EliSeg: Verified Target Construction for Report-Grounded Abnormality Segmentation

2026-08-07

AI Summary

This work addresses the challenges posed by ambiguous, negated, or irrelevant descriptions in radiology reports by introducing EliSeg, a novel framework that enables end-to-end inference of segmentable abnormal findings and their corresponding regions directly from unfiltered, raw reports. EliSeg employs a three-stage Actor–Verifier–Revision pipeline: the Actor generates candidate targets and masks under syntactic constraints, the Verifier independently reconstructs a valid list of abnormalities, and the Revision module iteratively refines the shared representation when structural inconsistencies arise. Notably, EliSeg operates without requiring predefined target identities or spatial prompts. Evaluated on MIMIC-CXR-ILS, it significantly outperforms existing methods by effectively suppressing mask generation for invalid mentions, and demonstrates strong cross-dataset transferability on CheXlocalize.

Abstract

Radiology reports describe clinical observations but do not specify executable segmentation targets. They may contain present, negated, prior,uncertain, or irrelevant findings, while multiple valid abnormalities may coexist. Existing segmentation methods largely bypass this ambiguity by receiving a target identity or spatial prompt before inference, which acts as a hidden target oracle. We study report-grounded abnormality segmentation, where a model must determine target eligibility, cardinality, and finding-to-mask correspondence directly from an unfiltered report before delineating the corresponding regions. We propose \textbf{EliSeg}, an atcor--verify--revise framework that integrates target construction with mask generation. A grammar-constrained Actor proposes target slots and masks, an independent text-only Verifier reconstructs the eligible finding inventory, and Revision selectively re-executes the shared Actor when their target structures disagree. EliSeg requires no predefined target identity, finding prompt, point, or bounding box. Experiments on MIMIC-CXR-ILS show that EliSeg consistently outperforms direct segmentation methods and extract-then-segment cascades across findings, while effectively suppressing masks for ineligible report mentions. Ablation studies confirm the complementary roles of verification and revision, and evaluation on CheXlocalize demonstrates effective transfer of the EliSeg to an external dataset.Code is available at https://github.com/Maybach-dream/EliSeg.

Problem

• report-grounded segmentation
• abnormality segmentation
• target ambiguity
• radiology report
• finding-to-mask correspondence

Innovation

• report-grounded segmentation
• target construction
• actor-verify-revise framework
• abnormality segmentation
• radiology report interpretation