Riesmeier, Jörg; Lasso, Andras; Pinter, Csaba; Fichtinger, Gabor
DCMQI: An open source library for standardized communication of quantitative image analysis results using DICOM Journal Article
In: 0000.
@article{fichtinger0000g,
title = {DCMQI: An open source library for standardized communication of quantitative image analysis results using DICOM},
author = {Jörg Riesmeier and Andras Lasso and Csaba Pinter and Gabor Fichtinger},
url = {https://core.ac.uk/download/pdf/154882139.pdf},
abstract = {Quantitative analysis of clinical image data is an active area of research that holds promise for precision medicine, early assessment of treatment response, and objective characterization of the disease. Interoperability, data sharing, and the ability to mine the resulting data are of increasing importance, given the explosive growth in the number of quantitative analysis methods being proposed. The Digital Imaging and Communications in Medicine (DICOM) standard is widely adopted for image and metadata in radiology. dcmqi (DICOM for Quantitative Imaging) is a free, open source library that implements conversion of the data stored in commonly used research formats into the standard DICOM representation. dcmqi source code is distributed under BSD-style license. It is freely available as a precompiled binary package for every major operating system, as a Docker image, and as an extension to 3D Slicer. Installation and usage instructions are provided in the GitHub repository at https://github. com/qiicr/dcmqi.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Quantitative analysis of clinical image data is an active area of research that holds promise for precision medicine, early assessment of treatment response, and objective characterization of the disease. Interoperability, data sharing, and the ability to mine the resulting data are of increasing importance, given the explosive growth in the number of quantitative analysis methods being proposed. The Digital Imaging and Communications in Medicine (DICOM) standard is widely adopted for image and metadata in radiology. dcmqi (DICOM for Quantitative Imaging) is a free, open source library that implements conversion of the data stored in commonly used research formats into the standard DICOM representation. dcmqi source code is distributed under BSD-style license. It is freely available as a precompiled binary package for every major operating system, as a Docker image, and as an extension to 3D Slicer. Installation and usage instructions are provided in the GitHub repository at https://github. com/qiicr/dcmqi.
Pinter, Csaba
Novel Mechanism Segments Anatomical Structures for 3D Printing April 27, 2017 Journal Article
In: 0000.
@article{fichtinger0000h,
title = {Novel Mechanism Segments Anatomical Structures for 3D Printing April 27, 2017},
author = {Csaba Pinter},
url = {https://www.kitware.com/novel-mechanism-segments-anatomical-structures-for-3d-printing/},
abstract = {A fundamental task in most aspects of medical image computing is segmentation, ie, delineation of anatomical structures of interest for further processing and quantification. Segmentation can be manual, it can be semi-automatic (through the initialization of an algorithm with limited input), or it can be fully automatic (through an autonomous algorithm). A multitude of software tools and algorithms exist for each type of segmentation, and segmentation has served as the subject of extensive research in the field of medical image computing.
Most commonly, three-dimensional (3D) binary volumes (labelmaps) store segmentation results. Each volume simply indicates whether a volumetric element (voxel) is inside or outside of the structure of interest. Three-dimensional binary volumes are optimal for most processing algorithms. To visualize structures, however, surface models are optimal. Instead of a structured grid of voxels, each surface model consists of a point cloud. Triangles connect the point cloud, which a 3D visualization can illustrate.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
A fundamental task in most aspects of medical image computing is segmentation, ie, delineation of anatomical structures of interest for further processing and quantification. Segmentation can be manual, it can be semi-automatic (through the initialization of an algorithm with limited input), or it can be fully automatic (through an autonomous algorithm). A multitude of software tools and algorithms exist for each type of segmentation, and segmentation has served as the subject of extensive research in the field of medical image computing.
Most commonly, three-dimensional (3D) binary volumes (labelmaps) store segmentation results. Each volume simply indicates whether a volumetric element (voxel) is inside or outside of the structure of interest. Three-dimensional binary volumes are optimal for most processing algorithms. To visualize structures, however, surface models are optimal. Instead of a structured grid of voxels, each surface model consists of a point cloud. Triangles connect the point cloud, which a 3D visualization can illustrate.
Most commonly, three-dimensional (3D) binary volumes (labelmaps) store segmentation results. Each volume simply indicates whether a volumetric element (voxel) is inside or outside of the structure of interest. Three-dimensional binary volumes are optimal for most processing algorithms. To visualize structures, however, surface models are optimal. Instead of a structured grid of voxels, each surface model consists of a point cloud. Triangles connect the point cloud, which a 3D visualization can illustrate.
IORDACHITA, I; SONG, SE; CHO, NB; WHITCOMB, LL; KRIEGER, A; FICHTINGER, G; GUION, P
DEVELOPMENT AND PRELIMINARY EVALUATION OF AN ACTUATED MRI-COMPATIBLE ROBOTIC DEVICE FOR MRI-GUIDED PROSTATE INTERVENTION Journal Article
In: 0000.
