisciplinary community. It is the intention of this paper to help to catalyze such an effort. In this paper, we identify pressing issues in clinical care, the potential of XR to address them, and the further research that is needed to realize that potential. We look at a broad range of areas where XR can play an important role, including direct support for the surgeon, support for the surgical team, support for the patient, and remote collaboration. We also consider ways in which XR can be integrated with AI to provide enhanced information and interaction. Discussions are underpinned by considerations of methods to evaluate contributions and progress. This paper is the result of a Dagstuhl Seminar on Extended Reality for the Operating Room (XR4OR) , held at the Leibniz Center for Informatics, Schloss Dagstuhl, Germany, in February 2025. It gathered twenty-four researchers working in the areas of virtual reality, augmented reality, medical informatics, human-computer interaction, and surgery.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{srikanthan2026,

title = {Do Foundation Models See Biology? Evaluating Attention Coherence with Spatial Transcriptomics in Glioblastoma},

author = {Dilakshan Srikanthan and Amoon Jamzad and Paul Wilson and Nooshin Maghsoodi and Robert Policelli and Gábor Fichtinger and John F. Rudan and Parvin Mousavi},

year  = {2026},

date = {2026-01-01},

journal = {arXiv (Cornell University)},

abstract = {Whether attention maps from pathology foundation models capture genuine biology remains unknown, yet this question is critical for clinical trust and regulatory approval. We propose a spatial transcriptomics-based framework for orthogonal, hypothesis-free evaluation of attention and apply it to five pathology foundation models (CONCH v1.5, UNI v2, Virchow2, GigaPath, H-Optimus-1) and a ResNet50 baseline. Using attention-based multiple instance learning, we train single-task and multi-task models to predict five molecular alterations in glioblastoma on the CPTAC cohort, validate on an independent TCGA cohort, and evaluate biological coherence of attention maps against 87 transcriptional signatures using co-registered Visium spatial transcriptomics data from 18 samples. Internally, no single encoder dominates across all tasks, and external validation inverts internal performance rankings. Attention maps show a five-fold enrichment gradient from pathways (Cohen's d=0.329) to individual genes (d=0.055), indicating that attention captures emergent multi-gene transcriptional programs rather than individual molecular events. Spatially smooth attention maps do not imply biological coherence, and different encoders attend to distinct biological compartments. Our framework provides objective, quantitative assessment of what foundation models learn from histopathology, moving the field beyond qualitative saliency map review.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{siddiqui2026,

title = {Registration of clinical MRI volumes to low-cost manikin heads for neuronavigation training},

author = {Shahbaaz Siddiqui and Colton Barr and András Lassó and Gábor Fichtinger},

year  = {2026},

date = {2026-01-01},

pages = {43},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rosenfeld2026,

title = {Validating RGB-D object detection for skill assessment in central venous catheterization using expert benchmarks},

author = {Josh Rosenfeld and Rebecca Hisey and Denise R. Wong and Ryan Varma and Gábor Fichtinger},

year  = {2026},

date = {2026-01-01},

pages = {41},

abstract = {Purpose: Computer-assisted surgical skill assessment has traditionally used physical sensors to track tool motion, which adds cost, setup time and can affect instrument handling. End-to-end video classifiers predict skill from video but offer limited interpretability. This study tests a low-cost, camera-based alternative for central venous catheterization that detects tools and computes depth-derived motion metrics. We compare the correlation with expert-rated OSATS scores for video-derived and EM-tracked path length to identify the better-aligned method. Methods: Five novices and five experts each performed ten trials on a venous access phantom, yielding 100 recordings. An RGB-D camera captured synchronized colour and depth video, and EM sensors recorded motion for the ultrasound probe and syringe. Videos were anonymized and scored with OSATS by four expert raters, then averaged per trial. A YOLOv8 network produced bounding boxes on the colour stream. Path length in millimetres was computed from depth for all annotated tools, and from EM tracking for the ultrasound probe and syringe using the Perk Tutor extension of 3D Slicer. Spearman rank correlations were computed between OSATS and path length per tool for both methods. Results: Ultrasound probe correlations with OSATS were −0.45 (p<0.001) for video and −0.35 (p<0.001) for EM. Syringe correlations were −0.58 (p<0.001) for video and −0.45 (p<0.001) for EM. No other tools showed a significant correlation. Conclusions: Object detection-derived path length aligned more strongly with expert ratings than EM-tracked path length, indicating a practical, low-cost, camera-based alternative.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{orosz2026,

title = {Explainable transfer learning ensemble AI model for lung ultrasound pneumothorax detection with expert benchmark},

author = {Gábor Orosz and Róbert Zsolt Szabó and Marcell Szabó and Pál Gyombolai and József T Tóth and Tamás Ruttkay and Tamás Ferenci and Tamás Ungi and Gábor Fichtinger and Tamás Haidegger},

year  = {2026},

date = {2026-01-01},

journal = {Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine},

volume = {34},

number = {1},

pages = {95},

publisher = {Biomed Central},

abstract = {Background 

Lung ultrasound is essential for rapid, radiation-free bedside pneumothorax diagnosis but limited by variability in human interpretation. Key gaps include insufficiently large and diverse human datasets, inconsistent image acquisition, lack of rigorous expert benchmarking, and inadequate clinical interpretability of existing artificial intelligence models. We aimed to develop and validate a robust, explainable artificial intelligence (AI) ensemble model addressing these critical gaps. 

Methods 

With our multidisciplinary team, we developed an explainable soft-voting ensemble model trained on 1,856 diverse ultrasound clips from critically ill patients, healthy volunteers, and tailored cadaver models. Model interpretability was ensured using visualization, with heatmaps validated by expert clinicians. The model’s diagnostic performance was rigorously benchmarked against 11 experienced clinicians using an …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{barr2026,

title = {Local LLMs as cooperative agents for low-cost surgical navigation support},

author = {Colton Barr and Colin Galvin and Amirali Azimi and Sarah Frisken and Steve Pieper and Gábor Fichtinger and Alexandra Golby and Parvin Mousavi},

year  = {2026},

date = {2026-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

volume = {21},

number = {7},

pages = {1613-1620},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{nassar2026,

title = {A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients},

author = {Sarah Nassar and Nooshin Maghsoodi and Sophia Mannina and Shamel Addas and Stephanie Sibley and Gábor Fichtinger and David Pichora and David Maslove and Purang Abolmaesumi and Parvin Mousavi},

year  = {2026},

date = {2026-01-01},

journal = {IEEE Transactions on Biomedical Engineering},

volume = {PP},

pages = {1-11},

abstract = {OBJECTIVE: Atrial fibrillation (AF) is the most common cardiac arrhythmia experienced by intensive care unit (ICU) patients and can cause adverse health effects. In this study, we publish a labelled ICU dataset and bench marks for AF detection. METHODS: We compared machine learning models across three data-driven artificial intelligence (AI) approaches: feature-based classifiers, deep learning (DL), and ECG foundation models (FMs). This comparison addresses a critical gap in the literature and aims to pinpoint which AI approach is best for high-performing AF detection. Electrocardiograms (ECGs) from a Canadian ICU and the 2021 PhysioNet/Computing in Cardiology Challenge were used to conduct the experiments. Multiple training configurations were tested, ranging from zero-shot in ference to transfer learning. RESULTS: Across both datasets, ECG FMs generally performed best, followed by DL, then feature-based classifiers. However, the difference between DL and feature-based classifiers is minimal and highly dependent on the model selected, with feature-based classifiers obtaining a very slightly higher average performance on our ICU test set but DL achieving a higher overall maximum performance. The models that achieved the top F1 score on our ICU test set were InceptionV3 with recurrence plots and a fine-tuned ECGFounder (F1 = 0.88). CONCLUSION: This study demonstrates promising potential for using AI to build an automatic patient monitoring system. SIGNIFICANCE: By publishing our labelled ICU dataset 1 and performance benchmarks, this work enables the research community to continue advancing the state-of-the-art in AF detection in the ICU environment.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{maghsoodi2026,

