Adaptive Prototype-based Interpretable Grading of Prostate Cancer

Riddhasree Bhattacharyya; Pallabi Dutta; Sushmita Mitra

cs.CVMar 5, 2026

Adaptive Prototype-based Interpretable Grading of Prostate Cancer

Authors: Riddhasree Bhattacharyya, Pallabi Dutta, Sushmita Mitra

Organizations: Machine Intelligence Unit, Indian Statistical Institute, Kolkata 700108

Abstract

Prostate cancer being one of the frequently diagnosed malignancy in men, the rising demand for biopsies places a severe workload on pathologists. The grading procedure is tedious and subjective, motivating the development of automated systems. Although deep learning has made inroads in terms of performance, its limited interpretability poses challenges for widespread adoption in high-stake applications like medicine. Existing interpretability techniques for prostate cancer classifiers provide a coarse explanation but do not reveal why the highlighted regions matter. In this scenario, we propose a novel prototype-based weakly-supervised framework for an interpretable grading of prostate cancer from histopathology images. These networks can prove to be more trustworthy since their explicit reasoning procedure mirrors the workflow of a pathologist in comparing suspicious regions with clinically validated examples. The network is initially pre-trained at patch-level to learn robust prototypical features associated with each grade. In order to adapt it to a weakly-supervised setup for prostate cancer grading, the network is fine-tuned with a new prototype-aware loss function. Finally, a new attention-based dynamic pruning mechanism is introduced to handle inter-sample heterogeneity, while selectively emphasizing relevant prototypes for optimal performance. Extensive validation on the benchmark PANDA and SICAP datasets confirms that the framework can serve as a reliable assistive tool for pathologists in their routine diagnostic workflows.

Figures & tables

Figure 1: Schematic representation of the workflow of the ADAPT framework

Figure 2: The architecture of the ADAPT framework. During stage 1 patch-level pretraining, the attention and WSI-level prediction modules are not needed. For stage 2 WSI-level fine-tuning, the attention module is not required. Stage 3 uses all the modules.

Figure 3: Training strategy for WSI-level fine-tuning

Grade	# Patches
Benign	4000
GG3	4247
GG4	4186
GG5	4039

Table 1: Dataset distribution at (a) patch-level and (b) WSI-level

Stage	Epochs	Batch size	Loss weights	Learning rate (LR)
1	30	64	$\mathcal{L}_{\text{patch}}$ : ( $\lambda_{\text{clst}}\>0.8,\lambda_{\text{sep}}\>0.08$ [ 13 ] )	Cosine annealing (Initial LR: 3e-4)
2	25	8	$\mathcal{L}_{\text{WSI}}$ : ( $\lambda_{\text{align}}:[0.03,0.1],\lambda_{\text{repel}}:[0.01,0.03]$ )	Cosine annealing (Initial LR: 1e-5-1e-3)
3	20	8	$\mathcal{L}_{\text{attn}}$ : ( $\alpha$ : [0.5,2], $\beta$ : [0.1,1])	Cosine annealing (Initial LR: 1e-3)

Table 2: Implementation details of the ADAPT framework

Figure 4: Ablation study evaluating the impact of the training stages and prototype counts on WSI-level Gleason grading performance over the PANDA dataset w.r.t. (a) Macro F1 score, and corresponding (b) Hamming loss

Figure 5: Fraction of low-attention prototypes, for configurations having prototypes per class as (a) 4, (b) 5, and (c) 6, over the PANDA dataset

Modules			Metrics
Attention block	BCE	$\mathcal{L}_{\text{attn}}$	F1 score	Hamming loss
			0.8130	0.1916
✓	✓		0.8255	0.1800
✓	✓	✓	0.8312	0.1769

Table 3: Ablation study of the Stage 3 modules on the PANDA dataset

Grade	PANDA		SICAP
Grade	F1 score	Hamming loss	F1 score	Hamming loss
GG3	0.8483	0.2341	0.8101	0.1764
GG4	0.8912	0.1699	0.8762	0.2100
GG5	0.7542	0.1238	0.7764	0.1848

Table 4: Grade-wise performance of ADAPT on test data

Figure 6: Prototype cross-activation matrix showing mean weighted prototype activations across patch classes for the PANDA dataset

Figure 7: Prototype visualization as training patches for Gleason grades (a) 3, (b) 4, and (c) 5, respectively, for the PANDA dataset. Within each group, Column 1 shows the original training patch with the prototype-activated region highlighted using a bounding box; Column 2 displays the corresponding prototype self-activation heatmap; and Column 3 represents the ground-truth Gleason mask

Figure 8: Prototype-based explanations for test WSIs from (a) PANDA, (b) SICAP datasets (WSI-level images are not available for SICAP). For each Gleason pattern present at WSI-level, the most confident patch predicted by ADAPT is visualized in terms of nearest prototype activation, bounding-box correspondence, Gleason mask, and similarity to the nearest prototype

Prostate Cancer Grading

See all 11 papers

KOAL: Knowledge-Driven Prostate Cancer Grading with Ordinal-Aware Learning
Jul 7, 2026Zheng Guo, Jiaqi Cui, Haocheng Xiong +5Medical Image Classification Ordinal Regression
School of Computer Science, Sichuan University, China · China Mobile (Suzhou) Software Technology Company Limited, China · Shanghai Changhai Hospital, Naval Medical University, China +1
Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images
Mar 19, 2026Vahid Monfared, Mohammad Hadi Gharib, Ali Sabri +4Medical Imaging Medical Image Classification
Department of Computer Science, Boston University Metropolitan College, Boston, MA, USA · MD, Clinical Fellow, Department of Radiology, McMaster University, Ontario, Canada · Department of Radiology, School of Medicine, 5th Azar Hospital, Radiology, Golestan University of Medical Sciences, Gorgan, Iran +6
Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading
Mar 10, 2026Marie Arrivat, Rémy Peyret, Elsa Angelini +1Prostate Cancer Grading Histopathology Image Classification
Primaa, Paris, France · LTCI, Telecom Paris, Institut Polytechnique de Paris, France

Jul 7, 2026J/K move · Enter open · S save

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

Zheng Guo, Jiaqi Cui, Haocheng Xiong, Jize Han+4

School of Computer Science, Sichuan University, China · China Mobile (Suzhou) Software Technology Company Limited, China · Shanghai Changhai Hospital, Naval Medical University, China+1

Medical Image Classification Ordinal Regression Oncology Prostate Cancer Grading Medical Image Representation Learning

Open paper AskPDF arXiv

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.

Abstract

Prostate Cancer Grading

Explore similar work

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

Interpretable Prostate Cancer Detection using a Small Cohort of MRI Images

Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading