A novel, AI-generated morphologic biomarker to predict prostate cancer recurrence in patients with intermediate risk of progression.

Abstract

Listen

Translate article

e17097 Background: About half of the prostate cancer (PCa) patients within an intermediate-risk group return to the clinic with disease progression after the first line of therapy. While these patients can be stratified into Gleason Grades (GG) 3+4 and 4+3, studies indicate that high-risk patients can still be found in both groups. Using our AI platform, we have developed a morphometric biomarker by analyzing digitized H&E slide images (WSIs), which can accurately predict early biochemical recurrence (within 36 months post-surgery) and the risk of metastatic disease more accurately than GG, TNM staging, and genomic tools. Methods: 125 intermediate-risk (n = 67, 3+4; n = 58, 4+3) samples were collected from the Icahn School of Medicine at Mount Sinai (ISSMS) to form a held-out test set. Seventy-eight patients within the test set had an associated genomic score. A series of deep learning models trained using data from ISMMS, the University of Wisconsin-Madison, and TCGA generated a high dimensional vector for each WSI to provide a numerical representation of observed morphologies, which is then converted into a single score to predict biochemical recurrence within 36 months (BCR) and rank risk of metastasis (MET). Area-under-the-receiver operating characteristic (AROC) was used to measure the accuracy of BCR, and the concordance index (CI) was used to measure the performance of MET. The high and low-risk groups' hazard ratios (HR) for patients within grades 3+4 and 4+3 show that our model can further stratify GG. Results: Our method was significantly better at predicting BCR (AROC: 0.801) and ranking MET (CI: 0.764) relative to GG, TNM, and genomic tool (Table 1). We further sub-stratified the patients into GG 3+4 and 4+3 and identified high-risk patients within each GG. Patients in GG 3+4 with high PATHOMIQ scores had a significantly higher risk of BCR (HR 3.3; 95% CI 1.44 – 7.56; p < 0.005) compared to the low PATHOMIQ score patients. A similar trend was seen in the GG 4+3 group (HR 3.0; 95% CI 1.32 – 6.83; p < 0.01). Conclusions: Our histopathology-based prognostic biomarker significantly improves over standard clinical markers in stratifying patients with intermediate-risk PCa for BCR and MET. Our method overcomes several limitations of genomic testing: We only need digitized WSIs. Our method is non-destructive and preserves the tissue for further interrogation. Moreover, our turn-around time is a few hours. Thus, the PATHOMIQ scoring method may strongly impact the management of intermediate-risk PCa patients and clinical trial patient selection for the successful development of new therapies for early-stage PCa. [Table: see text]