title = {Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment},

author = {Nooshin Maghsoodi and Amoon Jamzad and Robert Policelli and Mohammad Farahmand and Dilakshan Srikanthan and Martin Kaufmann and Kevin Y. M. Ren and Shaila Merchant and Sonal Varma and Ross Walker and Doug McKay and JOHN RUDAN and Gábor Fichtinger and Parvin Mousavi},

year  = {2026},

date = {2026-01-01},

journal = {arXiv (Cornell University)},

abstract = {Deep learning models can effectively use Rapid Evaporative Ionization Mass Spectrometry (REIMS) data for surgical margin assessment. However, their clinical adoption remains challenging due to limited generalization to operating room conditions. This difficulty arises because models are typically trained on labeled spectra collected from resected tissue samples, while they must operate on noisy, unlabeled data acquired directly during surgery. In addition, the black-box nature of deep learning models makes it difficult to understand and systematically improve their behavior. Concept-based learning offers a promising way to address these challenges by mapping raw measurements to human-understandable concepts. However, supervised concept-based approaches rely on concept annotations, which are difficult to obtain in complex mass spectrometry workflows. We propose Agent-Guided Concept Discovery, a framework that learns meaningful concepts directly from data without requiring predefined concept labels. During training, a reasoning agent refines semantic descriptions of the learned concepts and adaptively adjusts their weight based on diagnostic relevance. These concepts are further grounded using a biochemical knowledge graph to ensure consistency with known metabolic relationships. Across Skin and Breast Cancer datasets, our model improves balanced accuracy and sensitivity over the baseline. In a representative intraoperative case, it shows fewer false positives, indicating better generalization to surgical conditions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{connolly2026,

title = {No cancer left behind: a testbed and demonstration of concept for photoacoustic tumor bed inspection},

author = {Laura Connolly and Hyunwoo Song and Keshuai Xu and Anton Deguet and Simon Leonard and Gabor Fichtinger and Parvin Mousavi and Russell H Taylor and Emad Boctor},

year  = {2026},

date = {2026-01-01},

journal = {Computer Assisted Surgery},

volume = {31},

number = {1},

pages = {2604123},

publisher = {Taylor & Francis},

abstract = {Cancer resection surgery is unsuccessful if tumor tissue is left behind in the surgical cavity. Identifying the residual cancer requires additional imaging or postoperative histological analysis. Photoacoustic imaging can be used to image both the surface and depths of the resection cavity; however, its performance hinges on consistent probe placement and stable acoustic and optical coupling. As intra-cavity deployment of photoacoustic imaging is largely uncharted, several potential embodiments warrant rigorous investigation. We address this need with an open-source robotic testbed for intraoperative tumor-bed inspection using photoacoustic imaging. The platform integrates the da Vinci Research Kit, depth imaging, and electromagnetic tracking to automate cavity scanning and maintain repeatable probe trajectories. Using tissue-mimicking phantoms, we (i) demonstrate a novel imaging embodiment for …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{logan2026,

title = {Evaluating vibrotactile feedback for electromagnetic surgical navigation},

author = {Stuart Logan and Laura Connolly and Colton Barr and Parvin Mousavi and Gábor Fichtinger and Keyvan Hashtrudi-Zaad},

year  = {2026},

date = {2026-01-01},

pages = {73},

abstract = {INTRODUCTION: Breast-conserving surgery (BCS) requires precise excision of tumours while preserving healthy tissue, yet positive margin rates remain high due to challenges in intraoperative tumour localization. We investigate a guidance system that integrates tracked ultrasound, electromagnetic navigation, and a vibrotactile tactor to provide haptic feedback to the surgeon. METHODS: Our proposed system continuously measures the distance between the cautery tool and the tumour boundary, triggering vibrotactile signals as the instrument approaches the margin. In this paper, we evaluate system performance through electromagnetic interference characterization to determine the optimal tactor placement; latency testing to quantify end-to-end response time; and root-mean-square displacement analysis to verify that tactor vibration does not perturb the surgical instrument. RESULTS: We demonstrate that the hardware and software architecture are feasible for use, with minimal field distortion when the tactor is positioned greater than 10 cm from the electromagnetic (EM) sensor. End-to-end latency of 156 ± 45 ms for the wireless configuration, near the upper perceptual threshold for tactile feedback, and 126 ± 10 ms when using a wired connection. Finally, tactor activation induced negligible instrument motion, increasing cautery tip displacement by only 0.2 mm compared to the non-activated condition. CONCLUSIONS: These findings suggest that with proper tactor placement and communication configuration, the system can provide intraoperative tactile feedback without compromising navigation accuracy, supporting safer tumour margin identification and with further development, potentially reduce reoperation rates in BCS.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hisey2026,

title = {Feasibility of Learner-Led Model Building for Simulation-Based Training in Open Inguinal Hernia Repair: A Randomized Controlled Trial},

author = {Rebecca Hisey and Denesh Peramakumar and Vanessa Wiseman and Farah Zaza and Iona Abolmaesumi and Elizabeth Klosa and Aden Wong and Gabor Fichtinger and Boris Zevin},

year  = {2026},

date = {2026-01-01},

journal = {Journal of Surgical Education},

volume = {83},

number = {9},

pages = {104054},

publisher = {Elsevier},

abstract = {Objectives (1) To establish the feasibility of novice learners building inguinal hernia models for simulation-based training in open inguinal hernia repairs (IHR). (2) To examine the associations between participation in model building and learners’ self-reported confidence in understanding of the inguinal canal anatomy, the anatomic accuracy of learner-constructed models, and technical performance during a simulated open IHR. We hypothesized that learner-led model construction is feasible, supports acquisition of relevant anatomy knowledge, and improves performance in some steps of a simulated open IHR. Design Prospective randomized controlled trial. Setting Queen’s University, Kingston, Ontario, Canada; institutional academic training environment. Participants Forty-eight novice learners (second-year medical students) with minimal prior exposure to open or laparoscopic IHR were enrolled and randomly …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{harmanani2026,

title = {Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning},

author = {Mohamed Harmanani and Bining Long and Zhuoxin Guo and Paul Wilson and Amirhossein Sabour and Minh Nguyen Nhat To and Gábor Fichtinger and Purang Abolmaesumi and Parvin Mousavi},