@article{fichtinger0000q,
title = {DEVELOPMENT AND PRELIMINARY EVALUATION OF AN ACTUATED MRI-COMPATIBLE ROBOTIC DEVICE FOR MRI-GUIDED PROSTATE INTERVENTION},
author = {I IORDACHITA and SE SONG and NB CHO and LL WHITCOMB and A KRIEGER and G FICHTINGER and P GUION},
url = {https://scholar.google.com/scholar?cluster=18214167030426789194&hl=en&oi=scholarr},
abstract = {This paper reports the design, development, and magnetic resonance imaging (MRI) compatibility evaluation of an actuated transrectal prostate robot for MRI-guided intervention. The robot employs an actuated needle guide with the goal of reducing interventional procedure times and increasing needle placement accuracy. The design of the robot, employing piezo-ceramic-motor actuated needle guide positioning and manual needle insertion, is reported. Results of a MRI compatibility study show no reduction of MRI image signal-to-noise-ratio (SNR) with the motors disabled and a 40% to 60% reduction in SNR with the motors enabled. The addition of radio-frequency (RF) shielding is shown to significantly reduce image SNR degradation due to the presence of the robotic device.© 2010 IEEE.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper reports the design, development, and magnetic resonance imaging (MRI) compatibility evaluation of an actuated transrectal prostate robot for MRI-guided intervention. The robot employs an actuated needle guide with the goal of reducing interventional procedure times and increasing needle placement accuracy. The design of the robot, employing piezo-ceramic-motor actuated needle guide positioning and manual needle insertion, is reported. Results of a MRI compatibility study show no reduction of MRI image signal-to-noise-ratio (SNR) with the motors disabled and a 40% to 60% reduction in SNR with the motors enabled. The addition of radio-frequency (RF) shielding is shown to significantly reduce image SNR degradation due to the presence of the robotic device.© 2010 IEEE.
Kari, Lila; Hall, Walter Light; Buxton, Bill; Principal, Buxton Design; Li, Ming; Schaeffer, Jonathan
Distinguished Seminar Series Journal Article
In: 0000.
@article{fichtinger0000t,
title = {Distinguished Seminar Series},
author = {Lila Kari and Walter Light Hall and Bill Buxton and Buxton Design Principal and Ming Li and Jonathan Schaeffer},
url = {https://scholar.google.com/scholar?cluster=3578342665849253087&hl=en&oi=scholarr},
abstract = {Internet services offered for human use are suffering abuse by programs ('bots, spiders, scrapers, spammers, etc). We mount a defense against such attacks with CAPTCHAs,completely automatic public Turing tests to tell computers and humans apart.'These are special cases ofhuman interactive proofs'(HIPs), a class of security protocols allowing people easily to identify themselves over networks as members of given groups. I will review the five years of evolution of HIP R&D, highlights of the first NSF HIP workshop, and applications of HIPs now in use and on the horizon.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Internet services offered for human use are suffering abuse by programs ('bots, spiders, scrapers, spammers, etc). We mount a defense against such attacks with CAPTCHAs,completely automatic public Turing tests to tell computers and humans apart.'These are special cases ofhuman interactive proofs'(HIPs), a class of security protocols allowing people easily to identify themselves over networks as members of given groups. I will review the five years of evolution of HIP R&D, highlights of the first NSF HIP workshop, and applications of HIPs now in use and on the horizon.
Frivold, GP; Alcalde, J; Alcázar, JL; Alezra, D; Anscher, BM; Anscher, MS; Bae, K; Baikadi, M; Beriwal, S; Bernard, DA; Bhatia, S; Bhatnagar, A; Blasko, JC; Bradley, KA; Burdette, EC; Byhardt, RW; Cambeiro, M; Cantor, A; Chauveinc, L; Chu, JCH; Cohen, G; Concejo, C; Cosset, JM; Crook, J; Das, KJM; Das, RK; Datta, NR; Santos, J De Los; Dean, J; Deguchi, T; Dickler, A; Donat, M; Duchesne, GM; Dunning, BF; Eastham, J; Edwards, RP; Eijkenboom, WMH; Elliott, K; Evans, WK; Falkenberg, E; Falkson, C; Faul, C; Ferry, D; Fichtinger, G; Firat, S; Garrán, C; Garza, R; Gerszten, K; Gillan, C; Gillin, MT; Gotoh, T; Gressen, E; Greven, K; Griem, KL; Gupta, A; Gwede, CK
Flam, T, 122 Foley, DW, 152 Foster, GP, 262 Journal Article
In: Heron, vol. 500, pp. 118, 0000.
@article{fichtinger0000v,
title = {Flam, T, 122 Foley, DW, 152 Foster, GP, 262},
author = {GP Frivold and J Alcalde and JL Alcázar and D Alezra and BM Anscher and MS Anscher and K Bae and M Baikadi and S Beriwal and DA Bernard and S Bhatia and A Bhatnagar and JC Blasko and KA Bradley and EC Burdette and RW Byhardt and M Cambeiro and A Cantor and L Chauveinc and JCH Chu and G Cohen and C Concejo and JM Cosset and J Crook and KJM Das and RK Das and NR Datta and J De Los Santos and J Dean and T Deguchi and A Dickler and M Donat and GM Duchesne and BF Dunning and J Eastham and RP Edwards and WMH Eijkenboom and K Elliott and WK Evans and E Falkenberg and C Falkson and C Faul and D Ferry and G Fichtinger and S Firat and C Garrán and R Garza and K Gerszten and C Gillan and MT Gillin and T Gotoh and E Gressen and K Greven and KL Griem and A Gupta and CK Gwede},
url = {https://scholar.google.com/scholar?cluster=13867110131218914908&hl=en&oi=scholarr},
journal = {Heron},
volume = {500},
pages = {118},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Fichtinger, Gabor
MR Image Overlay: an Augmented Reality System for Needle Guidance Journal Article
In: 0000.
