Detecting and Grading Prostate Cancer in Radical Prostatectomy Specimens Through Deep Learning

An analysis evaluated the ability of deep learning algorithms to detect and grade prostate cancer (PCa) in radical prostatectomy specimens. The results were published in the journal Clinics.

Researchers selected 12 whole-slide images of radical prostatectomy specimens. Subsequently, the images were divided, analyzed, and annotated. The annotated areas were categorized as follows: stroma, normal glands, and Gleason patterns 3, 4, and 5. The investigators then performed two analyses: a categorical image classification method that labels each image as benign or as Gleason 3 through 5, and a scanning method in which distinct areas representative of benign and different Gleason patterns were identified.

The trained model was able to achieve an accuracy of 94.1% during training; however, the researchers noted, the concordance with expert uropathologists in the test dataset was only 44%.

“With the image-scanning method, our model demonstrated a validation accuracy of 91.2%. When the test images were used, the concordance between the deep learning method and uropathologists was 89%,” the researchers said of the results. Deep learning algorithms have a high potential for use in the diagnosis and grading of PCa. Scanning methods are likely to be superior to simple classification methods.”