year  = {2026},

date = {2026-01-01},

journal = {arXiv (Cornell University)},

abstract = {Concept Bottleneck Models (CBMs) are a prominent framework for interpretable AI that map learned visual features to a set of meaningful concepts for task-specific downstream predictions. Their sequential structure enhances transparency by connecting model predictions to the underlying concepts that support them. In medical imaging, where transparency is essential, CBMs offer an appealing foundation for explainable model design. However, discrete concept representations often overlook broader clinical context such as diagnostic guidelines and expert heuristics, reducing reliability in complex cases. We propose MedCBR, a concept-based reasoning framework that integrates clinical guidelines with vision-language and reasoning models. Labeled clinical descriptors are transformed into guideline-conformant text, and a concept-based model is trained with a multitask objective combining multimodal contrastive alignment, concept supervision, and diagnostic classification to jointly ground image features, concepts, and pathology. A reasoning model then converts these predictions into structured clinical narratives that explain the diagnosis, emulating expert reasoning based on established guidelines. MedCBR achieves superior diagnostic and concept-level performance, with AUROCs of 94.2% on ultrasound and 84.0% on mammography. Further experiments on non-medical datasets achieve 86.1% accuracy. Our framework enhances interpretability and forms an end-to-end bridge from medical image analysis to decision-making.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{guo2026,

title = {Pathology-guided contrastive pretraining enriches preoperative CT representations for prognosis},

author = {Zhuoxin Guo and Mohamed Harmanani and Paul Wilson and Minh Nguyen Nhat To and Tarek Elghareb and Obed Korshie Dzikunu and Nooshin Maghsoodi and Gábor Fichtinger and Purang Abolmaesumi and Parvin Mousavi},

year  = {2026},

date = {2026-01-01},

pages = {36},

abstract = {PURPOSE: Prognosis prediction is important for personalized cancer treatment. Histopathology imaging can provide key prognostic information but it relies on tissue obtained during surgery, which restricts its use for preoperative decision-making. Preoperative imaging modalities such as computed tomography (CT) are more accessible but often lack the pathological context needed for accurate prognosis. Multi-modal approaches that combine imaging and pathology aim to bridge this gap, yet they typically require both modalities at inference time, making them impractical for preoperative decision-making. METHODS: To address this, we adopt a multi-modal contrastive learning (MMCL) framework that uses histopathology embeddings to guide CT feature learning. This approach enables the CT encoder to capture pathology-informed patterns during pretraining. At inference, MMCL uses only CT and routine clinical factors, allowing practical preoperative application. We evaluate MMCL on the MMIST-ccRCC dataset using cross-validation for predicting 12-month survival status. RESULTS: MMCL achieves an AUROC of 76% using only preoperative CT and clinical factors during inference, surpassing state-of-the-art multi-modal models that leverage both preoperative data and postoperative pathology. Even with CT alone, MMCL matches the performance of state-of-the-art multi-modal baselines, underscoring its robustness. CONCLUSION: Our findings demonstrate that contrastive learning allows CT encoders to extract richer and prognostically relevant features. Importantly, at the testing stage, more accurate and non-invasive survival prediction is achieved using only preoperative CT and general clinical features. This approach provides a promising strategy to improve preoperative prognostic assessment, supporting early treatment planning and guiding personalized cancer care.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ndiaye2025,

title = {Feasibility of Open-Source Tracking-Based Metrics in Evaluating Ultrasound-Guided Needle Placement Skills in Senegal},

author = {Fatou Ndiaye and Rebecca Hisey and Kyle Sunderland and Idrissa Seck and Idy Diop and Ron Kikinis and Babacar Diao and Gábor Fichtinger and Mamadou Samba Camara},

year  = {2025},

date = {2025-01-01},

journal = {Communications in computer and information science},

pages = {174-180},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ungi2025,

title = {Bone-enhanced 3D ultrasound: a non-ionizing alternative for pediatric scoliosis assessment},

author = {Tamás Ungi and Catherine O. Wu and Sarah L. Dance and Charles Lawall and Charles Nagel and Gregg Khodorov and Robert W. Ford and Kevin Cleary and Gábor Fichtinger and Matthew E. Oetgen and Daniel Borschneck},

year  = {2025},

date = {2025-01-01},

journal = {European Spine Journal},

volume = {34},

number = {7},

pages = {2662-2668},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hisey2025,

title = {Objective skill assessment for cataract surgery from surgical microscope video},

author = {Rebecca Hisey and Henry Lee and Adrienne Duimering and John Liu and Vasudha Gupta and Tamas Ungi and Christine Law and Gabor Fichtinger and Matthew Holden},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

pages = {1-12},

publisher = {Springer International Publishing},

abstract = {Objective 

Video offers an accessible method for automated surgical skill evaluation; however, many platforms still rely on traditional six-degree-of-freedom (6-DOF) tracking systems, which can be costly, cumbersome, and challenging to apply clinically. This study aims to demonstrate that trainee skill in cataract surgery can be assessed effectively using only object detection from monocular surgical microscope video. 

Methods 

One ophthalmologist and four residents performed cataract surgery on a simulated eye five times each, generating 25 recordings. Recordings included both the surgical microscope video and 6-DOF instrument tracking data. Videos were graded by two expert ophthalmologists using the ICO-OSCAR: SICS rubric. We computed motion-based metrics using both object detection from video and 6-DOF tracking. We first examined correlations between each metric and expert scores for each rubric …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{farvolden2025,

title = {An accessible six-axis testbed for image-guided robotics research},

author = {Coleman Farvolden and Kian Hashtrudi-Zaad and Laura Connolly and Colton Barr and Gabor Fichtinger},

year  = {2025},

date = {2025-01-01},

volume = {13408},

pages = {458-463},

publisher = {SPIE},

abstract = {PURPOSE: Cancer can recur after tumor resection surgery if tumor tissue is missed and left behind. We hypothesize that intraoperative robotic imaging could be used to inspect the surgical cavity and localize residual cancer tissue. This technique has the potential to improve the success rate of tumor resection surgery. Towards this, we propose and evaluate a benchtop testbed for robotic manipulation of an optical imaging probe. We use low-cost hardware and open-source software to construct the testbed and describe the implementation so that it can be easily adopted to support similar research. METHODS: We implemented a reusable, open-source module in 3D Slicer for reading position coordinates and motion planning with an inexpensive 6-axis robotic arm in Robot Operating System (ROS). For demonstration, a custom end-effector was used to fix an optical probe to the robot. The accuracy of the testbed …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{rubino2025,

title = {Evaluating rapid evaporative ionization mass spectrometry profiles of human breast cancer cells using a 3D in vitro assay: Rubino et al.},

author = {Rachel E. Rubino and Martin Kaufmann and Amoon Jamzad and Natasha Iaboni and Kevin Yi Mi Ren and Jian Yu and Haidy Metwally and Manuela Kunz and John F. Rudan and Parvin Mousavi and Gabor Fichtinger and Richard Oleschuk and Christopher J. B. Nicol},

year  = {2025},

date = {2025-01-01},

journal = {Analytical and Bioanalytical Chemistry},

volume = {417},

number = {22},

pages = {5115-5130},

publisher = {Springer Science and Business Media LLC},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hashtrudi-zaad2025,

title = {Robotic tracking of a resection cavity using a low cost bench-top robotic arm and electromagnetics},

author = {Kian Hashtrudi-Zaad and Coleman Farvolden and Laura Connolly and Colton Barr and Gabor Fichtinger},

year  = {2025},

date = {2025-01-01},

volume = {13408},

pages = {217-222},

publisher = {SPIE},

abstract = {INTRODUCTION 

Roughly 40% of breast cancer patients are required to undergo corrective surgery after tumour resection via breast-conserving surgery (BCS). Sweeping of the cavity, resulting from the tumour resection, by spectroscopy and ultrasound imaging is emerging as a potential solution for identifying leftover cancer. However, the use of imaging modalities in the cavity is challenging as breast tissue is soft, malleable, and moves frequently. This paper presents and verifies an approach for tracking the relative motion of a resection cavity with a robotic arm. 

