MC-GenRef: Annotation-free mammography microcalcification segmentation with generative posterior refinement

2026-04-06

AI Summary

This work addresses the challenge of segmenting microcalcification clusters in mammograms, which is hindered by their small size, sparse distribution, scarcity of precise pixel-level annotations, and domain shift across institutions that exacerbates false positives and missed detections. To overcome these issues, the authors propose MC-GenRef, the first framework for microcalcification segmentation that operates without real dense annotations. It leverages a lightweight image formation model to generate high-fidelity synthetic data and introduces a seed-guided rectified flow generator. At test time, the method employs test-time generative posterior refinement (TT-GPR), incorporating edge-aware and overlap-consistency regularizations to iteratively refine predictions. Evaluated on INbreast using only synthetic training data, MC-GenRef achieves state-of-the-art Dice scores and demonstrates superior cross-domain generalization, significantly improving recall and reducing false negatives on an external Yonsei cohort.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Microcalcification (MC) analysis is clinically important in screening mammography because clustered puncta can be an early sign of malignancy, yet dense MC segmentation remains challenging: targets are extremely small and sparse, dense pixel-level labels are expensive and ambiguous, and cross-site shift often induces texture-driven false positives and missed puncta in dense tissue. We propose MC-GenRef, a real dense-label-free framework that combines high-fidelity synthetic supervision with test-time generative posterior refinement (TT-GPR). During training, real negative mammogram patches are used as backgrounds, and physically plausible MC patterns are injected through a lightweight image formation model with local contrast modulation and blur, yielding exact image-mask pairs without real dense annotation. Using only these synthetic labeled pairs, MC-GenRef trains a base segmentor and a seed-conditioned rectified-flow (RF) generator that serves as a controllable generative prior. During inference, TT-GPR treats segmentation as approximate posterior inference: it derives a sparse seed from the current prediction, forms seed-consistent RF projections, converts them into case-specific surrogate targets through the frozen segmentor, and iteratively refines the logits with overlap-consistent and edge-aware regularization. On INbreast, the synthetic-only initializer achieved the best Dice without real dense annotations, while TT-GPR improved miss-sensitive performance to Recall and FNR, with strong class-balanced behavior (Bal.Acc., G-Mean). On an external private Yonsei cohort ( n=50 ), TT-GPR consistently improved the synthetic-only initializer under cross-site shift, increasing Dice and Recall while reducing FNR. These results suggest that test-time generative posterior refinement is a practical route to reduce MC misses and improve robustness without additional real dense labeling.

Problem

• microcalcification segmentation
• dense annotation
• cross-site shift
• false positives
• missed detection

Innovation

• generative posterior refinement
• annotation-free segmentation
• microcalcification detection
• test-time refinement
• synthetic supervision