Artificial Intelligence Meets 3-D Imaging Prostate Biopsy
Did you ever shop for a dozen eggs and open the carton to make sure none are cracked? After assessing they’re all intact, that’s as far as your inspection goes. Now imagine you had x-ray vision, and you could see all 12 yolks in their 3-dimensional glory. You would know if each egg is perfect, or if there were any unusually small or misshaped centers. What an inspection that would be!
AI and imaging collaboration
A new research collaboration between Case Western Reserve (CWR) University’s Center for Computational Imaging and Personalized Diagnostics (CCIPD) and a University of Washington (UW) team of bioengineers are exploring a combination of Artificial Intelligence (AI) and 3-D imaging of prostate biopsy tissue in hopes of accomplishing a faster, more precise way to identify the aggression level of a patient’s prostate cancer (PCa). By doing so, they would enable doctors to quickly match patients with appropriate treatments. In turn, this can increase success rates.
The UW team, together with their leader Professor Jonathan Liu, advanced 3-D imaging of biopsy samples by using an open-top light sheet microscope that can nondestructively image an intact tissue sample, from which a computer can generate 3-D cellular depictions. The CWR researchers were involved in using AI to predict PCa aggression. The successful results of collaborative tests on actual biopsy samples were published in December, 2021.[i] Professor Liu stated, “We show for the first time that compared to traditional pathology — where a small fraction of each biopsy is examined in 2D on microscope slides — the ability to examine 100% of a biopsy in 3D is more informative and accurate.”[ii]
One member of the combined research team is my colleague Anant Madabhushi, PhD, who directs CWR’s CCIPD. I have tremendous respect for the investigational work he leads in AI, Machine Learning and Deep Learning. Based on their early research, his joint team with Professor Liu has now been awarded a 5-year $3.1 million grant by the National Institutes of Health, and I congratulate them.
It has been my privilege to have worked with Dr. Madabhushi in developing AI applications for PCa diagnostics, including publication and presentation of four papers:
- Toth R, Sperling D, Madabhushi A. Quantifying Post- Laser Ablation Prostate Therapy Changes on MRI via a Domain-Specific Biomechanical Model: Preliminary Findings,[iii] an AI-based model to quantify mpMRI-revealed tissue changes in the prostate after Focal Laser Ablation (FLA).
- Viswanath S, Toth R, Rusu M, Sperling D, Lepor H, Futterer J, Madabhushi A. Quantitative Evaluation of Treatment Related Changes on Multi-Parametric MRI after Laser Interstitial Thermal Therapy of Prostate Cancer[iv], a presentation on a way to identify mpMRI markers, particularly T2 weighted MRI, of favorable treatment response and predict long-term outcomes.
- Viswanath S, Toth R, Rusu M, Sperling D, Lepor H, Futterer J, Madabhushi A. Identifying Quantitative In Vivo Multi-Parametric MRI Features for Treatment Related Changes after Laser Interstitial Thermal Therapy of Prostate Cancer.[v] This 2014 published paper is a more developed and specific version of the above.
- Toth R, Ribault J, Gentile J, Sperling D, Madabhushi A. Simultaneous Segmentation of Prostatic Zones Using Active Appearance Models With Multiple Coupled Levelsets.[vi] This paper presents an improved algorithm that can be used in the training phase of deep learning for image recognition.
It’s thrilling to be in the forefront of PCa diagnostics augmented by AI. It’s an honor to be a pioneer alongside Dr. Madabhushi and his team, and to be able to bring AI innovation into our services at the Sperling Prostate Center. I hope you will take time to explore our blogs that are dedicated to Artificial Intelligence in Medicine. We have many topics, and want to share our excitement with you.
NOTE: This content is solely for purposes of information and does not substitute for diagnostic or medical advice. Talk to your doctor if you are experiencing pelvic pain, or have any other health concerns or questions of a personal medical nature.
[i] Xie W, Reder NP, Koyuncu C, Leo P et al. Prostate Cancer Risk Stratification via Nondestructive 3D Pathology with Deep Learning-Assisted Gland Analysis. Cancer Res. 2022 Jan 15;82(2):334-345.
[ii] McQuate, Sarah. “3D Imaging Method may Help Doctors Better Determine Prostate Cancer Aggressiveness.” UW News, Dec. 9, 2021. https://www.washington.edu/news/2021/12/09/3d-imaging-method-may-help-doctors-better-determine-prostate-cancer-aggressiveness
[iii] Toth R, Sperling D, Madabhushi A. Quantifying Post- Laser Ablation Prostate Therapy Changes on MRI via a Domain-Specific Biomechanical Model: Preliminary Findings. PLoS ONE. 2016 Apr; 11(4): e0150016. DOI: 10.1371/journal.pone.0150016
[iv] Viswanath S, Toth R, Rusu M, Sperling D, Lepor H, Futterer J, Madabhushi A. Quantitative Evaluation of Treatment Related Changes on Multi-Parametric MRI after Laser Interstitial Thermal Therapy of Prostate Cancer. Proceedings – Society of Photo-Optical Instrumentation Engineers. 2013 Mar; 8671:86711F. DOI: 10.1117/12.2008037
[v] Viswanath S, Toth R, Rusu M, Sperling D, Lepor H, Futterer J, Madabhushi A. Identifying Quantitative In Vivo Multi-Parametric MRI Features For Treatment Related Changes after Laser Interstitial Thermal Therapy of Prostate Cancer. Neurocomputing. 2014 Nov 20; 144: 13-23. DOI: 10.1016/j.neucom.2014.03.065
[vi] Toth R, Ribault J, Gentile J, Sperling D, Madabhushi A. Simultaneous Segmentation of Prostatic Zones Using Active Appearance Models With Multiple Coupled Levelsets. Computer Vision and Image Understanding. 2013 Aug; 117(9):1051-1060. DOI: 10.1016/j.cviu.2012.11.013
- Artificial Intelligence