METHODS 

We use electromagnetic tracking and a low cost 6-axis robotic arm to track a simulated resection cavity. We embed an electromagnetic sensor in a 3D printed retractor that is designed to hold the cavity open. An open-source module in 3D Slicer is then used to detect cavity motion from the retractor and command the robotic arm to follow the …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{reinke2025,

title = {Current validation practice undermines surgical AI development},

author = {Annika Reinke and Z. Li and Minu D. Tizabi and Pascaline André and Marcel Knopp and Mika M. Rother and Inês Machado and Maria S. Altieri and Deepak Alapatt and Sophia Bano and Sebastian Bodenstedt and Oliver Burgert and Elvis C. S. Chen and Justin Collins and Olivier Colliot and Evangelia Christodoulou and Tobias Czempiel and Adrito Das and Reuben Docea and Daniel A. Donoho and Qi Dou and Jennifer A. Eckhoff and Sandy Engelhardt and Gábor Fichtinger and Philipp Fuernstahl and Pablo García Kilroy and Stamatia Giannarou and Stephen Gilbert and Ines Gockel and Patrick Godau and Jan Gödeke and Teodor Grantcharov and Tamás Haidegger and Alexander Hann and Makoto Hashizume and Charles Heitz and Rebecca Hisey and Hanna Hoffmann and Arnaud Huaulmé and Paul F. Jäger and Pierre Jannin and Anthony Jarc and Rohit Jena and Yueming Jin and Leo Joskowicz and Luc Joyeux and Max Kirchner and Axel Krieger and Gernot Kronreif and Kyle Lam and Shlomi Laufer and Joël L. Lavanchy and G Lee and Robert H. Lim and Peng Liu and Lucas Luttner and Hani J. Marcus and Pietro Mascagni and Leon Mayer and Ozanan R. Meireles and Beat P. Mueller and Lars Mündermann and Hirenkumar Nakawala and Nassir Navab and Abdourahmane Ndong and Juliane Neumann and Felix Nickel and Marco Nolden and Chinedu Nwoye and Namkee Oh and Nicolas Padoy and Tim Rädsch and Micha Pfeiffer and Tim Rädsch and Hongliang Ren and Nicola Rieke and Dominik Rivoir and Duygu Sarikaya and Samuel Schmidgall and Matthias Seibold and Silvia Seidlitz and Alexander Seitel and Lalith Sharan and Jeffrey H. Siewerdsen and Vinkle Srivastav and Raphael Sznitman and Russell Taylor and Thuy N. Tran and Matthias Unberath and Fons Sommen and Martin Wagner and Amine Yamlahi and Shaohua K. Zhou and Aneeq Zia and Amin Madani and Danail Stoyanov and Stefanie Speidel and Daniel A. Hashimoto and Fiona R. Kolbinger and Lena Maier‐Hein},

year  = {2025},

date = {2025-01-01},

journal = {PubMed},

abstract = {Surgical data science (SDS) is rapidly advancing, yet clinical adoption of artificial intelligence (AI) in surgery remains limited, with inadequate validation emerging as an important contributing factor. In fact, existing validation practices often neglect the temporal and hierarchical structure of intraoperative videos, producing misleading, unstable, or clinically irrelevant results. In a pioneering, consensus-driven effort, we introduce a comprehensive catalog of validation pitfalls in AI-based surgical video analysis that was derived from a multi-stage Delphi process with 92 international experts. The collected pitfalls span three categories: (1) data (e.g., incomplete annotation, spurious correlations), (2) metric selection and configuration (e.g., neglect of temporal stability, mismatch with clinical needs), and (3) aggregation and reporting (e.g., clinically uninformative aggregation, failure to account for frame dependencies in hierarchical data structures). A systematic review of surgical AI papers reveals that these pitfalls are widespread in current practice, with the majority of studies failing to account for temporal dynamics or hierarchical data structure, or relying on clinically uninformative metrics. Experiments on real surgical video datasets provide empirical evidence that ignoring temporal and hierarchical data structures can substantially understate uncertainty, obscure critical failure modes, and even alter algorithm rankings. To address these shortcomings, we provide a catalogue of best practices compiled in a multi-stage Delphi process. Together, this work provides an evidence-based framework to inform more rigorous validation of surgical video analysis algorithms and to guide future efforts in benchmarking, reporting, regulatory review, and clinical translation.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{radcliffe2025a,

title = {Anomaly detection using intraoperative iKnife data: a comparative analysis in breast cancer surgery},

author = {Olivia Radcliffe and Laura Connolly and Amoon Jamzad and Martin Kaufmann and Shaila J. Merchant and Jay Engel and Ross Walker and Sonal Varma and Gábor Fichtinger and John F. Rudan and Parvin Mousavi},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

volume = {20},

number = {9},

pages = {1953-1963},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{radcliffe2025,

title = {Advancing Prosthetic Care Access on the Thailand–Burma Border Through Open-Source Technology},

author = {Olivia Radcliffe and Aung Tin Tun and Nyein Chan Aung and Wunn Lei Thwe and Laura Connolly and Tamás Ungi and Kanchana Thornton and Colleen Davison and Eva Purkey and Parvin Mousavi and Gábor Fichtinger},

year  = {2025},

date = {2025-01-01},

journal = {IEEE Pulse},

volume = {16},

number = {6},

pages = {64-70},

abstract = {The ongoing civil war in Myanmar (Burma) has severely disrupted the country's health care system, forcing widespread displacement and creating a critical shortage of medical care and prosthetic devices for refugees and migrants along the Thai border. Prohibitive costs, resource shortages, and movement constraints severely limit access to essential health care and functional prosthetics in this region. This article details a collaboration between Queen's University and the Burma Children Medical Fund (BCMF), a nongovernmental organization (NGO) that established a 3-D-printed prosthetic program in 2019 using open-source technology. Since 2023, this collaboration has facilitated a three-year student mobility program, sending researchers to Thailand to enhance BCMF's existing initiative by addressing technical limitations and improving design autonomy. Using the development of a short transradial (below-elbow) prosthetic as a case study for this collaborative framework, the team employed low-cost 3-D scanning and computer-aided design (CAD) to modify an open-source prosthetic model for better suspension and fit. Our approach prioritized local capacity building by training local staff in CAD to ensure design autonomy and implementing filament dryers to mitigate humidity-related printing errors. From 2019 to 2024, the program provided free prostheses to 76 individuals, including five recipients of the customized below-elbow design. Pilot evaluations using the Orthotics Prosthetics Users Survey (OPUS) indicated positive results, with recipients reporting high levels of functionality and satisfaction, and no reported adverse effects. Ultimately, this work demonstrates the feasibility of a framework for academic-NGO partnerships that leverages adaptable, open-source technology to deliver equitable prosthetic care in conflict-affected and resource-constrained settings.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{barr2025,

title = {Benchmarking NousNav: quantifying the spatial accuracy and clinical performance of an affordable, open-source neuronavigation system},

author = {Colton Barr and Colin Galvin and Parikshit Juvekar and Erickson Torio and Samantha Horvath and Samantha Sadler and Annie Li and R. E. Bardsley and Tina Kapur and Steve Pieper and Sonia Pujol and Sarah Frisken and Gábor Fichtinger and Alexandra J. Golby},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