@article{fichtinger0000x,
title = {MR Image Overlay: an Augmented Reality System for Needle Guidance},
author = {Gabor Fichtinger},
url = {https://scholar.google.com/scholar?cluster=14037511090116778528&hl=en&oi=scholarr},
abstract = {MRI-guided percutaneous needle-based surgery has become part of routine clinical practice. There are millions of these procedures performed in Canada. The conventional MRI-guided needle intervention is usually performed with the primary goal of navigating a needle to a target while sparing healthy and/or critical structures. Potential limitations of conventional unassisted free-hand needle placement include the physician's ability to align and maintain the correct trajectory and angle toward a target, especially in case of deep targets. In contemporary practice, images are displayed on the operator's 2D console only outside the treatment room, where the physician plans the intervention. Then the physician enters the room, mentally registers the images with the anatomy of the actual patient, and uses hand-eye coordination to execute the planned intervention. Previous concept has been shown and preliminary results discussed from demonstrated MRI-guided needle intervention using an augmented reality 2D image overlay system in a closed configuration 1.5T MRI scanner. However, the limited availability of interventional MR imaging systems and the length of time of MR-guided interventions have been limiting factors in the past. This dissertation addresses topics related to evaluating and developing the 2D augmented reality system, the assistance device for MRI-guided needle interventions. This research effort has primarily focused on developing a new adjustable 2D MR image overlay system and validating the previous 2D image overlay system in the clinical environment. The adjustable system requirement is to overcome the oblique …},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
MRI-guided percutaneous needle-based surgery has become part of routine clinical practice. There are millions of these procedures performed in Canada. The conventional MRI-guided needle intervention is usually performed with the primary goal of navigating a needle to a target while sparing healthy and/or critical structures. Potential limitations of conventional unassisted free-hand needle placement include the physician's ability to align and maintain the correct trajectory and angle toward a target, especially in case of deep targets. In contemporary practice, images are displayed on the operator's 2D console only outside the treatment room, where the physician plans the intervention. Then the physician enters the room, mentally registers the images with the anatomy of the actual patient, and uses hand-eye coordination to execute the planned intervention. Previous concept has been shown and preliminary results discussed from demonstrated MRI-guided needle intervention using an augmented reality 2D image overlay system in a closed configuration 1.5T MRI scanner. However, the limited availability of interventional MR imaging systems and the length of time of MR-guided interventions have been limiting factors in the past. This dissertation addresses topics related to evaluating and developing the 2D augmented reality system, the assistance device for MRI-guided needle interventions. This research effort has primarily focused on developing a new adjustable 2D MR image overlay system and validating the previous 2D image overlay system in the clinical environment. The adjustable system requirement is to overcome the oblique …
Pinter, Csaba; Olding, Tim; Schreiner, L John; Fichtinger, Gabor
Using Fuzzy Logics to Determine Optimal Oversampling Factor for Rasterizing RT Structures in DVH Computation Journal Article
In: 0000.
@article{fichtinger0000y,
title = {Using Fuzzy Logics to Determine Optimal Oversampling Factor for Rasterizing RT Structures in DVH Computation},
author = {Csaba Pinter and Tim Olding and L John Schreiner and Gabor Fichtinger},
url = {http://perk.cs.queensu.ca/sites/perkd7.cs.queensu.ca/files/Pinter2016-manuscript.pdf},
abstract = {Purpose
Rasterizing three-dimensional surfaces into binary image volumes is a frequently performed 10 operation in radiation therapy (RT) workflows. For example, in both the clinic and research, dose-volume histograms (DVH) are used to evaluate the quality of an RT treatment plan. To calculate a DVH, the 3D surfaces (ie RT structures, usually targets and organs at risk) need to be rasterized into binary volumes. The details of this step may significantly influence the output DVH, so special attention is needed when setting up the rasterization parameters.
Methods
An effective way of improving the quality of the 15 rasterized volume (ie increasing similarity between that and the original structure) is to apply oversampling on the reference volume to simply increase the resolution of the output structure binary volume. However, increasing the oversampling factor significantly raises the computational and storage cost. This paper proposes a fuzzy-based automatic calculation of the oversampling factor so that higher values are only used in cases where necessary and beneficial. A fuzzy inference system was introduced 20 that applies fuzzy rules to determine an optimal oversampling factor based on two measures: relative structure size and structure complexity.
