Bias Field Correction in Endorectal Diffusion Imaging – VISION AND IMAGE PROCESSING (VIP) RESEARCH GROUP

Jeffrey Glaister

vipadmin — Thu, 23 Mar 2023 19:33:19 +0000

I received my BASc in Systems Design Engineering from the University of Waterloo in 2011. Through my co-op terms, I gained experience in medical imaging by working for Sunnybrook Health Sciences Centre. As part of my 3rd year design project, I developed a signature recognition system for point-of-sale authentication. For my 4th year design project, I worked on a novel video compression algorithm.

Email: jeffrey.glaister@uwaterloo.ca

Supervisors

Alexander Wong, David Clausi

Research interests

My research interests are in the fields of pattern recognition and image processing, applied to biomedical imaging. I am interested in developing image processing algorithms to automate the analysis of medical images, such as those captured using MRI, X-ray or other modalities. Other work is in the area of novel video compression algorithms.

Research topics

Biomedical Imaging

Research demos

Bias Field Correction in Endorectal Diffusion Imaging
Correlated Diffusion Imaging
Skin Cancer Detection

Publications

Journal Articles / Conference Papers

Journal Articles

Conference Papers

Top

Dorothy Lui

Dorothy Lui — Thu, 23 Mar 2023 19:29:04 +0000

I completed my bachelor’s in Mechatronics Engineering at the University of Waterloo in 2012. I am now pursuing my master’s in Systems Design Engineering under the supervision of Prof. Wong. I was first exposed to image processing while working on in vivo bone implant images to determine bone porosity at the UW Rapid Prototyping Lab. Then, I worked at Colibri Technologies applying digital signal processing to ultrasound images.

Supervisors

Alexander Wong

Research interests

I am passionate about image processing and pattern recognition, particularly in applications in biomedical imaging. My current research involves developing new algorithms to automate segmentation of particular features in biomedical images.

Research topics

Biomedical Imaging
Computer Vision
Image Segmentation/Classification
Multiresolution Techniques
Stochastic Models

Research demos

Bias Field Correction in Endorectal Diffusion Imaging
Enhanced Decoupled Active Contour Using Structural and Textural Variation Energy Functionals
Enhanced Low-dose Computed Tomography
Hybrid Structural and Texture Distinctiveness Vector Field Convolution for Region Segmentation

Publications

Journal Articles / Conference Papers

Journal Articles

Conference Papers

Top

Bias Field Correction in Endorectal Diffusion Imaging

vipadmin — Mon, 20 Mar 2023 19:38:11 +0000

Prostate cancer is the most common type of cancer affecting males in North America today. Diffusion-weighted MRI (DWI) has been useful in prognosis because of its improved visualization of dense cancerous tissue due to restricted diffusion of water in these regions. An additional endorectal coil has been used to improve the signal-to-noise ratio (SNR) in the prostate gland region however introduces an undesirable bias field which shows increased intensity nearest the coil which diminishes with distance.

Previous approaches have adjusted the MRI acquisition process to compensate for the bias field however this does not account for bias fields caused by the anatomy. Other approaches are post-processing methods that use filtering, surface fitting or segmentation.

A bias field correction method was developed here at VIP that automatically estimates the bias field and corrects for it. The resulting correction allows for improved visualization of the prostate gland (Fig. 1) and of tumors in high b-value computations (Fig. 2).

Fig. 1. DWI of the prostate with b = 0 sec/mm² with an endorectal coil with and without the bias field. The proposed approach removes the bias field in the peripheral zone and brightens the prostate gland for improved delineation from the background.

Fig. 2. Computed high b-value b = 1500 sec/mm² with tumor: High b-value images display tumors with brighter intensities. Red arrows indicate tumors and the blue arrow indicates a bright region that could be mistaken for a tumor due to the bias field. The corrected image removes the bias field effectively to remove this incorrectly identified region.

Related people

Directors

Students

Alumni

Related research areas

Biomedical Imaging

Related publications

Journal Articles

Conference Papers

Alexander Wong

Alexander Wong — Thu, 23 Feb 2023 21:38:59 +0000

Alexander Wong is currently the Canada Research Chair in Medical Imaging Systems and an assistant professor in the Department of Systems Design Engineering at the University of Waterloo. He had previously received his B.A.Sc. degree in Computer Engineering from the University of Waterloo, Waterloo, ON, Canada in 2005, his M.A.Sc. degree in Electrical and Computer Engineering from the University of Waterloo, Waterloo, ON, Canada in 2007, and his Ph.D. degree Systems Design Engineering from the University of Waterloo, ON, Canada in 2010. He was also a NSERC postdoctoral research fellow at Sunnybrook Health Sciences Centre. He has published over 450 refereed journal and conference papers, as well as patents, in various fields such as computational imaging, artificial intelligence, computer vision, and multimedia systems. He has received numerous awards including three Outstanding Performance Awards, a Distinguished Performance Award, an Engineering Research Excellence Award, a Sandford Fleming Teaching Excellence Award, an Early Researcher Award from the Ministry of Economic Development and Innovation, a Best Paper Award at the NIPS Workshop on NIPS Workshop on Transparent and Interpretable Machine Learning (2017), a Best Paper Award at the NIPS Workshop on Efficient Methods for Deep Neural Networks (2016), two Best Paper Awards by the Canadian Image Processing and Pattern Recognition Society (CIPPRS) (2009 and 2014), a Distinguished Paper Award by the Society of Information Display (2015), two Best Paper Awards for the Conference of Computer Vision and Imaging Systems (CVIS) (2015,2017), Synaptive Best Medical Imaging Paper Award (2016), two Magna Cum Laude Awards and one Cum Laude Award from the Annual Meeting of the Imaging Network of Ontario, CIX TOP 20 (2017), AquaHacking Challenge First Prize (2017), Best Student Paper at Ottawa Hockey Analytics Conference (2017), and the Alumni Gold Medal.

Students

Supervision – Current

PDF

ph.D.

M.A.Sc.

Supervision – Completed

PDF

ph.D.

M.A.Sc.

Research topics

Biomedical Imaging
Computer Vision
Discovery Radiomics
Evolutionary Deep Intelligence
Image Segmentation/Classification
Multiresolution Techniques
Remote Sensing
Scientific Imaging
Stochastic Models
Video Analysis

Research demos

Action Recognition in Video
Bias Field Correction in Endorectal Diffusion Imaging
Coded Hemodynamic Imaging
Correlated Diffusion Imaging
Disparate Scene Registration
Enhanced Decoupled Active Contour Using Structural and Textural Variation Energy Functionals
Enhanced Low-dose Computed Tomography
Grid Seams: A fast superpixel algorithm for real-time applications
Hybrid Structural and Texture Distinctiveness Vector Field Convolution for Region Segmentation
Image Denoising
Multiplexed Optical High-coherence Interferometry
SAR Sea Ice Image Synthesis
Skin Cancer Detection
Statistical Textural Distinctiveness for Salient Region Detection in Natural Images
Stereo Vision for Dimension Estimation

Publications

Journal Articles / Conference Papers

Journal Articles

Conference Papers

Top