volume = {20},

number = {12},

pages = {2529-2540},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{gabriel2025,

title = {Application of foundation models for colorectal cancer tissue classification in mass spectrometry imaging},

author = {Alon Gabriel and Amoon Jamzad and Mohammad Farahmand and Martin Kaufmann and Natasha Iaboni and David Hurlbut and Kevin Ren and Christopher J. B. Nicol and John F. Rudan and Sonal Varma and Gábor Fichtinger and Parvin Mousavi},

year  = {2025},

date = {2025-01-01},

journal = {Technologies},

volume = {13},

number = {10},

pages = {434},

abstract = {Colorectal cancer (CRC) remains a leading global health challenge, with early and accurate diagnosis crucial for effective treatment. Histopathological evaluation, the current diagnostic gold standard, faces limitations including subjectivity, delayed results, and reliance on well-prepared tissue slides. Mass spectrometry imaging (MSI) offers a complementary approach by providing molecular-level information, but its high dimensionality and the scarcity of labeled data present unique challenges for traditional supervised learning. In this study, we present the first implementation of foundation models for MSI-based cancer classification using desorption electrospray ionization (DESI) data. We evaluate multiple architectures adapted from other domains, including a spectral classification model known as FACT, which leverages audio–language pretraining. Compared to conventional machine learning approaches, these foundation models achieved superior performance, with FACT achieving the highest cross-validated balanced accuracy (93.27%±3.25%) and AUROC (98.4%±0.7%). Ablation studies demonstrate that these models retain strong performance even under reduced data conditions, highlighting their potential for generalizable and scalable MSI-based cancer diagnostics. Future work will explore the integration of spatial and multi-modal data to enhance clinical utility.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{connolly2025,

title = {Touching the tumor boundary: a pilot study on ultrasound-based virtual fixtures for breast-conserving surgery},

author = {Laura Connolly and Tamás Ungi and Adnan Munawar and Anton Deguet and Chris Yeung and Russell H. Taylor and Parvin Mousavi and Gábor Fichtinger and Keyvan Hashtrudi-Zaad},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

volume = {20},

number = {6},

pages = {1105-1113},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{farahmand2025,

title = {FACT: foundation model for assessing cancer tissue margins with mass spectrometry},

author = {Mohammad Farahmand and Amoon Jamzad and Fahimeh Fooladgar and Laura Connolly and Martin Kaufmann and Kevin Ren and John F. Rudan and Doug McKay and Gábor Fichtinger and Parvin Mousavi},

year  = {2025},

date = {2025-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

volume = {20},

number = {6},

pages = {1097-1104},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{jamzad2025a,

title = {MassVision: An Open-Source End-to-End Platform for AI-Driven Mass Spectrometry Imaging Analysis},

author = {Amoon Jamzad and Jade Warren and Ayesha Syeda and Martin Kaufmann and Natasha Iaboni and Christopher J. B. Nicol and John F. Rudan and Kevin Ren and David Hurlbut and Sonal Varma and Gábor Fichtinger and Parvin Mousavi},

year  = {2025},

date = {2025-01-01},

journal = {Analytical Chemistry},

volume = {97},

number = {39},

pages = {21588-21597},

abstract = {Mass spectrometry imaging (MSI) combines spatial and spectral data to reveal detailed molecular compositions within biological samples. Despite their immense potential, MSI workflows are hindered by the complexity and high dimensionality of the data, making their analysis computationally intensive and often requiring expertise in coding. Existing tools frequently lack the integration needed for seamless, scalable, and end-to-end workflows, forcing researchers to rely on local solutions or multiple platforms, which hinders efficiency and accessibility. We introduce MassVision, a comprehensive software platform for MSI analysis. Built on the 3D Slicer ecosystem, MassVision integrates MSI-specific functionalities while addressing general user requirements for accessibility and usability. Its intuitive interface lowers barriers for researchers with varying levels of computational expertise, while its scalability supports high-throughput studies and multislide data sets. Key functionalities include visualization, segmentation, colocalization, data set curation, data set merging, spectral and spatial preprocessing, statistical analysis, AI model training, and AI deployment on full MSI data. We detail the workflow and functionalities of MassVision and demonstrate its effectiveness through different experimental use cases such as exploratory data analysis, ion identification, and tissue-type classification on in-house and publicly available data from different MSI modalities. These use cases underscore MassVision's ability to seamlessly integrate MSI data handling steps into a single platform and highlight its potential to reveal new insights and structures when examining biological samples. By combining cutting-edge functionality with user-centric design, MassVision addresses longstanding challenges in MSI data analysis and provides a robust tool for advancing the user's ability to achieve biologically meaningful insights from MSI data. MassVision is freely available via 3D Slicer (documentation: https://SlicerMassVision.readthedocs.io/). The in-house MSI data have been made publicly available in MetaboLights with the identifier MTBLS12868.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{othman2025,

title = {211 Three-Dimensional Navigated Mass Spectrometry for Intraoperative Margin Assessment During Breast Cancer Surgery},

author = {Amira Othman and Martin Kaufmann and Teaghan Koster and Amoon Jamzad and Tamas Ungi and Jessica Rodgers and Julie Mcmullen and Chris Yeung and Natasja Janssen and Kathryn Solberg and Joanna Cheesman and John Rudan and Parvin Mousavi and Gabor Fichtinger and Andrea Gallo Hoyos and Doris Jabs and Jay Engel and Shaila Merchant and Ross Walker and Kevin Ren and Sonal Varma},

year  = {2025},

date = {2025-01-01},

journal = {Laboratory Investigation},

volume = {105},

number = {3},

publisher = {Elsevier},

abstract = {Background 

Intraoperative frozen sections are not routine in Breast cancer (BC), hence, patients with positive margin need reoperation for margin clearance. Technologies that can identify residual cancer in real-time during the surgery can be of immense help in reducing the morbidity, healthcare utilization and, the prognosis in BC. Rapid evaporative ionization mass spectrometry (REIMS) is a mass spectrometric technique that can chemically profile the surgical cauterization plume to classify the tissue as either cancerous, suspicious or non-cancerous. A plastic tube with solvent is attached to the cautery knife (i-knife) and it passes the smoke generated from cautery of the tissue to the mass spectrometric machine located in the OR. The spectra generated from this smoke solution are assessed in real-time to help classify the tissue. Our goal was to compare the accuracy of REIMS with histology (the gold standard) to …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{jamzad2025,

title = {MassVision: An open-source end-to-end platform for AI-driven mass spectrometry image analysis},

author = {Amoon Jamzad and Jade Warren and Ayesha Syeda and Martin Kaufmann and Natasha Iaboni and Christopher Nicol and John Rudan and Kevin Ren and David Hurlbut and Sonal Varma and Gabor Fichtinger and Parvin Mousavi},