Results
The proposed algorithm was used to automatically},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Purpose
Rasterizing three-dimensional surfaces into binary image volumes is a frequently performed 10 operation in radiation therapy (RT) workflows. For example, in both the clinic and research, dose-volume histograms (DVH) are used to evaluate the quality of an RT treatment plan. To calculate a DVH, the 3D surfaces (ie RT structures, usually targets and organs at risk) need to be rasterized into binary volumes. The details of this step may significantly influence the output DVH, so special attention is needed when setting up the rasterization parameters.
Methods
An effective way of improving the quality of the 15 rasterized volume (ie increasing similarity between that and the original structure) is to apply oversampling on the reference volume to simply increase the resolution of the output structure binary volume. However, increasing the oversampling factor significantly raises the computational and storage cost. This paper proposes a fuzzy-based automatic calculation of the oversampling factor so that higher values are only used in cases where necessary and beneficial. A fuzzy inference system was introduced 20 that applies fuzzy rules to determine an optimal oversampling factor based on two measures: relative structure size and structure complexity.
Results
The proposed algorithm was used to automatically
Rasterizing three-dimensional surfaces into binary image volumes is a frequently performed 10 operation in radiation therapy (RT) workflows. For example, in both the clinic and research, dose-volume histograms (DVH) are used to evaluate the quality of an RT treatment plan. To calculate a DVH, the 3D surfaces (ie RT structures, usually targets and organs at risk) need to be rasterized into binary volumes. The details of this step may significantly influence the output DVH, so special attention is needed when setting up the rasterization parameters.
Methods
An effective way of improving the quality of the 15 rasterized volume (ie increasing similarity between that and the original structure) is to apply oversampling on the reference volume to simply increase the resolution of the output structure binary volume. However, increasing the oversampling factor significantly raises the computational and storage cost. This paper proposes a fuzzy-based automatic calculation of the oversampling factor so that higher values are only used in cases where necessary and beneficial. A fuzzy inference system was introduced 20 that applies fuzzy rules to determine an optimal oversampling factor based on two measures: relative structure size and structure complexity.
Results
The proposed algorithm was used to automatically
Fichtinger, Gabor; Martel, Anne; Peters, Terry
Medical image computing and computer-assisted intervention: 14th international conference; proceedings Journal Article
In: 0000.
@article{fichtinger0000z,
title = {Medical image computing and computer-assisted intervention: 14th international conference; proceedings},
author = {Gabor Fichtinger and Anne Martel and Terry Peters},
url = {https://scholar.google.com/scholar?cluster=13217379728334074159&hl=en&oi=scholarr},
publisher = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Fichtinger, Gábor
Robotically assisted, image guided planning and execution of percutaneous therapies Journal Article
In: 0000.
@article{fichtinger0000_27,
title = {Robotically assisted, image guided planning and execution of percutaneous therapies},
author = {Gábor Fichtinger},
url = {https://scholar.google.com/scholar?cluster=3545029094221762276&hl=en&oi=scholarr},
abstract = {The planning and execution of percutaneous therapies are very diverse. We investigated those that make use of a localization frame. When using a so called stereotacic frame, a base is rigidly attached to the patient that provides the coordinate system (Figure 1). Execution can be done using robots when the localization frame is attached rigidly to the robot itself.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The planning and execution of percutaneous therapies are very diverse. We investigated those that make use of a localization frame. When using a so called stereotacic frame, a base is rigidly attached to the patient that provides the coordinate system (Figure 1). Execution can be done using robots when the localization frame is attached rigidly to the robot itself.
U-Thainual, P; Fritz, J; Moonjaita, C; Ungi, T; Flammang, A; Carrino, JA; Fichtinger, G; Iordachita, I
MR Image Overlay Guidance System (MR-IOS): System Evaluation for Clinical Use Journal Article
In: 0000.
@article{fichtinger0000_28,
title = {MR Image Overlay Guidance System (MR-IOS): System Evaluation for Clinical Use},
author = {P U-Thainual and J Fritz and C Moonjaita and T Ungi and A Flammang and JA Carrino and G Fichtinger and I Iordachita},
url = {http://perk.cs.queensu.ca/sites/perk.cs.queensu.ca/files/LE-477A_UThainual_Paweena.pdf},
abstract = {Purpose
A clinical augmented reality guidance system was developed for MR imaging guided musculoskeletal and spine interventions (Magnetic Resonance Image Overlay System, MR-IOS)[1]. The MR-IOS was used in conjunction with a laboratory system “Perk Station Platform, PSP”; a training platform for percutaneous needle based interventions [2]. The purpose of this study was to assess the MR environment compatibility, technical accuracy, technical efficacy and operator performance of the MR-IOS.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Purpose
A clinical augmented reality guidance system was developed for MR imaging guided musculoskeletal and spine interventions (Magnetic Resonance Image Overlay System, MR-IOS)[1]. The MR-IOS was used in conjunction with a laboratory system “Perk Station Platform, PSP”; a training platform for percutaneous needle based interventions [2]. The purpose of this study was to assess the MR environment compatibility, technical accuracy, technical efficacy and operator performance of the MR-IOS.
