A Workflow to Efficiently Generate Dense Tissue Ground Truth Masks for Digital Breast Tomosynthesis

2026-04-13

AI Summary

This work addresses the scarcity of high-quality, fully annotated data that hinders dense tissue segmentation in digital breast tomosynthesis (DBT). The authors propose an efficient weakly supervised framework that requires only a coarse region delineation and a threshold specification on the central slice of a DBT volume. Leveraging region projection and slice-adaptive thresholding, the method automatically generates consistent binary masks of dense tissue across the entire volume. This approach substantially reduces annotation burden while preserving inter-slice consistency, achieving a median Dice score of 0.83 on the DBTex dataset—comparable to the inter-radiologist agreement level of 0.84.

Technology Category

Computer Vision: SegmentationMachine Learning: Semi-Supervised LearningKnowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsWeb Mining and Content Analysis: Robustness and generalizability of Web mining methodsResponsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Digital breast tomosynthesis (DBT) is now the standard of care for breast cancer screening in the USA. Accurate segmentation of fibroglandular tissue in DBT images is essential for personalized risk estimation, but algorithm development is limited by scarce human-delineated training data. In this study we introduce a time- and labor-saving framework to generate a human-annotated binary segmentation mask for dense tissue in DBT. Our framework enables a user to outline a rough region of interest (ROI) enclosing dense tissue on the central reconstructed slice of a DBT volume and select a segmentation threshold to generate the dense tissue mask. The algorithm then projects the ROI to the remaining slices and iteratively adjusts slice-specific thresholds to maintain consistent dense tissue delineation across the DBT volume. By requiring annotation only on the central slice, the framework substantially reduces annotation time and labor. We used 44 DBT volumes from the DBTex dataset for evaluation. Inter-reader agreement was assessed by computing patient-wise Dice similarity coefficients between segmentation masks produced by two radiologists, yielding a median of 0.84. Accuracy of the proposed method was evaluated by having a radiologist manually segment the 20th and 80th percentile slices from each volume (CC and MLO views; 176 slices total) and calculate Dice scores between the manual and proposed segmentations, yielding a median of 0.83.

Problem

• Digital Breast Tomosynthesis
• Fibroglandular Tissue Segmentation
• Ground Truth Annotation
• Dense Tissue Mask
• Training Data Scarcity

Innovation

• digital breast tomosynthesis
• dense tissue segmentation
• human-annotated ground truth
• slice-wise threshold adaptation
• annotation efficiency