year  = {2025},

date = {2025-01-01},

journal = {bioRxiv},

pages = {2025.01. 29.635489},

publisher = {Cold Spring Harbor Laboratory},

abstract = {Mass spectrometry imaging (MSI) combines spatial and spectral data to reveal detailed molecular compositions within biological samples. Despite their immense potential, MSI workflows are hindered by the complexity and high dimensionality of the data, making their analysis computationally intensive and often requiring expertise in coding. Existing tools frequently lack the integration needed for seamless, scalable, and end-to-end workflows, forcing researchers to rely on local solutions or multiple platforms, hindering efficiency and accessibility. We introduce MassVision, a comprehensive software platform for MSI analysis. Built on the 3D Slicer ecosystem, MassVision integrates MSI-specific functionalities while addressing general user requirements for accessibility and usability. Its intuitive interface lowers barriers for researchers with varying levels of computational expertise, while its scalability supports high-throughput studies and multi-slide datasets. Key functionalities include visualization, co-localization, dataset curation, dataset merging, spectral and spatial preprocessing, AI model training, and AI deployment on full MSI data. We detail the workflow and functionalities of MassVision and demonstrate its effectiveness through different experimental use cases such as exploratory data analysis, ion identification, and tissue-type classification, on in-house and publicly available data from different MSI modalities. These use cases underscore the MassVision's ability to seamlessly integrate MSI data handling steps into a single platform, and highlight its potential to reveal new insights and structures when examining biological samples. By …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ordaz2025b,

title = {C-CASE 2024: Surgical Education Through Innovation: Canadian Conference for the Advancement of Surgical Education, Oct. 17-18, 2024, Toronto, Ontario},

author = {Daniel Josué Guerra Ordaz and Magdalena Cordoba and Éolie Delisle and Rocío Branes and Sophie Nguyen and Waiel Abdulaziz Daghistani and Maryam Mozafarinia and Carlos Cordoba and Jessica Maher and Marisa Dorling and Kirk Haan and Danah Fahad and Alexander Moise and Gizelle Francis and Youssef Omar and Elysia Grose and Timothy Phillips and Alexandra D'Souza and Shaishav Datta and Kyle Wanzel and Retage Al Bader and Clementine Affana and Ashish Kumar and Nancy Posel and David Fleiszer and Emily Lan-Vy Nguyen and Prachikumari Patel and Ahmer Irfan and Jason Aubrey and Taylor M Coe and Hala Muaddi and Roxana Bucur and Nadia Rukavina and Chaya Shwaartz and Khaled Skaik and Wassim Elmasry and Devon Haseltine and Matthew Bilson and Mahmoud Moustafa and Amrit Das and Maryam Wagner and Carlos Gomez-Garibello and Cariane Driad and Xavier Sonesaksith-Turcotte and Émilie Sandman and Lily Trang Huynh and Prevost Jantchou and Marie-Lyne Nault and Jasmine Ng and Jaskarn Dhaliwal and Henna Salim and Ayesha Shakeel and Suffia Malik and Wiley Chung and Lucy Yang and Abdullah Al-Ani and Mohamed Bondok and Helen Chung and Patrick Gooi and Giancarlo Sticca and Joseph Petruccelli and Dominique Dorion and Yousef Abdelkhalek Saber Omar and Kalpesh Hathi and Timothy Philips and Lalenthra Naidoo and Xin Yu Yang and Gabrielle Massé and Jean-François Tremblay and Franck Vandenbroucke-Menu and Mai-Kim Gervais and Julien Letendre and Hugues Jeanmart and Ariane Lacaille-Ranger and Farbod Niazi and Abrar Ahmed and Zeel Patel and Saman Arfaie and Crystal Ma and Gregory Mikerov and Jack Legler and Emily Steinberg and Elie Fadel and Liam Murad and Julia Biris and Charles Desgagné and Justine Colivas and Brandon Noyon and Adam Dubrowski and Érica Patocskai and Jason Kreutz and Donald McPhalen and Claire Temple-Oberle and Sonaina Chopra and Jasmin Dhanoa and Jason M Harley and Anita Acai and Amy Keuhl and Quang Ngo and Jonathan Sherbino and Ereny Bassilious and Elif Bilgic and Anushka Pradhan and Emily Volfson and Zackary Tsang and Megan Mak and Mojgan Hodaie and Denesh Peramakumar and Rebecca Hisey and Elizabeth Klosa and Aden Wong and Farah Zaza and Gabor Fichtinger and Boris Zevin and James Lisondra and Remi Gao and Albert Fung and Alicia Belaiche and Johanie Victoria Piché and Adam Hocini and Myriam Belaiche and Louise McNaughton-Filion and Constance Bouthillier and Tomas Cordoba and Charlotte McEwen and Iqbal Jaffer and Faizan Amin and Jeffrey Barsuk and William McGaghie and Matthew Sibbald and Edgar Akuffo-Addo and Jaycie Dalson and Kwame Agyei and Samiha Mohsen and Safia Yusuf and Clara Juando-Prats and Jory Simpson and Gursharan Sohi and Bianca Giglio and Vanja Davidovic and Recai Yilmaz and Abdulmajeed Albeloushi and Mohamed Alhantoobi and Abicumaran Uthamacumaran and Jason Lapointe and Ahmad Alhaj and Rothaina Saeedi and Trisha Tee and Rolando Del Maestro and Victoria Tran},

year  = {2025},

date = {2025-01-01},

journal = {Canadian journal of surgery. Journal canadien de chirurgie},

volume = {68},

number = {1suppl1},

pages = {S1-S13},

abstract = {C-CASE 2024: Surgical Education Through Innovation: Canadian Conference for the Advancement of Surgical Education, Oct. 17-18, 2024, Toronto, Ontario C-CASE 2024: Surgical Education Through Innovation: Canadian Conference for the Advancement of Surgical Education, Oct. 17-18, 2024, Toronto, Ontario Can J Surg. 2025 Feb 6;68(1suppl1):S1-S13. doi: 10.1503/cjs.000225. Print 2025 Jan-Feb. Authors Daniel Josué Guerra Ordaz 1 , Magdalena Cordoba 1 , Éolie Delisle 1 , Rocío Branes 1 , Sophie Nguyen 1 , Waiel Abdulaziz Daghistani 1 , Maryam Mozafarinia 1 , Carlos Cordoba 1 , Jessica Maher 2 , Marisa Dorling 2 , Kirk Haan 2 , Danah Fahad 2 , Alexander Moise 2 , Gizelle Francis 2 , Youssef Omar 2 , Elysia Grose 2 , Timothy Phillips 2 , Alexandra D'Souza 3 , Shaishav Datta 3 , Kyle Wanzel 3 , Retage Al Bader 4 , Clementine Affana 4 , Ashish Kumar 4 , Nancy Posel 5 , David Fleiszer 5 , Emily Lan-Vy …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ordaz2025,

title = {C-CASE 2024: Surgical Education Through Innovation01. A 25-year retrospective of Canadian plastic surgery research and its influence: a thorough bibliometric study02 …},

