How can artificial intelligence (AI) help medical professionals identify, diagnose, and treat prostate cancer? This is what a recent study published in Radiology hopes to address as a team of researchers developed an AI model designed to identify prostate cancer lesions, which holds the potential to help medical professionals and patients make the best-informed decisions regarding diagnoses and treatment options.
For the study, which was conducted between January 2021 to August 2023, the researchers had their AI model examine MRI scans from 732 patients, including 438 patients who underwent radiation therapy (RT) and 294 patients who underwent radical prostatectomy (RP). The goal was to compare a potential success rate of the AI model identifying tumors compared to patient treatment between 5 to 10 years after being diagnosed.
In the end, the AI model demonstrated an 85 percent accuracy in identifying cancerous lesions. Additionally, the AI model identified the larger volume lesions that resulted in failed treatment and metastasis, which is when cancer tumors spread beyond the original location within the body. Finally, the AI model determined that RT patients were at a decreased risk of metastasis based on their tumor volumes.
“Al-determined tumor volume has the potential to advance precision medicine for patients with prostate cancer by improving our ability to understand the aggressiveness of a patient's cancer and therefore recommend the most optimal treatment,” said Dr. David D. Yang, MD, who is an instructor in the Harvard Medical School and lead author of the study.
This study comes as 2024 has seen almost 300,000 new cases of prostate cancer within the United States with more than 35,000 dying from prostate cancer during this year, as well.
How will AI continue to advance identification, diagnosis, and treatment of prostate cancer in the coming years and decades? Only time will tell, and this is why we science!
As always, keep doing science & keep looking up!
Sources: Radiology, EurekAlert!, National Cancer Institute