A clinical augmented reality guidance system was developed for MR imaging guided musculoskeletal and spine interventions (Magnetic Resonance Image Overlay System, MR-IOS)[1]. The MR-IOS was used in conjunction with a laboratory system “Perk Station Platform, PSP”; a training platform for percutaneous needle based interventions [2]. The purpose of this study was to assess the MR environment compatibility, technical accuracy, technical efficacy and operator performance of the MR-IOS.
Fichtinger, Gabor; Iordachita, Iulian
Paweena U-Thainual, Jan Fritz, Choladawan Moonjaita, Tamas Ungi, Aaron Flammang, John A. Carrino Journal Article
In: 0000.
@article{fichtinger0000_29,
title = {Paweena U-Thainual, Jan Fritz, Choladawan Moonjaita, Tamas Ungi, Aaron Flammang, John A. Carrino},
author = {Gabor Fichtinger and Iulian Iordachita},
url = {http://perk.cs.queensu.ca/sites/perkd7.cs.queensu.ca/files/10.1007_s11548-012-0788-0.pdf},
abstract = {Purpose A clinical augmented reality guidance system was developed for MRI-guided musculoskeletal interventions Magnetic Resonance Image Overlay System (MR-IOS). The purpose of this study was to assess MRI compatibility, system accuracy, technical efficacy, and operator performance of the MR-IOS.
Methods and materials The impact of the MR-IOS on the MR environment was assessed by measuring image quality with signal-to-noise ratio (SNR) and signal intensity uniformity with the system in various on/off states. The system accuracy was assessed with an in-room preclinical experi-},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Purpose A clinical augmented reality guidance system was developed for MRI-guided musculoskeletal interventions Magnetic Resonance Image Overlay System (MR-IOS). The purpose of this study was to assess MRI compatibility, system accuracy, technical efficacy, and operator performance of the MR-IOS.
Methods and materials The impact of the MR-IOS on the MR environment was assessed by measuring image quality with signal-to-noise ratio (SNR) and signal intensity uniformity with the system in various on/off states. The system accuracy was assessed with an in-room preclinical experi-
Methods and materials The impact of the MR-IOS on the MR environment was assessed by measuring image quality with signal-to-noise ratio (SNR) and signal intensity uniformity with the system in various on/off states. The system accuracy was assessed with an in-room preclinical experi-
Fichtinger, G; Deguet, A; Masamune, K; Balogh, E; Fischer, G; Mathieu, H; Taylor, RH; Fayad, L; deOliveira, M; Zinreich, SJ
Needle insertion in CT Scanner with Image Overlay-Phantom and Cadaver Studies Journal Article
In: 0000.
@article{fichtinger0000_30,
title = {Needle insertion in CT Scanner with Image Overlay-Phantom and Cadaver Studies},
author = {G Fichtinger and A Deguet and K Masamune and E Balogh and G Fischer and H Mathieu and RH Taylor and L Fayad and M deOliveira and SJ Zinreich},
url = {https://www.researchgate.net/profile/Emese-Balogh-4/publication/250727227_Needle_insertion_in_CT_Scanner_with_Image_Overlay_-_Phantom_and_Cadaver_Studies/links/0deec529c3a9b9c285000000/Needle-insertion-in-CT-Scanner-with-Image-Overlay-Phantom-and-Cadaver-Studies.pdf},
abstract = {We present an image overlay system that assists in surgical needle insertions inside conventional CT scanners. The device is mounted on the gantry of the CT scanner and consists of a flat LCD display and a semi-transparent mirror. In the preoperative calibration process the overlay system and the imaging plane of the scanner are registered. As a result, looking at the patient through the mirror, the CT image appears to be floating inside the patient with correct size and position providing the physician with two-dimensional” X-ray vision” to guide needle placement procedures. The physician inserts the needle following the optimal path identified in the CT image that is rendered on the LCD and thereby reflected in the mirror. The system promises to increase needle placement accuracy and also to reduce X-ray dose, patient discomfort, and procedure time by eliminating faulty insertion attempts. We report phantom studies and cadaver experiments in several clinical applications.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We present an image overlay system that assists in surgical needle insertions inside conventional CT scanners. The device is mounted on the gantry of the CT scanner and consists of a flat LCD display and a semi-transparent mirror. In the preoperative calibration process the overlay system and the imaging plane of the scanner are registered. As a result, looking at the patient through the mirror, the CT image appears to be floating inside the patient with correct size and position providing the physician with two-dimensional” X-ray vision” to guide needle placement procedures. The physician inserts the needle following the optimal path identified in the CT image that is rendered on the LCD and thereby reflected in the mirror. The system promises to increase needle placement accuracy and also to reduce X-ray dose, patient discomfort, and procedure time by eliminating faulty insertion attempts. We report phantom studies and cadaver experiments in several clinical applications.
Krieger, Axel; Song, S; Cho, Nathan Bongjoon; Guion, Peter; Iordachita, Iulian; Fichtinger, Gabor; Whitcomb, Louis L
Development and Preliminary Evaluation of a MRI-guided Transrectal Prostate Intervention Journal Article
In: 0000.
