Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection

• URL: http://arxiv.org/abs/2606.30951v1
• Date: Mon, 29 Jun 2026 22:07:39 GMT
• Title: Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection
• Abstract summary: Prost-RL reframes $$US PCa detection as a spatially aware, policy-driven inference problem by learning where to look before decoding.<n>Prost-RL integrates a lightweight reinforcement-learning policy into a foundation-model encoder-decoder to generate interpretable spatial attention maps.<n>On a cohort of 6,607 biopsy cores from 693 patients, Prost-RL achieves $79.0pm3.5$ AUROC with $64.6pm6.3$% sensitivity at 80% specificity for core-level detection.
• Score: 3.289558200859529
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Micro-ultrasound ($μ$US) is a new, emerging, and promising imaging modality for prostate cancer (PCa) detection, but accurate identification of suspicious tissue remains highly dependent on clinical experience, leading to substantial inter-observer variability. Machine-learning assistance can reduce this variability; however, training reliable deep models is challenging because supervision is sparse and noisy -- typically limited to core-level histopathology outcomes (e.g., cancer grade and its percentage in a biopsy core) without pixel-level lesion annotations and under severe class imbalance. We introduce Prost-RL, which reframes $μ$US PCa detection as a spatially aware, policy-driven inference problem by learning where to look before decoding. Prost-RL integrates a lightweight reinforcement-learning policy into a foundation-model encoder-decoder to generate interpretable spatial attention maps that act as soft prompts for both cancer-likelihood heatmap prediction and image-level classification. We further propose Adaptive Policy Optimization (APO) to stabilize hybrid supervised-RL training and a noise-robust objective combining symmetric cross-entropy with negative-entropy regularization to mitigate weak-label noise and encourage sharp localization. On a cohort of 6,607 biopsy cores from 693 patients across five clinical sites, Prost-RL achieves $79.0\pm3.5$ AUROC with $64.6\pm6.3$% sensitivity at 80% specificity for core-level detection (+2.1 AUROC and +4.5 sensitivity points over the strongest baseline), and $79.3\pm5.8$ AUROC for clinically significant cancer classification. The learned policy highlights biopsy-aligned regions, providing transparent, spatially grounded evidence alongside quantitative risk predictions. Code is available at: https://github.com/DeepRCL/Prost-RL.

