TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation

• URL: http://arxiv.org/abs/2602.02963v1
• Date: Tue, 03 Feb 2026 01:03:41 GMT
• Title: TRACE: Temporal Radiology with Anatomical Change Explanation for Grounded X-ray Report Generation
• Abstract summary: 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.
• Score: 4.726777092009554
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal comparison of chest X-rays is fundamental to clinical radiology, enabling detection of disease progression, treatment response, and new findings. While vision-language models have advanced single-image report generation and visual grounding, no existing method combines these capabilities for temporal change detection. We introduce Temporal Radiology with Anatomical Change Explanation (TRACE), the first model that jointly performs temporal comparison, change classification, and spatial localization. Given a prior and current chest X-ray, TRACE generates natural language descriptions of interval changes (worsened, improved, stable) while grounding each finding with bounding box coordinates. TRACE demonstrates effective spatial localization with over 90% grounding accuracy, establishing a foundation for this challenging new task. Our ablation study uncovers an emergent capability: change detection arises only when temporal comparison and spatial grounding are jointly learned, as neither alone enables meaningful change detection. This finding suggests that grounding provides a spatial attention mechanism essential for temporal reasoning.

Related papers

• How Good are Foundation Models in Longitudinal MRI Disease Progression Reasoning? [49.14050864978079]
  We introduce the Time-Aware Multi-View MRI Benchmark, an evaluation framework unifying multi-view anatomical input, temporal reasoning, and structured localization guidance.<n>The benchmark comprises 3,920 expert-verified question-answer pairs derived from 890 patients across over 3,200 longitudinal MRI timepoints.
  arXiv  Detail & Related papers  (2026-08-13T14:35:20Z)
• CT-$Δ$Bench: A Benchmark for Longitudinal 3D Medical Imaging Difference Reporting with Vision-Language Models [21.022823890203597]
  longitudinal imaging difference reporting is a task in which a model takes two temporally separated scans from the same patient and generates a clinically meaningful report.<n>We introduce CT-$$Bench, a dedicated benchmark for this task with patient-level splitting to prevent information leakage.<n>We also develop change-aware metrics specifically designed to capture clinically meaningful longitudinal changes, and conduct an independent physician validation.
  arXiv  Detail & Related papers  (2026-08-12T00:55:31Z)
• ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI Prediction [81.07048249760953]
  longitudinal changes are often subtle and confined to specific anatomical regions.<n>Most subject-specific brain structure remains stable over time.<n>ProgFormer is a hierarchical voxel-space Diffusion Transformer for longitudinal brain MRI prediction.
  arXiv  Detail & Related papers  (2026-07-30T00:13:42Z)
• GRCD: Grounded Region Change Detection for Multi-Finding Chest X-Ray Pairs [7.272024968089535]
  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.
  arXiv  Detail & Related papers  (2026-07-02T19:14:50Z)
• CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography [11.122386852153546]
  We introduce CheXTemporal, a dataset for temporally grounded reasoning in chest radiography consisting of paired prior-current chest X-rays.<n>The dataset includes a five-class progression taxonomy (new, worse, stable, improved, resolved), localized spatial supervision of pathology, explicit spatial-temporal alignment.<n>We evaluate multiple vision-language CXR models on grounding and progression-classification tasks in a zero-shot setting.
  arXiv  Detail & Related papers  (2026-05-11T22:47:24Z)
• Temporal Inversion for Learning Interval Change in Chest X-Rays [3.686530147760242]
  We introduce TILA (Temporal Inversion-aware Learning and Alignment), a framework that uses temporal inversion, reversing image pairs, as a supervisory signal.<n>TILA integrates inversion-aware objectives across pretraining, fine-tuning, and inference, complementing conventional appearance modeling with explicit learning of temporal order.<n>We also propose a unified evaluation protocol to assess order sensitivity and consistency under temporal inversion, and introduce MS-CXR-Tretrieval, a retrieval evaluation set constructed through a general protocol.
  arXiv  Detail & Related papers  (2026-04-06T09:52:26Z)
• A Diffusion-Driven Fine-Grained Nodule Synthesis Framework for Enhanced Lung Nodule Detection from Chest Radiographs [2.45811518457038]
  Early detection of lung cancer in chest radiographs (CXRs) is crucial for improving patient outcomes.<n>No nodule detection remains challenging due to their subtle appearance and variability in radiological characteristics.<n>This paper proposes a novel diffusion-based framework with low-rank adaptation (LoRA) adapters for characteristic controlled nodule synthesis on CXRs.
  arXiv  Detail & Related papers  (2026-03-02T09:43:58Z)
• Capturing Longitudinal Changes in Brain Morphology Using Temporally Parameterized Neural Displacement Fields [1.8124328823188356]
