Artificial Intelligence in Medicine: Global Prostate Cancer Expert Supports AI for Prostate Cancer Imaging
From conferences to global summits and industry exhibitions, Dubai provides a dynamic business events offering, made up of global connectivity, state-of-the-art hotels and venues, first-class infrastructure and great hospitality. This is how one event site describes the merits of hosting an important international professional conference in the capital city of the emirate of Dubai. In fact, the prestigious Société Internationale d’Urologie (SIU) chose Dubai as the site for their Nov. 10-14, 2021 conference.
According to their website, the Société Internationale d’Urologie was founded in Paris, in 1907, by Dr. Jean Casimir Félix-Guyon. In 1999, the SIU established permanent headquarters in Montreal, Canada. Their mission is to enable urologists in all nations, through international cooperation in education and research, to apply the highest standards of urological care to their patients.
At the 2021 conference, noted British urologist Mark Emberton addressed the future of prostate cancer (PCa) imaging. Emberton is very well qualified to deliver remarks on that topic. He is described as a “urologist and prostate cancer research specialist using novel imaging techniques and minimally invasive treatments to improve diagnosis and treatment of prostate cancer.” As Professor of Interventional Oncology at University College London, and Honorary Consultant Urological Surgeon at University College Hospital, he has steadfastly pursued the application of advanced technologies in the service of PCa patients. He is undoubtedly among the world’s experts support the application of Artificial Intelligence (AI) to prostate imaging.
Emberton on the use of AI in prostate imaging
Emberton did not confine his insights to multiparametric MRI alone, though it has been the leading game-changer in prostate imaging. He pointed out that AI can be adapted for PSMA PET scans and micro-ultrasound. Specifically, he discussed the contribution of AI methods in processing finished mpMRI scans, where AI can detect image information that the human eye can’t perceive.
The heart of his presentation was very well reported by the conference coverage service UroToday:
Based on current data, AI in prostate imaging is currently useful for calculating prostate volume with semi-automatic segmentation of the prostate contour driven by machine learning approaches and auto-segmentation of prostate zones through convolutional neural networks. Further, there is evidence that AI may assist with lesion detection, segmentation, and characterization. This may in fact improve detection of lesions in the transition zone and enhance the characterization of marginal lesions (PI-RADS 3) though this has not yet been adopted in routine practice. More interestingly, radiomics may allow for a prediction of aggressivity with discrimination of aggressive and non-aggressive lesions. Additionally, while imaging approaches are routinely used for loco-regional staging, there have been few studies assessing the role of AI in this context. He emphasized that there is consistent and growing literature supporting the use of AI to improve prostate cancer diagnosis and risk stratification.[i]
As part of his talk, Emberton described the ongoing exploration of simplifying mpMRI. For example, studies are being conducted on the use of two parameters (bi-parametric) vs. three or four parameters (multiparametric) in order to shorten imaging times and reduce expense, thus conceivably making prostate MRI more widely available. He spoke about research into ways in which AI could contribute to the analysis of anatomic and diffusion-weighted post-processing, in order to boost the accuracy of these two parameters in order to eliminate the use of contrast enhancement.
Although everything presented by Emberton is not yet practically tested and available in clinical use, he concluded by stating that “imaging is likely to be simplified in the coming years. This will facilitate the integration of AI in imaging which will be expected, therefore, to have an increasing role in helping clinicians maximize the clinical utility of imaging studies.”[ii]
At the Sperling Prostate Center, we have been pioneering AI tools in ways that benefit the accuracy of our mpMRI and diagnostics. We thank Dr. Emberton for his enlightening AI talk to the illustrious Société Internationale d’Urologie.
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] Wallis, Christopher. SIU 2021: The Future of Prostate Cancer Imaging: Will AI Play a Role? The 41st Congress of the Société Internationale d’Urologie (SIU) November 10-14 in Dubai. https://www.urotoday.com/conference-highlights/siu-2021/133937-siu-2021-the-future-of-prostate-cancer-imaging-will-ai-play-a-role.html
- Artificial Intelligence, Prostate imaging