Related papers

• Learning Prostate Anatomy at Test Time for Cancer Detection in Micro-Ultrasound [24.492164115951358]
  Domain shift across clinical centers remains a fundamental barrier to deploying deep learning models for prostate cancer detection.<n>We propose ANT, a segmentation-guided TTA framework that adapts a pretrained cancer detection encoder to the target domain.<n>The model was trained on 693 patients imaged with an earlier-generation micro-ultrasound scanner in a multi-center clinical trial, and evaluated on 118 patients acquired with a newer-generation system across two centers.
  arXiv  Detail & Related papers  (2026-08-20T20:36:40Z)
• Histopathological Spectrum-Guided Prostate Stratification via Segmentation-Assisted Diagnostic Transformer [29.021037203684227]
  We construct a Prostate Cancer Histopathology Spectrum dataset (PCa-HSD)<n>We formulate a clinically meaningful four-class classification task, addressing the underrepresentation of benign lesions that are easily confounded with prostate cancer in existing datasets.<n>Our proposed method consistently improves accuracy across backbones, achieving the best average accuracy of 0.633 and JointRecall of 0.768 in five-fold cross-validation on a cohort of 344 patients.
  arXiv  Detail & Related papers  (2026-07-19T10:03:47Z)
• A deep learning pipeline for PAM50 subtype classification using histopathology images and multi-objective patch selection [0.2958068627971103]
  The PAM50 gene signature is widely recognized as a standard for classifying breast cancer into intrinsic subtypes.<n>In this study, we introduce a novel optimization-driven deep learning framework that aims to reduce reliance on costly molecular assays.<n>Our method jointly optimize patch informativeness, spatial diversity, uncertainty, and patch count by combining the non-dominated sorting genetic algorithm II (NSGA-II) with Monte Carlo dropout-based uncertainty estimation.
  arXiv  Detail & Related papers  (2026-04-02T09:13:24Z)
• Maximizing T2-Only Prostate Cancer Localization from Expected Diffusion Weighted Imaging [68.57480103120561]
  Multiparametric MRI is increasingly recommended as a first-line noninvasive approach to detect and localize prostate cancer.<n>Early machine learning attempts using only T2w images have shown promising diagnostic performance in segmenting radiologist-annotated lesions.<n>This work investigates an arguably more challenging application using only T2w at inference, but to localize individual cancers based on independent histopathology labels.
  arXiv  Detail & Related papers  (2026-04-01T14:50:18Z)
• Adaptive Detector-Verifier Framework for Zero-Shot Polyp Detection in Open-World Settings [7.768426131383283]
  Existing approaches struggle with the domain gap between controlled laboratory conditions and clinical practice.<n>We propose AdaptiveDetector, a novel two-stage detector-verifier framework comprising a YOLOv11 detector with a vision-language model (VLM) verifier.<n>This combination of adaptive thresholding and cost-sensitive reinforcement learning achieves clinically aligned, open-world polyp detection with substantially fewer false negatives.
  arXiv  Detail & Related papers  (2025-12-13T23:33:05Z)
• PolypSeg-GradCAM: Towards Explainable Computer-Aided Gastrointestinal Disease Detection Using U-Net Based Segmentation and Grad-CAM Visualization on the Kvasir Dataset [7.02937797539818]
  Colorectal cancer (CRC) remains one of the leading causes of cancer-related morbidity and mortality worldwide.<n>Deep learning methods have demonstrated strong potential for automated polyp analysis, but their limited interpretability remains a barrier to clinical adoption.<n>We present PolypSeg-GradCAM, a framework that integrates the U-Net architecture with Gradient-weighted Class Activation Mapping (Grad-CAM) for transparent polyp segmentation.
  arXiv  Detail & Related papers  (2025-09-17T02:57:33Z)
• Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping [80.92960114162746]
  We propose PathPT, a novel framework that exploits the potential of vision-language pathology foundation models.<n>PathPT converts WSI-level supervision into fine-grained tile-level guidance by leveraging the zero-shot capabilities of VL models.<n>Results show that PathPT consistently delivers superior performance, achieving substantial gains in subtyping accuracy and cancerous region grounding ability.
  arXiv  Detail & Related papers  (2025-08-21T18:04:41Z)
• TRUSWorthy: Toward Clinically Applicable Deep Learning for Confident Detection of Prostate Cancer in Micro-Ultrasound [3.8208601340697386]
  We propose TRUSWorthy, a carefully designed, tuned, and integrated system for reliable PCa detection.<n>Our pipeline integrates self-supervised learning, multiple-instance learning aggregation using transformers, random-undersampled boosting and ensembling.<n>Our method outperforms previous state-of-the-art deep learning methods in terms of accuracy and uncertainty calibration.
  arXiv  Detail & Related papers  (2025-02-20T16:31:24Z)
• Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports [68.39938936308023]
  We propose a novel text-guided learning method to achieve highly accurate cancer detection results. Our approach can leverage clinical knowledge by large-scale pre-trained VLM to enhance generalization ability.
  arXiv  Detail & Related papers  (2024-05-23T07:03:38Z)
• Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies [62.840338941861134]
  We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset. We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis. This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
  arXiv  Detail & Related papers  (2023-02-16T17:06:23Z)
• Lung Cancer Lesion Detection in Histopathology Images Using Graph-Based Sparse PCA Network [93.22587316229954]
  We propose a graph-based sparse principal component analysis (GS-PCA) network, for automated detection of cancerous lesions on histological lung slides stained by hematoxylin and eosin (H&E) We evaluate the performance of the proposed algorithm on H&E slides obtained from an SVM K-rasG12D lung cancer mouse model using precision/recall rates, F-score, Tanimoto coefficient, and area under the curve (AUC) of the receiver operator characteristic (ROC)
  arXiv  Detail & Related papers  (2021-10-27T19:28:36Z)
• Controlling False Positive/Negative Rates for Deep-Learning-Based Prostate Cancer Detection on Multiparametric MR images [58.85481248101611]
  We propose a novel PCa detection network that incorporates a lesion-level cost-sensitive loss and an additional slice-level loss based on a lesion-to-slice mapping function. Our experiments based on 290 clinical patients concludes that 1) The lesion-level FNR was effectively reduced from 0.19 to 0.10 and the lesion-level FPR was reduced from 1.03 to 0.66 by changing the lesion-level cost.
  arXiv  Detail & Related papers  (2021-06-04T09:51:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.