Classifying Malignancy in Prostate Glandular Structures from Biopsy Scans with Deep Learning

Simple Summary In recent years, the prostate cancer histopathological description proposed by Gleason has emerged as a universal standard used for disease diagnosis and progression. Recently, a grading scheme on a point scale is based on Gleason patterns. Current scores are highly dependent on the expert urinary histopathologist and show a high level of variability among experts. To aid the clinician, we have developed deep learning models that provide a decision aid in identifying the primary cancer grade (dominant Gleason pattern). Histopathological classification in prostate cancer remains a challenge with high dependence on the expert practitioner. We develop a deep learning (DL) model to identify the most prominent Gleason pattern in a highly curated data cohort and validate it on an independent dataset. The histology images are partitioned in tiles (14,509) and are curated by an expert to identify individual glandular structures with assigned primary Gleason pattern grades. We use transfer learning and fine-tuning approaches to compare several deep neural network architectures that are trained on a corpus of camera images (ImageNet) and tuned with histology examples to be context appropriate for histopathological discrimination with small samples. In our study, the best DL network is able to discriminate cancer grade (GS3/4) from benign with an accuracy of 91%, F-1-score of 0.91 and AUC 0.96 in a baseline test (52 patients), while the cancer grade discrimination of the GS3 from GS4 had an accuracy of 68% and AUC of 0.71 (40 patients).

Automated summary

In recent years, Gleason's prostate cancer histopathological description has become a universal standard for disease diagnosis and progression. We have developed deep learning models to assist clinicians in identifying the primary cancer grade. These models have significant application value in histopathological classification.