Skip to content

Generative Active Learning for Label-Efficient Pan-Organ Ultrasound Diagnosis

Nov 2026 · 0 citations
Computer Science

TL;DR

EvoDiff is introduced, a generative active learning framework that integrates diffusion modelling with information-theoretic objectives, evolutionary search, and curriculum-based sampling to select informative samples across heterogeneous US datasets and has the potential to support clinical annotation workflows.

Abstract

Medical ultrasound (US) enables real-time, non-invasive diagnosis, yet building US-based AI systems is limited by data scarcity, costly expert annotation, and limited cross-center generalizability. Privacy constraints and instance-level reporting hinder the collection of diverse abnormal cases and frame-level labels, while repeated retraining for new centers increases computational cost. We introduce EvoDiff, a generative active learning framework that integrates diffusion modelling with information-theoretic objectives, evolutionary search, and curriculum-based sampling to select informative samples across heterogeneous US datasets. EvoDiff formulates sample selection as a generate-to-retrieve process, in which diffusion-based optimization in feature space guided by information gain produces synthetic probes, and only the real unlabeled samples retrieved by these probes are annotated and used for downstream training. Across six benchmarks covering fifteen datasets and 16,696 images, we evaluate EvoDiff on convolutional network and transformer-based foundation model. EvoDiff approaches fully supervised performance with substantially fewer labels, outperforms active learning baselines, and improves foundation model generalization under cross-domain external validation on unseen cohorts. A reader study with six radiologists indicates the potential to support clinical annotation workflows, with a model-based estimated 24% to 84% reduction in annotation workload at matched downstream performance.

View source

Similar papers

Preprint Nov 2026

Attention Residual U-Net for Enhanced Cross-Dataset Polyp Localization in Endoscopy

Precise localization of pathologies in endoscopy is a critical task in medical imaging, with deep learning (DL) frameworks now serving as the primary methodology for automated lesion detection. Today, generic object detection methods, such as YOLO, provide state-of-the-art performance in this context. However, their ro...

Romil Imtiaz, D. Iakovidis · 0 citations
Open access Oct 2026

Attention-Based Spatial-Temporal Learning for Enhanced Kidney Abnormality Diagnosis from Ultrasound Images

Kidney abnormalities, when detected late, can develop into chronic conditions such as kidney tumors and cardiorenal syndrome. Recently, there has been a move toward automation, especially as it pertains to developing a framework for advanced preprocessing, feature fusion, and hybrid spatial-temporal learning for the de...

Ravikumar Ch, Satyanarayana Nimmala, P. Vasanthsena et al. · 0 citations
Preprint Nov 2026

ProtoCouncil: Multi-Encoder Anatomical Prototypes for Prostate Cancer Detection in Micro-Ultrasound

Purpose: Micro-ultrasound ($\mu$US) is a promising modality for prostate cancer (PCa) detection, but identifying suspicious tissue depends heavily on clinical experience. Models trained on sparse, noisy core-level pathology offer little insight into their decisions and can fail under domain shift. Clinical use needs a...

Mohammad Mahdi Abootorabi, N. Maghsoodi, Armin Saadat et al. · 0 citations
Preprint Nov 2026

Toward Foundation Detection Models via Example-Based Grounding in EM-DETR

DeepLearning (DL)-based Computer-Aided Diagnostic (CAD) systems have shown great promise in supporting clinicians, but their performance heavily depends on the availability of large, well-annotated datasets. In medical lesion detection, the scarcity of comprehensive, stan dardized annotations and the heterogeneity of e...

Sheethal Bhat, B. Georgescu, Awais Mansoor et al. · 0 citations
Open access Nov 2026

SSGNet++: Stage-Aware Generative Augmentation and Ensemble-Guided Pseudo-Labelling for Medical Imaging

Limited annotation and class imbalance remain important challenges in medical image analysis. SSGNet++ examines class-specific StyleGAN3 augmentation for classification and an iterative pseudo-labelling pipeline for segmentation, combining predictions from heterogeneous multi-base and multi-head models with optional ma...

Mo-Song Ma, T. Stathaki, Michalis Lazarou · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.