KOAL: Knowledge-Driven Prostate Cancer Grading with Ordinal-Aware Learning

2026-07-07

AI Summary

Current multiparametric MRI–based approaches for prostate cancer Gleason grading often neglect critical clinical information and fail to model the inherent hierarchical structure of Gleason patterns. To address these limitations, this work proposes the KOAL framework, which uniquely integrates clinical variables to dynamically modulate imaging features, extracts semantic anchors from radiology reports for knowledge-guided prototype alignment, and incorporates hierarchical ordinal constraints with a differentiable microbial logistic mapping layer. This design effectively disentangles primary and secondary Gleason patterns while enforcing pathological consistency. Evaluated on both the public PI-CAI dataset and an internal cohort, KOAL significantly outperforms state-of-the-art methods, markedly improving the accuracy of non-invasive Gleason grading.

Abstract

Non-invasive prediction of Gleason Grade Group (GGG) in prostate cancer using multiparametric MRI (mpMRI) is clinically vital for reducing unnecessary biopsies. Existing GGG prediction methods face two major limitations. First, they often overlook non-image information critical for GGG prediction, including age, prostate-specific antigen (PSA), and expert priors embedded in radiology reports. Second, they tend to oversimplify GGG as flat categorical labels, failing to account for its intrinsic hierarchy of primary and secondary Gleason patterns. To this end, we propose a novel Knowledge-Driven Ordinal-Aware Learning (KOAL) framework with three synergistic modules. Specifically, the Clinical-Context Modulation (CCM) module uses clinical variables (e.g., age and PSA) to dynamically modulate discriminative image representations. The Knowledge-Guided Prototype Alignment (KGPA) module leverages an LLM to extract group-specific expert knowledge from training radiology reports and clinical guidelines, producing offline semantic anchors describing grade-specific radiological findings without requiring patient-specific reports at inference. Through prototype contrastive alignment, patient-specific mpMRI representations are matched with these anchors to promote pathology-aligned representation learning. The Hierarchical Ordinal-aware Constraints (HOC) module decouples primary and secondary Gleason pattern prediction and maps their probabilistic outputs to GGG via a Differentiable Bio-logic Mapping Layer (DBML), ensuring pathological grading consistency. Experiments on public PI-CAI and in-house datasets demonstrate that KOAL outperforms state-of-the-art methods. Code is available at: https://github.com/Gother-GZ/KOAL.

Problem

• prostate cancer
• Gleason Grade Group
• multiparametric MRI
• ordinal grading
• clinical context

Innovation

• Ordinal-aware learning
• Knowledge-driven
• Prototype alignment
• Hierarchical grading
• Clinical-context modulation