← VIR Lab
BMVC 2026

GRCD

Grounded Region Change Detection for Multi-Finding Chest X-Ray Pairs

OFM Riaz Rahman Aranya · Peyman Najafirad · Kevin Desai

The University of Texas at San Antonio

Abstract

Radiologists routinely compare current and prior chest X-rays to track disease progression, producing follow-up reports that describe multiple findings, each localised to an anatomical region and annotated with a temporal change status. Existing automated methods either generate reports from a single image without modelling temporal context, or incorporate temporal information but do not ground their outputs spatially. The few approaches that combine temporal reasoning with spatial grounding are restricted to single-finding descriptions, leaving multi-finding reports with mixed change directions unaddressed. We present GRCD, a framework for grounded report generation from chest X-ray pairs in the multi-finding setting. We first construct a rigorously cleaned dataset of temporal chest X-ray pairs by identifying and correcting two systematic labelling errors in the source annotations. We then introduce a Region-Guided Change Token module that encodes per-region temporal change across anatomical structures and injects this signal into a language model through a dual-pathway strategy combining prepended spatial tokens with gated cross-attention. On a multi-finding test set, GRCD outperforms existing baselines on text generation and clinical accuracy metrics, with gains in change detection.

Key Contributions

GRCD addresses the clinically realistic multi-finding setting that prior work leaves unaddressed.

🎯

Multi-Finding Generation

First model to generate temporal reports with multiple co-occurring findings, each with its own change label and bounding box grounding.

🧹

Data Cleaning Pipeline

Three-tier pipeline that identifies and corrects two systematic errors in Chest ImaGenome: same-study AP retakes and silent NLP absence. Yields a 40,250-pair benchmark.

🧠

Dual-Pathway RGCT

Region-Guided Change Tokens encode per-region temporal change and reach the LLM via both prepended tokens and gated cross-attention for complementary spatial signals.

Architecture

GRCD combines a frozen BioViL-T temporal encoder with a Region-Guided Change Token module and an autoregressive LLM decoder.

GRCD Architecture

The RGCT module crops 25 anatomical regions from both feature maps, compares them across time, and produces 25 change tokens. Six key tokens are prepended to the LLM input (Pathway A), while all 25 are injected via gated cross-attention (Pathway B).

Dataset Construction

We identify and fix two systematic errors in standard Chest ImaGenome temporal pair construction.

Source
243K Scene Graphs
Chest ImaGenome v1.0
→
Pairing
179K Pairs
Adjacent studies
→
Fix 1
-25K Same-Study
AP retake removal
→
Fix 2
-113K Tier-3
Silent absence filter
→
Final
40,250 Pairs
28K train / 4K val / 8K test

Issue 1: Same-Study AP Retakes

14% of pairs come from the same exam (duplicate AP exposures). Both images share one report, so no temporal information can be learned. Removed by checking study ID equality.

Issue 2: Silent NLP Absence

77% of NEW/RESOLVED transitions lack textual evidence. NLP-derived labels fabricate change when findings are simply omitted. Three-tier confidence system retains only verified labels.

Main Results

Evaluated on 7,967 multi-finding test pairs. GRCD values are mean ± std over 3 seeds.

Metric BioViL-T Clf Retrieval TRACE GRCD (Ours)
Natural Language Generation
BLEU-4 — 0.273 0.078 0.398 ± 0.003
METEOR — 0.374 0.213 0.494 ± 0.003
ROUGE-L — 0.376 0.176 0.493 ± 0.003
Clinical Accuracy
CheXbert F1 — 0.368 0.175 0.567 ± 0.009
RadGraph F1 — 0.353 0.222 0.473 ± 0.002
Grounding
Mean IoU — — 0.545 0.540 ± 0.005
IoU > 0.5 — — 64.0% 61.4 ± 0.5%
Change Detection
Report-level 37.6% — 39.8% 53.3 ± 0.2%
Balanced Acc. 46.6% — 35.7% 50.0 ± 0.3%
GRCD qualitative examples

Qualitative examples. Each row: the prior CXR, the current CXR with ground-truth boxes, and with GRCD's predicted boxes. Box colours mark change type (worsening / improving / stable); green and red text highlight matched and mismatched report sentences.

Ablation Study

Each component contributes to the final performance. RGCT is essential; dual pathway outperforms either strategy alone.

Configuration BLEU-4 METEOR CheXbert F1 IoU > 0.5 Change Det.
A: No RGCT 0.007 0.067 0.062 — 37.6%
B: 6-region, prepend only 0.362 0.467 0.570 64.2% 51.6%
C: 25-region, cross-attention only 0.394 0.476 0.512 57.9% 54.4%
D: 25-region, dual pathway (GRCD) 0.402 0.498 0.576 61.8% 53.6%

Citation

@inproceedings{aranya2026grcd, title = {GRCD: Grounded Region Change Detection for Multi-Finding Chest X-Ray Pairs}, author = {Aranya, OFM Riaz Rahman and Najafirad, Peyman and Desai, Kevin}, booktitle = {British Machine Vision Conference (BMVC)}, year = {2026} }