@article{fichtinger0000_31,
title = {Development and Preliminary Evaluation of a MRI-guided Transrectal Prostate Intervention},
author = {Axel Krieger and S Song and Nathan Bongjoon Cho and Peter Guion and Iulian Iordachita and Gabor Fichtinger and Louis L Whitcomb},
url = {https://www.academia.edu/download/42878814/Development_and_Preliminary_Evaluation_o20160220-17499-1vaqu44.pdf},
abstract = {Numerous studies have shown that transrectal ultrasound (TRUS)-guided prostate biopsy fails to detect cancer in significant numbers, since contemporary ultrasound cannot resolve target lesions [1]. Improved biopsy targeting with magnetic resonance imaging (MRI) could potentially overcome the shortcomings of ultrasound for the diagnosis and local therapy for prostate cancer. To utilize such advantages, a number of MRI-compatible prostate intervention systems were introduced. However, previously reported systems require the patient to be removed from the MRI scanner during the interventional procedure. A fully actuated robot, however, enables both imaging and interventional procedures to be performed entirely inside the scanner without removing the patient. Moreover, a fully actuated robot could simplify and speed up the procedure; allow for real-time needle insertion visualization; enable detection of prostate deformation, misalignment, and deflection of the needle; and allow for onthe-spot corrections to needle placements.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Numerous studies have shown that transrectal ultrasound (TRUS)-guided prostate biopsy fails to detect cancer in significant numbers, since contemporary ultrasound cannot resolve target lesions [1]. Improved biopsy targeting with magnetic resonance imaging (MRI) could potentially overcome the shortcomings of ultrasound for the diagnosis and local therapy for prostate cancer. To utilize such advantages, a number of MRI-compatible prostate intervention systems were introduced. However, previously reported systems require the patient to be removed from the MRI scanner during the interventional procedure. A fully actuated robot, however, enables both imaging and interventional procedures to be performed entirely inside the scanner without removing the patient. Moreover, a fully actuated robot could simplify and speed up the procedure; allow for real-time needle insertion visualization; enable detection of prostate deformation, misalignment, and deflection of the needle; and allow for onthe-spot corrections to needle placements.
Rivaz, Hassan; Foroughi, Pezhman; Boctor, Emad; Zellars, Richard; Fichtinger, Gabor; Hager, Gregory
High Resolution Ultrasound Elastography: a Dynamic Programming Approach Journal Article
In: MICCAI 2007 Workshop Proceedings, pp. 113, 0000.
@article{fichtinger0000_32,
title = {High Resolution Ultrasound Elastography: a Dynamic Programming Approach},
author = {Hassan Rivaz and Pezhman Foroughi and Emad Boctor and Richard Zellars and Gabor Fichtinger and Gregory Hager},
url = {https://www.researchgate.net/profile/Poul-Nielsen-2/publication/224027899_Computational_biomechanics_of_the_breast_the_importance_of_the_reference_state/links/02bfe51326862be08a000000/Computational-biomechanics-of-the-breast-the-importance-of-the-reference-state.pdf#page=118},
journal = {MICCAI 2007 Workshop Proceedings},
pages = {113},
abstract = {This paper presents a 2D strain estimation technique that minimizes a cost function using dynamic programming (DP). The cost function incorporates similarity of echo amplitudes and displacement continuity. The method is capable of creating high quality elastograms at the same resolution as the original RF data. Since tissue deformations are smooth, the incorporation of the smoothness into the cost function results in reduced decorrelation noise. Freehand palpation elastography shows that the method is more robust to signal decorrelation (caused by scatterer motion in high axial compression and non-axial motions of the probe) compared to the correlation techniques. In-vitro experiments depict that the method is able to detect small hard lesions. The method is also suitable for real time elastography.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper presents a 2D strain estimation technique that minimizes a cost function using dynamic programming (DP). The cost function incorporates similarity of echo amplitudes and displacement continuity. The method is capable of creating high quality elastograms at the same resolution as the original RF data. Since tissue deformations are smooth, the incorporation of the smoothness into the cost function results in reduced decorrelation noise. Freehand palpation elastography shows that the method is more robust to signal decorrelation (caused by scatterer motion in high axial compression and non-axial motions of the probe) compared to the correlation techniques. In-vitro experiments depict that the method is able to detect small hard lesions. The method is also suitable for real time elastography.
Rivaz, Hassan; Boctor, Emad; Fichtinger, Gabor
Ultrasound Speckle Detection Journal Article
In: 0000.
@article{fichtinger0000_33,
title = {Ultrasound Speckle Detection},
author = {Hassan Rivaz and Emad Boctor and Gabor Fichtinger},
url = {https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=444ad2671e8c5046cc3ba8e198c532abe14177c8},
abstract = {Speckle detection is essential in many areas of quantitative ultrasound. In this work, speckle is characterized with R= SNR and S= skewness of the amplitude of the ultrasound signal data A. Different powers of A can be used to calculate R and S. Prager et al.[1] proposed a method for finding the optimum power value, which then was further scrutinized [2]. We propose using two different powers of A in R and S, and perform a large number of computer simulations to find these optimal values.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Speckle detection is essential in many areas of quantitative ultrasound. In this work, speckle is characterized with R= SNR and S= skewness of the amplitude of the ultrasound signal data A. Different powers of A can be used to calculate R and S. Prager et al.[1] proposed a method for finding the optimum power value, which then was further scrutinized [2]. We propose using two different powers of A in R and S, and perform a large number of computer simulations to find these optimal values.