  We propose a novel longitudinal registration method that models structural changes using temporally parameterized neural displacement fields.<n>We demonstrate the effectiveness of our method on 4D brain MR registration.
  arXiv  Detail & Related papers  (2025-04-13T10:38:00Z)
• A Comparison of Object Detection and Phrase Grounding Models in Chest X-ray Abnormality Localization using Eye-tracking Data [1.4272411349249625]
  This paper investigates how text enhances abnormality localization in chest X-rays by comparing the performance and explainability of these two tasks.<n>To establish an explainability baseline, we proposed an automatic pipeline to generate image regions for report sentences using radiologists' eye-tracking data.<n>The better performance - mIoU = 0.36 vs. 0.20 - and explainability - Containment ratio 0.48 vs. 0.26 - of the phrase grounding model infers the effectiveness of text in enhancing chest X-ray abnormality localization.
  arXiv  Detail & Related papers  (2025-03-02T21:54:47Z)
• Domain Adaptive Lung Nodule Detection in X-ray Image [3.660022474436894]
  We introduce a novel domain adaptive approach for lung nodule detection that leverages mean teacher self-training and contrastive learning. First, we propose a hierarchical contrastive learning strategy to refine nodule representations and enhance the distinction between nodules and background. Second, we introduce a nodule-level domain-invariant feature learning (NDL) module to capture domain-invariant features through adversarial learning.
  arXiv  Detail & Related papers  (2024-07-28T04:46:55Z)
• RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning [14.440200446778642]
  We propose RECAP, which generates precise and accurate radiology reports via dynamic disease progression reasoning. It then combines the historical records,temporal information, and radiographs for report generation, where a progression graph and dynamic progression reasoning mechanism are devised to accurately select the attributes of each observation and progression.
  arXiv  Detail & Related papers  (2023-10-21T00:05:32Z)
• DeepLOC: Deep Learning-based Bone Pathology Localization and Classification in Wrist X-ray Images [1.45543311565555]
  This paper presents a novel approach for bone pathology localization and classification in wrist X-ray images. The proposed methodology addresses two critical challenges in wrist X-ray analysis: accurate localization of bone pathologies and precise classification of abnormalities.
  arXiv  Detail & Related papers  (2023-08-24T12:06:10Z)
• 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)
• SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection [76.01333073259677]
  We propose the use of Space-aware Memory Queues for In-painting and Detecting anomalies from radiography images (abbreviated as SQUID) We show that SQUID can taxonomize the ingrained anatomical structures into recurrent patterns; and in the inference, it can identify anomalies (unseen/modified patterns) in the image.
  arXiv  Detail & Related papers  (2021-11-26T13:47:34Z)
• SpineOne: A One-Stage Detection Framework for Degenerative Discs and Vertebrae [54.751251046196494]
  We propose a one-stage detection framework termed SpineOne to simultaneously localize and classify degenerative discs and vertebrae from MRI slices. SpineOne is built upon the following three key techniques: 1) a new design of the keypoint heatmap to facilitate simultaneous keypoint localization and classification; 2) the use of attention modules to better differentiate the representations between discs and vertebrae; and 3) a novel gradient-guided objective association mechanism to associate multiple learning objectives at the later training stage.
  arXiv  Detail & Related papers  (2021-10-28T12:59:06Z)
• Generative Residual Attention Network for Disease Detection [51.60842580044539]
  We present a novel approach for disease generation in X-rays using a conditional generative adversarial learning. We generate a corresponding radiology image in a target domain while preserving the identity of the patient. We then use the generated X-ray image in the target domain to augment our training to improve the detection performance.
  arXiv  Detail & Related papers  (2021-10-25T14:15:57Z)
• Contralaterally Enhanced Networks for Thoracic Disease Detection [120.60868136876599]
  There exist many similar structures in the left and right parts of the chest, such as ribs, lung fields and bronchial tubes. This kind of similarities can be used to identify diseases in chest X-rays, according to the experience of broad-certificated radiologists. We propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals.
  arXiv  Detail & Related papers  (2020-10-09T10:15:26Z)
• 4D Spatio-Temporal Deep Learning with 4D fMRI Data for Autism Spectrum Disorder Classification [69.62333053044712]
  We propose a 4D convolutional deep learning approach for ASD classification where we jointly learn from spatial and temporal data. We employ 4D neural networks and convolutional-recurrent models which outperform a previous approach with an F1-score of 0.71 compared to an F1-score of 0.65.
  arXiv  Detail & Related papers  (2020-04-21T17:19:06Z)

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.