Profile – Perk Lab

Zachary Baum

Graduate student (Masters)

School of Computing

Queen's University

Zachary (Zac) started in the Perk Lab as 2nd-year Biomedical Computing undergraduate student and completed his undergraduate degree (2017) and MSc (2019) in the Perk Lab.

His research focuses are in Computer-Assisted Surgery and Guided Interventions, and he specializes in the use of augmented reality (AR) and holographic visualizations for surgical training and planning.

Ungi, Tamas; Greer, Hastings; Sunderland, Kyle R.; Wu, Victoria; Baum, Zachary M C; Schlenger, Christopher; Oetgen, Matthew; Cleary, Kevin; Aylward, Stephen; Fichtinger, Gabor

Automatic spine ultrasound segmentation for scoliosis visualization and measurement Journal Article

In: IEEE Transactions on Biomedical Engineering, vol. 67, no. 11, pp. 3234 - 3241, 2020.

Abstract | Links | BibTeX

@article{Ungi2020,

title = {Automatic spine ultrasound segmentation for scoliosis visualization and measurement},

author = {Tamas Ungi and Hastings Greer and Kyle R. Sunderland and Victoria Wu and Zachary M C Baum and Christopher Schlenger and Matthew Oetgen and Kevin Cleary and Stephen Aylward and Gabor Fichtinger},

url = {https://ieeexplore.ieee.org/document/9034149

https://labs.cs.queensu.ca/perklab/wp-content/uploads/sites/3/2024/02/Ungi2020.pdf},

doi = {10.1109/TBME.2020.2980540},

year  = {2020},

date = {2020-03-01},

urldate = {2020-03-01},

journal = {IEEE Transactions on Biomedical Engineering},

volume = {67},

number = {11},

pages = {3234 - 3241},

abstract = {<p>\emph{Objective:} Integrate tracked ultrasound and AI methods to provide a safer and more accessible alternative to X-ray for scoliosis measurement. We propose automatic ultrasound segmentation for 3-dimensional spine visualization and scoliosis measurement to address difficulties in using ultrasound for spine imaging. \emph{Methods:} We trained a convolutional neural network for spine segmentation on ultrasound scans using data from eight healthy adult volunteers. We tested the trained network on eight pediatric patients. We evaluated image segmentation and 3-dimensional volume reconstruction for scoliosis measurement. \emph{Results:} As expected, fuzzy segmentation metrics reduced when trained networks were translated from healthy volunteers to patients. Recall decreased from 0.72 to 0.64 (8.2% decrease), and precision from 0.31 to 0.27 (3.7% decrease). However, after finding optimal thresholds for prediction maps, binary segmentation metrics performed better on patient data. Recall decreased from 0.98 to 0.97 (1.6% decrease), and precision from 0.10 to 0.06 (4.5% decrease). Segmentation prediction maps were reconstructed to 3-dimensional volumes and scoliosis was measured in all patients. Measurement in these reconstructions took less than 1 minute and had a maximum error of 2.2° compared to X-ray. \emph{Conclusion:} automatic spine segmentation makes scoliosis measurement both efficient and accurate in tracked ultrasound scans. \emph{Significance:} Automatic segmentation may overcome the limitations of tracked ultrasound that so far prevented its use as an alternative of X-ray in scoliosis measurement.</p>},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

Baum, Zachary M C

AUGMENTED REALITY TRAINING PLATFORM FOR PLACEMENT OF NEUROSURGICAL BURR HOLES Masters Thesis

Queen’s University, Kingston, ON, 2019.

Abstract | Links | BibTeX

@mastersthesis{Baum2019c,

title = {AUGMENTED REALITY TRAINING PLATFORM FOR PLACEMENT OF NEUROSURGICAL BURR HOLES},

author = {Zachary M C Baum},

url = {http://hdl.handle.net/1974/26123

https://labs.cs.queensu.ca/perklab/wp-content/uploads/sites/3/2024/02/Baum2019c.pdf},

year  = {2019},

date = {2019-04-01},

urldate = {2019-04-01},

volume = {Masters},

address = {Kingston, ON},

school = {Queen’s University},

abstract = {<p>Augmented reality has been used in neurosurgery to aid in the visualization of lesions, though it has not been widely adopted for simulation-based neurosurgical training. This work aims to determine if augmented reality can improve identification of drill location and drill angle for neurosurgical procedures and to define objective metrics for assessing trainee performance.<br /> 

An augmented reality visualization system was developed using the Microsoft HoloLens. Trainee performance metrics were defined and validated intra-operatively in fifteen neurosurgical cases by attending neurosurgeons and trainees. Trainee performance in localization of drill location and angle tasks was assessed in a simulated training with augmented reality visualization and compared with two other visualization methods.<br /> The proposed metrics allowed us to significantly differentiate levels of competence between attending neurosurgeons and trainees in identification of drill location with (p = 0.011) and without (p = 0.001) the HoloLens and drill angle with (p = 0.032) the HoloLens. Augmented reality visualization significantly improved trainee performance in localization of drill location (p < 0.001 and p = 0.008) and angle (p < 0.001 and p < 0.001) in comparison to two other visualization methods. Trainees rated augmented reality visualization equally or more helpful compared to the two other visualization methods.<br /> 

Trainee performance assessment with augmented reality visualization and the proposed performance metrics stands to add practical value to neurosurgical training curricula. This work represents a necessary step in curriculum development in neurosurgical training for the task of drill location and angle localization in a variety of neurosurgical procedures.</p>},

keywords = {},

pubstate = {published},

tppubtype = {mastersthesis}

}

Baum, Zachary M C; Church, Ben; Lasso, Andras; Ungi, Tamas; Schlenger, Christopher; Borschneck, Daniel P.; Mousavi, Parvin; Fichtinger, Gabor

Step-wise identification of ultrasound-visible anatomical landmarks for 3D visualization of scoliotic spine Conference

SPIE Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling, vol. 10951, San Diego, California, 2019.