Xu, Sheng; Fichtinger, Gabor
Volumetric Reconstruction from Projected Images Journal Article
In: 0000.
@article{fichtinger0000_34,
title = {Volumetric Reconstruction from Projected Images},
author = {Sheng Xu and Gabor Fichtinger},
url = {https://scholar.google.com/scholar?cluster=1237346242502800244&hl=en&oi=scholarr},
abstract = {[METHODS]
After the silhouettes are drawn in each 2D image, the contours are digitized, filled, and pixelized. When the system goes operational or real patients, the silhouettes will be drawn by the physicians. The resulting binary image contains pixels of value 0 that correspond to the background and pixels of value 1 that correspond to the inside of the silhouette. Fluoroscopic images are typically used at their original resolution, but one may consider re-sampling when speed becomes a critical issue in intra-operative treatment planning. For simplicity, we reconstruct one object at a time.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
[METHODS]
After the silhouettes are drawn in each 2D image, the contours are digitized, filled, and pixelized. When the system goes operational or real patients, the silhouettes will be drawn by the physicians. The resulting binary image contains pixels of value 0 that correspond to the background and pixels of value 1 that correspond to the inside of the silhouette. Fluoroscopic images are typically used at their original resolution, but one may consider re-sampling when speed becomes a critical issue in intra-operative treatment planning. For simplicity, we reconstruct one object at a time.
After the silhouettes are drawn in each 2D image, the contours are digitized, filled, and pixelized. When the system goes operational or real patients, the silhouettes will be drawn by the physicians. The resulting binary image contains pixels of value 0 that correspond to the background and pixels of value 1 that correspond to the inside of the silhouette. Fluoroscopic images are typically used at their original resolution, but one may consider re-sampling when speed becomes a critical issue in intra-operative treatment planning. For simplicity, we reconstruct one object at a time.
Tokuda, Junichi; Fischer, Gregory S; Csoma, Csaba; Gobbi, David G; Blevins, Jack; Fichtinger, Gabor; Burdette, Clif; Tempany, Clare M; Hata, Nobuhiko
Software/Hardware Integration for MRI-guided Robotic Prostate Intervention using Open IGT Link Journal Article
In: 0000.
@article{fichtinger0000_35,
title = {Software/Hardware Integration for MRI-guided Robotic Prostate Intervention using Open IGT Link},
author = {Junichi Tokuda and Gregory S Fischer and Csaba Csoma and David G Gobbi and Jack Blevins and Gabor Fichtinger and Clif Burdette and Clare M Tempany and Nobuhiko Hata},
url = {https://www.na-mic.org/w/img_auth.php/9/9c/Miccaiws-tokuda.pdf},
abstract = {We propose a software and hardware integration strategy for MRI-guided robotic prostate intervention using an open network communication protocol. In the MRI-guided robotic intervention, the robot, navigation software and MRI scanner communicate one to another via Ethernet to exchange various data eg robot position, commands and MR images. Since the components were developed in the different sites including academic and industrial in our research partnership, establishing interoperativity among them with standardized communication protocol was essential in the collaborative development. As a key technology for the collaboration, we developed a new open network protocol called Open IGT Link. The specification of the protocol is simple enough for the developers to implement the interface to any kinds of software including embedded system, but extensible to transfer any types of data for image guided application in the standardized way. We report our system integration for MRI-guided robotic prostate intervention using Open IGT Link.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We propose a software and hardware integration strategy for MRI-guided robotic prostate intervention using an open network communication protocol. In the MRI-guided robotic intervention, the robot, navigation software and MRI scanner communicate one to another via Ethernet to exchange various data eg robot position, commands and MR images. Since the components were developed in the different sites including academic and industrial in our research partnership, establishing interoperativity among them with standardized communication protocol was essential in the collaborative development. As a key technology for the collaboration, we developed a new open network protocol called Open IGT Link. The specification of the protocol is simple enough for the developers to implement the interface to any kinds of software including embedded system, but extensible to transfer any types of data for image guided application in the standardized way. We report our system integration for MRI-guided robotic prostate intervention using Open IGT Link.
Barr, Colton
SlicerChat: Building a Local Chatbot for 3D Slicer Unpublished Forthcoming
Forthcoming.
@unpublished{nokey,
title = {SlicerChat: Building a Local Chatbot for 3D Slicer},
author = {Colton Barr},
url = {https://labs.cs.queensu.ca/perklab/wp-content/uploads/sites/3/2024/06/SlicerChat_2024.pdf},
keywords = {},
pubstate = {forthcoming},
tppubtype = {unpublished}
}
Yang, Jianming; Hisey, Rebecca; Bierbrier, Joshua; Fichtinger, Gabor; Law, Christine; Holden, Matthew
Frame Selection Methods to Streamline Surgical Video Annotation for Tool Detection Tasks Proceedings Forthcoming
Forthcoming.
