ng AI to aid in cancer contouring, the team at UCLA Health discovered that the accuracy and consistency of predicting the size of cancer was 45 times greater compared to when doctors relied solely on traditional clinical imaging and blood tests to estimate the extent of the cancer. This use of artificial intelligence can greatly minimize the likelihood of underestimating the scope of prostate cancer, leading to more precise diagnosis, treatment planning, and surgical procedures.Utilizing AI for cancer contouring has proven to be significantly more accurate and consistent in predicting cancer size compared to relying solely on conventional clinical imaging and blood tests, according to researchers. In fact, the prediction was found to be 45 times more precise when AI was used. The results of the study were recently published in the Journal of Urology.
Dr. Wayne Brisbane, the study author and assistant professor, emphasized the importance of accurately determining the extent of prostate cancer for effective treatment planning. Different stages of cancer may require different approaches, such as active surveillance, surgery, focal therapy, radiation therapy, hormone therapy, chemotherapy, or a combination of these treatments.The author of the article is a urology professor at the David Geffen School of Medicine at UCLA and also a member of the UCLA Health Jonsson Comprehensive Cancer Center.
Assessing the severity of prostate cancer is a complicated task that usually requires a surgeon to take into account different diagnostic tests such as a prostate-specific antigen (PSA) blood test, imaging tests like MRI, CT scans, and other clinical features simultaneously in order to determine how aggressive the cancer cells are.
Doctors often rely on the appearance of a tumor on an MRI, but the true extent of the prostate cancer may not be visible on the MRI, causing doctors to underestimate the size of the tumor, according to Brisbane. AI
In order to address this challenging problem, a new AI system has been developed by researchers at UCLA and Avenda Health. This AI system has already proven to be more effective in defining the margins of prostate cancer compared to MRI. This demonstrates the potential of AI to enhance minimally invasive treatment methods such as focal therapy. Focal therapy is a relatively new approach for treating prostate cancer, with the goal of eliminating cancer cells while minimizing damage to surrounding healthy tissue. However, prior to this study, the performance of the AI system in the hands of physicians had not been tested.
In order to address this challenging problem, a new AI system has been developed by researchers at UCLA and Avenda Health. This AI system has already proven to be more effective in defining the margins of prostate cancer compared to MRI. This demonstrates the potential of AI to enhance minimally invasive treatment methods such as focal therapy. Focal therapy is a relatively new approach for treating prostate cancer, with the goal of eliminating cancer cells while minimizing damage to surrounding healthy tissue. However, prior to this study, the performance of the AI system in the hands of physicians had not been tested.
To assess how AI software affects the cancer contouring and clinical decision-making of doctors, researchers carried out a study involving multiple readers and cases. The study compared the contouring methods used by physicians with and without AI assistance. Seven urologists and three radiologists with experience ranging from two to 23 years reviewed the cases of 50 patients who had undergone a prostatectomy and were potential candidates for focal therapy. Each case included T2-weighted MRI images and outlines of the prostate gland and surrounding areas.suspected cancer before a biopsy report. The doctors first examined the images and outlined the potential cancerous areas by hand, trying to encompass all the important disease. After a wait of at least four weeks, they reviewed the same cases and utilized AI software to help them locate the cancerous areas. An assessment was then performed to assess the precision and negative margin rate of the cancer outlines drawn by each method. The study revealed that when using traditional methods, doctors only suspected cancer before a biopsy report.achieved a negative margin 1.6% of the time. When assisted by AI the number increased to 72.8%.
“We observed that AI assistance improved the accuracy and consistency of doctors, leading to increased agreement among them,” explained Shyam Natarajan, assistant adjunct professor of urology, surgery, and bioengineering and senior author of the study.
The team also discovered that the use of AI resulted in higher clinician recommendations for focal therapy in patients with unilateral cancer and minimized variation in accurate tumor encapsulation, potentially reducing the likelihood of side effects.It is often associated with more aggressive treatments like surgery or radiation therapy. ”the use of AI in cancer treatment could result in more effective and personalized care for patients, with treatments that are better tailored to their individual needs and more successful in fighting the disease,” said Brisbane. The study received partial funding from the National Cancer Institute at the National Institutes of Health. The study’s co-first authors are Sakina Mohammed Mota and Alan Priester, from Avenda Health. Other authors include James Sayre from UCLA and Joshua Shubert, Jeremey Bong and Brittany Berry-Pusey from Avenda Health.Avenda Health.
The following individuals have conflicts of interest: Mota, Priester, Shubert, and Bong are employed by Avenda Health. Berry-Pusey and Natarajan are co-founders of Avenda Health. Sayre provides consulting services for Avenda Health.
