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

• URL: http://arxiv.org/abs/2607.02719v1
• Date: Thu, 02 Jul 2026 19:14:50 GMT
• Title: GRCD: Grounded Region Change Detection for Multi-Finding Chest X-Ray Pairs
• Abstract summary: GRCD is a framework for grounded report generation from chest X-ray pairs in the multi-finding setting.<n>We first construct a rigorously cleaned dataset of temporal chest X-ray pairs.<n>We then introduce a Region-Guided Change Token module that encodes per-region temporal change across anatomical structures.
• Score: 7.272024968089535
• License: http://creativecommons.org/licenses/by/4.0/
• 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. Ablation studies confirm that the dual-pathway design outperforms either integration strategy in isolation on text and clinical metrics, and that region-level change encoding is necessary for multi-finding generation. Code is available at https://github.com/UTSA-VIRLab/GRCD

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• ALTER: Modeling Longitudinal Changes via Regional Differencing for 3D CT Report Generation [2.9905735389905153]
  Anatomically Localized Temporal Evidence Representation (ALTER)<n>General Prior Integration (GPI) incorporates the prior CT and report to establish historical context for the current examination.<n>Regional Proxy Differencing (RPD) enables each current anatomical region to retrieve a historical proxy from a single shared encoding of the prior volume and to derive localized interval evidence.<n> Interval Change Fusion (ICF) converts current abnormality states with region-distributed differences into change-aware soft prompts that guide report generation.
  arXiv  Detail & Related papers  (2026-08-06T05:27:38Z)
• CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation [5.6071155906499115]
  Category-Wise Contrastive Decoding (CWCD) is a novel and modular framework designed to enhance structured radiology report generation (SRRG)<n>CWCD consistently outperforms baseline methods across both clinical efficacy and natural language generation metrics.
  arXiv  Detail & Related papers  (2026-04-12T02:10:28Z)
• TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation [4.726777092009554]
  We introduce Temporal Radiology with Anatomical Change Explanation (TRACE), the first model that jointly performs temporal comparison, change classification, and spatial localization.<n>Given a prior and current chest X-ray, TRACE generates natural language descriptions of interval changes while grounding each finding with bounding box coordinates.<n>Our ablation study uncovers an emergent capability: change detection arises only when temporal comparison and spatial grounding are jointly learned.
  arXiv  Detail & Related papers  (2026-02-03T01:03:41Z)
• Large Language Model with Region-guided Referring and Grounding for CT Report Generation [4.804660464589285]
  Existing methods primarily only consider the global features of the entire volume.<n>We propose Reg2RG, the first region-guided referring and grounding framework for CT report generation.
  arXiv  Detail & Related papers  (2024-11-23T12:25:06Z)
• Towards a Benchmark for Colorectal Cancer Segmentation in Endorectal Ultrasound Videos: Dataset and Model Development [59.74920439478643]
  In this paper, we collect and annotated the first benchmark dataset that covers diverse ERUS scenarios. Our ERUS-10K dataset comprises 77 videos and 10,000 high-resolution annotated frames. We introduce a benchmark model for colorectal cancer segmentation, named the Adaptive Sparse-context TRansformer (ASTR)
  arXiv  Detail & Related papers  (2024-08-19T15:04:42Z)
• Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment [59.75420353684495]
  Machine learning applications on signals such as computer vision or biomedical data often face challenges due to the variability that exists across hardware devices or session recordings. In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities. We show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings.
  arXiv  Detail & Related papers  (2024-07-19T13:33:38Z)
• Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation [48.723504098917324]
  We propose an Unify, Align and then Refine (UAR) approach to learn multi-level cross-modal alignments. We introduce three novel modules: Latent Space Unifier, Cross-modal Representation Aligner and Text-to-Image Refiner. Experiments and analyses on IU-Xray and MIMIC-CXR benchmark datasets demonstrate the superiority of our UAR against varied state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-28T12:42:12Z)
• Medical Image Captioning via Generative Pretrained Transformers [57.308920993032274]
  We combine two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The proposed model is tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO.
  arXiv  Detail & Related papers  (2022-09-28T10:27:10Z)
• Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays [65.88435151891369]
  Radiomics-Guided Transformer (RGT) fuses textitglobal image information with textitlocal knowledge-guided radiomics information. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomic information.
  arXiv  Detail & Related papers  (2022-07-10T06:32:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.