author = {Daniel Josué Guerra Ordaz and Jessica Maher and Alexandra D’Souza and Retage Al Bader and Nancy Posel and Emily Lan-Vy Nguyen and Khaled Skaik and Cariane Driad and Jasmine Ng and Lucy Yang and Giancarlo Sticca and Gizelle Francis and Xin Yu Yang and Farbod Niazi and Joseph Petruccelli and Gregory Mikerov and Justine Colivas and Jason Kreutz and Sonaina Chopra and Anushka Pradhan and Emily Volfson and Denesh Peramakumar and Prachikumari Patel and Alicia Belaiche and Constance Bouthillier and Charlotte McEwen and Edgar Akuffo-Addo and Gursharan Sohi and Bianca Giglio and Victoria Tran and Megan Skakum and Rachael Allen and Amrit Das and Alyson McKenna and Magdalena Cordoba and Éolie Delisle and Rocío Branes and Sophie Nguyen and Waiel Abdulaziz Daghistani and Maryam Mozafarinia and Carlos Cordoba and Marisa Dorling and Kirk Haan and Danah Fahad and Alexander Moise and Youssef Omar and Elysia Grose and Timothy Phillips and Shaishav Datta and Kyle Wanzel and Clementine Affana and Ashish Kumar and David Fleiszer and Ahmer Irfan and Jason Aubrey and Taylor M Coe and Hala Muaddi and Roxana Bucur and Nadia Rukavina and Chaya Shwaartz and Wassim Elmasry and Devon Haseltine and Matthew Bilson and Mahmoud Moustafa and Maryam Wagner and Carlos Gomez-Garibello and Xavier Sonesaksith-Turcotte and Émilie Sandman and Lily Trang Huynh and Prevost Jantchou and Marie-Lyne Nault and Jaskarn Dhaliwal and Henna Salim and Ayesha Shakeel and Suffia Malik and Wiley Chung and Abdullah Al-Ani and Mohamed Bondok and Helen Chung and Patrick Gooi and Dominique Dorion and Yousef Abdelkhalek Saber Omar and Kalpesh Hathi and Timothy Philips and Lalenthra Naidoo and Gabrielle Massé and Jean-François Tremblay and Franck Vandenbroucke-Menu and Mai-Kim Gervais and Julien Letendre and Hugues Jeanmart and Ariane Lacaille-Ranger and Abrar Ahmed and Zeel Patel and Saman Arfaie and Crystal Ma and Jack Legler and Emily Steinberg and Elie Fadel and Liam Murad and Julia Biris and Charles Desgagné and Brandon Noyon and Adam Dubrowski and Érica Patocskai and Donald McPhalen and Claire Temple-Oberle and Jasmin Dhanoa and Jason M Harley and Anita Acai and Amy Keuhl and Quang Ngo and Jonathan Sherbino and Ereny Bassilious and Elif Bilgic and Zackary Tsang and Megan Mak and Mojgan Hodaie and Rebecca Hisey and Elizabeth Klosa and Aden Wong and Farah Zaza and Gabor Fichtinger and Boris Zevin and James Lisondra and Remi Gao and Albert Fung and Johanie Victoria Piché and Adam Hocini and Myriam Belaiche and Louise McNaughton-Filion and Tomas Cordoba and Iqbal Jaffer and Faizan Amin and Jeffrey Barsuk and William McGaghie and Matthew Sibbald and Jaycie Dalson and Kwame Agyei and Samiha Mohsen and Safia Yusuf and Clara Juando-Prats and Jory Simpson and Vanja Davidovic and Recai Yilmaz and Abdulmajeed Albeloushi and Mohamed Alhantoobi and Abicumaran Uthamacumaran and Jason Lapointe and Ahmad Alhaj},

year  = {2025},

date = {2025-01-01},

volume = {68},

number = {1suppl1},

pages = {S1-S13},

publisher = {Canadian Journal of Surgery},

abstract = {Background: 

Bibliometric analysis is used to assess and interpret the academic output and impact within a specific field. We aimed to measure the quantity and quality of plastic surgery research conducted by Canadian authors from 1999 to 2023. 

Methods: 

An extensive bibliometric analysis was carried out using the Web of Science Core Collection, retrieving data from 60 leading plastic surgery journals, focusing on original articles and reviews published between 1999 and 2023. The InCites Benchmarking & Analytics platform was used to evaluate the quantity and quality of the publications. The quality was assessed using 2 main metrics: category-normalized citation impact (CNCI) and the percentage of publications in the top quartile of journals based on impact factors. We employed VOSviewer to visualize notable keywords and map collaborative relationships among universities over various periods. 

Results …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{barr2024,

title = {Extracting 3D Prostate Geometry from 2D Optically-Tracked Transrectal Ultrasound Images},

author = {Colton Barr and Leah Groves and Tamas Ungi and D Robert Siemens and Babacar Diao and Ron Kikinis and Parvin Mousavi and Gabor Fichtinger},

year  = {2024},

date = {2024-01-01},

pages = {32-37},

publisher = {IEEE},

abstract = {The technical challenges of traditional transrectal ultrasound-guided prostate biopsy, combined with the limited availability of more advanced prostate imaging techniques, have exacerbated existing differences in prostate cancer outcomes between high-resource and low-resource healthcare settings. The objective of this paper is to improve the tools available to clinicians in low-resource settings by working towards an inexpensive ultrasound-guided prostate biopsy navigation system. The principal contributions detailed here are the design, implementation, and testing of a system capable of generating a 3D model of the prostate from spatially-tracked 2D ultrasound images. The system uses open-source software, low-cost materials, and deep learning to segment and localize cross-sections of the prostate in order to produce a patient-specific 3D prostate model. A user study was performed to evaluate the …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fichtinger2024g,

title = {3D volume reconstruction for pediatric scoliosis evaluation using motion-tracked ultrasound},

author = {Lucas Hintz and Sarah C Nanziri and Sarah Dance and Kochai Jawed and Matthew Oetgen and Tamas Ungi and Gabor Fichtinger and Christopher Schlenger and Kevin Cleary},

url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12928/1292811/3D-volume-reconstruction-for-pediatric-scoliosis-evaluation-using-motion-tracked/10.1117/12.3008629.short},

year  = {2024},

date = {2024-01-01},

volume = {12928},

pages = {223-227},

publisher = {SPIE},

abstract = {We have evaluated AI-segmented 3D spine ultrasound for scoliosis measurement in a feasibility study of pediatric patients enrolled over two months in the orthopedic clinic at Children’s National Hospital. Patients who presented to clinic for scoliosis evaluation were invited to participate and their spines were scanned using the method. Our system consists of three Optitrack cameras which track a Clarius wireless ultrasound probe and infrared marked waistbelt. Proprietary SpineUs software uses neural networks to build a volumetric reproduction of the spine in real-time using a laptop computer. We can approximate the maximal lateral curvature using the transverse process angle of the virtual reconstruction; these angles were compared to those from the radiographic exams for each patient from the same visit. Scans and radiographs from five patients were examined and demonstrate a linear correlation between …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fichtinger2024i,

title = {Three-dimensional navigated mass spectrometry for intraoperative margin assessment during breast cancer surgery},

author = {Martin Kaufmann and Amoon Jamzad and Tamas Ungi and Jessica Rodgers and Teaghan Koster and Yeung Chris and Natasja Janssen and Julie McMullen and Kathryn Solberg and Joanna Cheesman and Kevin Ti Mi Ren and Sonal Varma and Shaila Merchant and Cecil Jay Engel and G Ross Walker and Andrea Gallo and Doris Jabs and Parvin Mousavi and Gabor Fichtinger and John Rudan},

url = {https://scholar.google.com/scholar?cluster=16985799098796735653&hl=en&oi=scholarr},

year  = {2024},

date = {2024-01-01},

volume = {31},

issue = {1},

pages = {S10-S10},

publisher = {SPRINGER},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fichtinger2024f,

title = {Using NURBS for virtual resections in liver surgery planning: a comparative usability study},

author = {Gabriella d'Albenzio and Rebecca Hisey and Dilakshan Srikanthan and Tamas Ungi and Andras Lasso and Davit Aghayan and Gabor Fichtinger and Rafael Palomar},

url = {https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12927/129270Z/Using-NURBS-for-virtual-resections-in-liver-surgery-planning/10.1117/12.3006486.short},

year  = {2024},

date = {2024-01-01},

volume = {12927},

pages = {235-241},

publisher = {SPIE},

abstract = {PURPOSE 

Accurate preoperative planning is crucial for liver resection surgery due to the complex anatomical structures and variations among patients. The need of virtual resections utilizing deformable surfaces presents a promising approach for effective liver surgery planning. However, the range of available surface definitions poses the question of which definition is most appropriate. 

