GUIDE-US: Grade-Informed Unpaired Distillation of Encoder Knowledge from Histopathology to Micro-UltraSound

TL;DR

GUIDE-US introduces an unpaired histopathology-guided knowledge distillation framework to train a micro-US encoder for prostate cancer grading. The method uses a two-stage teacher-student setup: a histopathology foundation-model teacher trained on whole-slide images guides a micro-US student via ABMIL-based aggregation and a triplet distillation objective, with a weakly supervised segmentation branch. Results show improved detection of clinically significant prostate cancer at 60% specificity and better ISUP-grade discrimination compared to state-of-the-art imaging baselines, with statistically significant gains. This approach enables earlier, more reliable risk stratification using imaging alone, potentially improving biopsy targeting and clinical decision-making, with code to be released upon publication.

Abstract

Purpose: Non-invasive grading of prostate cancer (PCa) from micro-ultrasound (micro-US) could expedite triage and guide biopsies toward the most aggressive regions, yet current models struggle to infer tissue micro-structure at coarse imaging resolutions. Methods: We introduce an unpaired histopathology knowledge-distillation strategy that trains a micro-US encoder to emulate the embedding distribution of a pretrained histopathology foundation model, conditioned on International Society of Urological Pathology (ISUP) grades. Training requires no patient-level pairing or image registration, and histopathology inputs are not used at inference. Results: Compared to the current state of the art, our approach increases sensitivity to clinically significant PCa (csPCa) at 60% specificity by 3.5% and improves overall sensitivity at 60% specificity by 1.2%. Conclusion: By enabling earlier and more dependable cancer risk stratification solely from imaging, our method advances clinical feasibility. Source code will be publicly released upon publication.

Figures (4)

• Figure 1: Overview of the two-stage pathology-guided teacher-student framework for micro-US ISUP grading. In Stage 1 (top), a histopathology teacher model is trained on whole-slide images (WSIs) using attention-based multiple-instance learning (MIL) for aggregated patch embeddings and a multi-layer perceptron (MLP) for ISUP classification, with weights subsequently frozen. In Stage 2 (bottom), the micro-US student model undergoes multi-task training: an image encoder extracts the full image patches features, then the biopsy-region patches are aggregated via attention-based MIL into embeddings that are guided to match frozen pathology representations through contrastive knowledge distillation. Concurrently, an image decoder generates full-image cancer masks, enabling ROI isolation for weakly supervised segmentation guided by coarse histopathology reports.
• Figure 2: AUROC per ISUP grade group for biopsy-region features from the encoder, comparing our method (orange) to the ProstNFound+ baseline (blue).
• Figure 3: Ablation studies. (a) Triplet loss vs. CLIP-style contrastive loss across key metrics. (b) Step-wise ablation of proposed components showing cumulative gain in Sens@60%Spec (csPCa) from the ProstNFound+ baseline. (c) Sensitivity to triplet-loss weight $\alpha$ (mean across folds) on Sens@60%Spec (csPCa).
• Figure 4: Qualitative comparison of cancer probability heatmaps between our method (top row) and the ProstNFound+ baseline (bottom row) on micro-US cases. The biopsy regions are overlaid on each image. The ground-truth ISUP grade and cancer involvement for each case are shown.