S2D-ALIGN: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation

• URL: http://arxiv.org/abs/2511.11066v1
• Date: Fri, 14 Nov 2025 08:34:06 GMT
• Title: S2D-ALIGN: Shallow-to-Deep Auxiliary Learning for Anatomically-Grounded Radiology Report Generation
• Authors: Jiechao Gao, Chang Liu, Yuangang Li,
• Abstract summary: Existing methods have leveraged the powerful cross-modal generation capabilities of Multimodal Large Language Models (MLLMs)<n>We propose textscS2D-Align, a novel SFT paradigm that establishes anatomically-grounded alignment by leveraging auxiliary signals of varying granularities.<n>For evaluation, we conduct experiments on the public textscMIMIC-CXR and textscIU X-Ray benchmarks, where textscS2D-Align achieves state-of-the-art performance.
• Score: 8.720883068109774
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Radiology Report Generation (RRG) aims to automatically generate diagnostic reports from radiology images. To achieve this, existing methods have leveraged the powerful cross-modal generation capabilities of Multimodal Large Language Models (MLLMs), primarily focusing on optimizing cross-modal alignment between radiographs and reports through Supervised Fine-Tuning (SFT). However, by only performing instance-level alignment with the image-text pairs, the standard SFT paradigm fails to establish anatomically-grounded alignment, where the templated nature of reports often leads to sub-optimal generation quality. To address this, we propose \textsc{S2D-Align}, a novel SFT paradigm that establishes anatomically-grounded alignment by leveraging auxiliary signals of varying granularities. \textsc{S2D-Align} implements a shallow-to-deep strategy, progressively enriching the alignment process: it begins with the coarse radiograph-report pairing, then introduces reference reports for instance-level guidance, and ultimately utilizes key phrases to ground the generation in specific anatomical details. To bridge the different alignment stages, we introduce a memory-based adapter that empowers feature sharing, thereby integrating coarse and fine-grained guidance. For evaluation, we conduct experiments on the public \textsc{MIMIC-CXR} and \textsc{IU X-Ray} benchmarks, where \textsc{S2D-Align} achieves state-of-the-art performance compared to existing methods. Ablation studies validate the effectiveness of our multi-stage, auxiliary-guided approach, highlighting a promising direction for enhancing grounding capabilities in complex, multi-modal generation tasks.

Related papers

• HAAF: Hierarchical Adaptation and Alignment of Foundation Models for Few-Shot Pathology Anomaly Detection [10.649984141835189]
  We propose the Hierarchical Adaptation and Alignment Framework (HAAF)<n>At its core is a novel Cross-Level Scaled Alignment mechanism that enforces a sequential calibration order.<n>A dual-branch inference strategy integrates semantic scores with geometric prototypes to ensure stability in few-shot settings.
  arXiv  Detail & Related papers  (2026-01-24T10:31:21Z)
• DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities [3.5045368873011924]
  We propose the DiA-gnostic VLVAE, which achieves robust radiology reporting through Disentangled Alignment.<n>Our framework is designed to be resilient to missing modalities by disentangling shared and modality-specific features.<n>A compact LLaMA-X decoder then uses these disentangled representations to generate reports efficiently.
  arXiv  Detail & Related papers  (2025-11-08T11:08:27Z)
• scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration [53.683726781791385]
  We introduce a scalable and flexible generative framework called single-cell Multi-omics Regularized Disentangled Representations (scMRDR) for unpaired multi-omics integration.<n>Our method achieves excellent performance on benchmark datasets in terms of batch correction, modality alignment, and biological signal preservation.
  arXiv  Detail & Related papers  (2025-10-28T21:28:39Z)
• SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning [23.984926906083473]
  Panoptic Scene Graph Generation (PSG) integrates instance segmentation with relation understanding to capture pixel-level structural relationships in complex scenes.<n>Recent approaches leveraging pre-trained vision-language models (VLMs) have significantly improved performance in the open-vocabulary setting.<n>We propose SPADE (SPatial-Aware Denoising-nEtwork) framework -- a novel approach for open-vocabulary PSG.
  arXiv  Detail & Related papers  (2025-07-08T09:03:24Z)
• Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation [50.433911327489554]
  The goal of referring remote sensing image segmentation (RRSIS) is to generate a pixel-level mask of the target object identified by the referring expression.<n>To address the aforementioned challenges, a novel RRSIS framework is proposed, termed the cross-modal bidirectional interaction model (CroBIM)<n>To further forster the research of RRSIS, we also construct RISBench, a new large-scale benchmark dataset comprising 52,472 image-language-label triplets.
  arXiv  Detail & Related papers  (2024-10-11T08:28:04Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• 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)
• Cross-Modal Causal Intervention for Medical Report Generation [107.76649943399168]
  Radiology Report Generation (RRG) is essential for computer-aided diagnosis and medication guidance.<n> generating accurate lesion descriptions remains challenging due to spurious correlations from visual-linguistic biases.<n>We propose a two-stage framework named CrossModal Causal Representation Learning (CMCRL)<n> Experiments on IU-Xray and MIMIC-CXR show that our CMCRL pipeline significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-16T07:23:55Z)
• G$^2$DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification [3.909938091041451]
  RGB-IR person re-identification aims to retrieve person-of-interest between heterogeneous modalities. This paper presents a Geometry-Guided Dual-Alignment learning framework (G$2$DA) to tackle sample-level modality difference.
  arXiv  Detail & Related papers  (2021-06-15T03:14:31Z)
• Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation [61.01704175938995]
  In this paper, we propose a novel Bidirectional Global-to-Local (BiGL) adaptation framework under a UDA scheme. Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor. The proposed method outperforms several state-of-the-art unsupervised domain adaptation methods by a large margin.
  arXiv  Detail & Related papers  (2021-05-17T10:11:45Z)

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.