METHODS 

The study compares the use of NURBS and B´ezier surfaces for the definition of virtual resections through a usability study, where 25 participants (19 biomedical researchers and 6 liver surgeons) completed tasks using varying numbers of control points driving surface deformations and different surface types. Specifically, participants aim to perform virtual liver resections using 16 and 9 control points for NURBS and B´ezier surfaces. The goal is to assess whether they can attain an optimal resection plan, effectively …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fichtinger2024e,

title = {ImSpect: Image-driven self-supervised learning for surgical margin evaluation with mass spectrometry},

author = {Laura Connolly and Fahimeh Fooladgar and Amoon Jamzad and Martin Kaufmann and Ayesha Syeda and Kevin Ren and Purang Abolmaesumi and John F Rudan and Doug McKay and Gabor Fichtinger and Parvin Mousavi},

url = {https://link.springer.com/article/10.1007/s11548-024-03106-1},

year  = {2024},

date = {2024-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

pages = {1-8},

publisher = {Springer International Publishing},

abstract = {Purpose 

Real-time assessment of surgical margins is critical for favorable outcomes in cancer patients. The iKnife is a mass spectrometry device that has demonstrated potential for margin detection in cancer surgery. Previous studies have shown that using deep learning on iKnife data can facilitate real-time tissue characterization. However, none of the existing literature on the iKnife facilitate the use of publicly available, state-of-the-art pretrained networks or datasets that have been used in computer vision and other domains. 

Methods 

In a new framework we call ImSpect, we convert 1D iKnife data, captured during basal cell carcinoma (BCC) surgery, into 2D images in order to capitalize on state-of-the-art image classification networks. We also use self-supervision to leverage large amounts of unlabeled, intraoperative data to accommodate the data requirements of these networks. 

Results 

Through extensive ablation …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{fichtinger2024c,

title = {Abstract PO2-23-07: Three-dimensional navigated mass spectrometry for intraoperative margin assessment during breast cancer surgery},

author = {Martin Kaufmann and Amoon Jamzad and Tamas Ungi and Jessica R Rodgers and Teaghan Koster and Chris Yeung and Josh Ehrlich and Alice Santilli and Mark Asselin and Natasja Janssen and Julie McMullen and Kathryn Solberg and Joanna Cheesman and Alessia Di Carlo and Kevin Yi Mi Ren and Sonal Varma and Shaila Merchant and Cecil Jay Engel and G Ross Walker and Andrea Gallo and Doris Jabs and Parvin Mousavi and Gabor Fichtinger and John F Rudan},

url = {https://aacrjournals.org/cancerres/article/84/9_Supplement/PO2-23-07/743683},

year  = {2024},

date = {2024-01-01},

journal = {Cancer Research},

volume = {84},

issue = {9_Supplement},

pages = {PO2-23-07-PO2-23-07},

publisher = {The American Association for Cancer Research},

abstract = {Positive resection margins occur in approximately 25% of breast cancer (BCa) surgeries, requiring re-operation. Margin status is not routinely available during surgery; thus, technologies that identify residual cancer on the specimen or cavity are needed to provide intraoperative decision support that may reduce positive margin rates. Rapid evaporative ionization mass spectrometry (REIMS) is an emerging technique that chemically profiles the plume generated by tissue cauterization to classify the ablated tissue as either cancerous or non-cancerous, on the basis of detected lipid species. Although REIMS can distinguish cancer and non-cancerous breast tissue by the signals generated, it does not indicate the location of the classified tissue in real-time. Our objective was to combine REIMS with spatio-temporal navigation (navigated REIMS), and to compare performance of navigated REIMS with conventional …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{yeung2024,

title = {From quantitative metrics to clinical success: assessing the utility of deep learning for tumor segmentation in breast surgery},

author = {Chris Yeung and Tamas Ungi and Zoe Hu and Amoon Jamzad and Martin Kaufmann and Ross Walker and Shaila Merchant and Cecil Jay Engel and Doris Jabs and John Rudan and Parvin Mousavi and Gabor Fichtinger},

url = {https://link.springer.com/article/10.1007/s11548-024-03133-y},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {International Journal of Computer Assisted Radiology and Surgery},

pages = {1-9},

publisher = {Springer International Publishing},

abstract = {Purpose 

Preventing positive margins is essential for ensuring favorable patient outcomes following breast-conserving surgery (BCS). Deep learning has the potential to enable this by automatically contouring the tumor and guiding resection in real time. However, evaluation of such models with respect to pathology outcomes is necessary for their successful translation into clinical practice. 

Methods 

Sixteen deep learning models based on established architectures in the literature are trained on 7318 ultrasound images from 33 patients. Models are ranked by an expert based on their contours generated from images in our test set. Generated contours from each model are also analyzed using recorded cautery trajectories of five navigated BCS cases to predict margin status. Predicted margins are compared with pathology reports. 

Results 

The best-performing model using both quantitative evaluation and our visual …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{yang2024,

title = {Frame Selection Methods to Streamline Surgical Video Annotation for Tool Detection Tasks},

author = {Jianming Yang and Rebecca Hisey and Joshua Bierbrier and Christine Law and Gabor Fichtinger and Matthew Holden},

year  = {2024},

date = {2024-01-01},

pages = {892-898},

publisher = {IEEE},

abstract = {Given the growing volume of surgical data and the increasing demand for annotation, there is a pressing need to streamline the annotation process for surgical videos. Previously, annotation tools for object detection tasks have greatly evolved, reducing time expense and enhancing ease. There are also many initial frame selection approaches for Artificial Intelligence (AI) assisted annotation tasks to further reduce human effort. However, these methods have rarely been implemented and reported in the context of surgical datasets, especially in cataract surgery datasets. The identification of initial frames to annotate before the use of any tools or algorithms determines annotation efficiency. Therefore, in this paper, we chose to prioritize the development of a method for selecting initial frames to facilitate the subsequent automated annotation process. We propose a customized initial frames selection method based on …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{hashtrudi-zaad2024,

title = {Expert-guided optimization of ultrasound segmentation models for 3D spine imaging},

author = {Kian Hashtrudi-Zaad and Tamas Ungi and Chris Yeung and Zachary Baum and Pavel-Dumitru Cernelev and Anthony N Hage and Christopher Schlenger and Gabor Fichtinger},

year  = {2024},

date = {2024-01-01},

pages = {680-685},

publisher = {IEEE},

abstract = {We explored ultrasound for imaging bones, specifically the spine, as a safer and more accessible alternative to conventional X-ray. We aimed to improve how well deep learning segmentation models filter bone signals from ultrasound frames with the goal of using these segmented images for reconstructing the 3-dimensional spine volume.Our dataset consisted of spatially tracked ultrasound scans from 25 patients. Image frames from these scans were also manually annotated to provide training data for image segmentation deep learning. To find the optimal automatic segmentation method, we assessed five different artificial neural network models and their variations by hyperparameter tuning. Our main contribution is a new approach for model selection, employing an Elo rating system to efficiently rank trained models based on their visual performance as assessed by clinical users. This method addresses the …},

keywords = {},

pubstate = {published},

tppubtype = {article}

}