@proceedings{nokey,
title = {Frame Selection Methods to Streamline Surgical Video Annotation for Tool Detection Tasks},
author = {Jianming Yang and Rebecca Hisey and Joshua Bierbrier and Gabor Fichtinger and Christine Law and Matthew Holden},
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 feature
clustering and compare it to commonly used temporal selection
methods. In each method, initial frames from cataract surgery
videos are selected to train a surgical tool detection model.
The model assists in the automated annotation process by
predicting bounding boxes for the surgery video objects in the
remaining frames. Evaluations of these methods are based on
how many edits users need to perform when annotating the
initial frames and how many edits users are expected to perform
to correct all predictions. Additionally, the total annotation cost
for each method is compared. Results indicate that on average,
the proposed cluster-based approach requires the fewest total
edits and exhibits the lowest total annotation cost compared
to conventional methods. These findings highlight a promising
direction for developing a complete application, featuring
streamlined AI-assisted annotation processes for surgical tool
detection tasks.},
keywords = {},
pubstate = {forthcoming},
tppubtype = {proceedings}
}
—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 feature
clustering and compare it to commonly used temporal selection
methods. In each method, initial frames from cataract surgery
videos are selected to train a surgical tool detection model.
The model assists in the automated annotation process by
predicting bounding boxes for the surgery video objects in the
remaining frames. Evaluations of these methods are based on
how many edits users need to perform when annotating the
initial frames and how many edits users are expected to perform
to correct all predictions. Additionally, the total annotation cost
for each method is compared. Results indicate that on average,
the proposed cluster-based approach requires the fewest total
edits and exhibits the lowest total annotation cost compared
to conventional methods. These findings highlight a promising
direction for developing a complete application, featuring
streamlined AI-assisted annotation processes for surgical tool
detection tasks.
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 feature
clustering and compare it to commonly used temporal selection
methods. In each method, initial frames from cataract surgery
videos are selected to train a surgical tool detection model.
The model assists in the automated annotation process by
predicting bounding boxes for the surgery video objects in the
remaining frames. Evaluations of these methods are based on
how many edits users need to perform when annotating the
initial frames and how many edits users are expected to perform
to correct all predictions. Additionally, the total annotation cost
for each method is compared. Results indicate that on average,
the proposed cluster-based approach requires the fewest total
edits and exhibits the lowest total annotation cost compared
to conventional methods. These findings highlight a promising
direction for developing a complete application, featuring
streamlined AI-assisted annotation processes for surgical tool
detection tasks.
Yang, Jianming; Hisey, Rebecca; Bierbrier, Joshua; Fichtinger, Gabor; Law, Christine; Holden, Matthew
Frame Selection Methods to Streamline Surgical Video Annotation for Tool Detection Tasks Conference Forthcoming
IEEE, Forthcoming.
@conference{nokey,
title = {Frame Selection Methods to Streamline Surgical Video Annotation for Tool Detection Tasks},
author = {Jianming Yang and Rebecca Hisey and Joshua Bierbrier and Gabor Fichtinger and Christine Law and Matthew Holden},
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 feature
clustering and compare it to commonly used temporal selection
methods. In each method, initial frames from cataract surgery
videos are selected to train a surgical tool detection model.
The model assists in the automated annotation process by
predicting bounding boxes for the surgery video objects in the
remaining frames. Evaluations of these methods are based on
how many edits users need to perform when annotating the
initial frames and how many edits users are expected to perform
to correct all predictions. Additionally, the total annotation cost
for each method is compared. Results indicate that on average,
the proposed cluster-based approach requires the fewest total
edits and exhibits the lowest total annotation cost compared
to conventional methods. These findings highlight a promising
direction for developing a complete application, featuring
streamlined AI-assisted annotation processes for surgical tool
detection tasks.},
keywords = {},
pubstate = {forthcoming},
tppubtype = {conference}
}
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 feature
clustering and compare it to commonly used temporal selection
methods. In each method, initial frames from cataract surgery
videos are selected to train a surgical tool detection model.
The model assists in the automated annotation process by
predicting bounding boxes for the surgery video objects in the
remaining frames. Evaluations of these methods are based on
how many edits users need to perform when annotating the
initial frames and how many edits users are expected to perform
to correct all predictions. Additionally, the total annotation cost
for each method is compared. Results indicate that on average,
the proposed cluster-based approach requires the fewest total
edits and exhibits the lowest total annotation cost compared
to conventional methods. These findings highlight a promising
direction for developing a complete application, featuring
streamlined AI-assisted annotation processes for surgical tool
detection tasks.
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 feature
clustering and compare it to commonly used temporal selection
methods. In each method, initial frames from cataract surgery
videos are selected to train a surgical tool detection model.
The model assists in the automated annotation process by
predicting bounding boxes for the surgery video objects in the
remaining frames. Evaluations of these methods are based on
how many edits users need to perform when annotating the
initial frames and how many edits users are expected to perform
to correct all predictions. Additionally, the total annotation cost
for each method is compared. Results indicate that on average,
the proposed cluster-based approach requires the fewest total
edits and exhibits the lowest total annotation cost compared
to conventional methods. These findings highlight a promising
direction for developing a complete application, featuring
streamlined AI-assisted annotation processes for surgical tool
detection tasks.