# Anatomical Attention Alignment representation for Radiology Report Generation

arXiv: https://arxiv.org/abs/2505.07689 · HTML: https://mlsanity.com/paper/2505.07689/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 12 May 2025.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning](https://mlsanity.com/paper/1612.01887/) (2016)
- [Cross-modal Memory Networks for Radiology Report Generation](https://mlsanity.com/paper/2204.13258/) (2022)
- [Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation](https://mlsanity.com/paper/1805.08298/) (2018)
- [Competence-based Multimodal Curriculum Learning for Medical Report Generation](https://mlsanity.com/paper/2206.14579/) (2022)
- [A Medical Semantic-Assisted Transformer for Radiographic Report Generation](https://mlsanity.com/paper/2208.10358/) (2022)
- [R2Gen-Mamba: A Selective State Space Model for Radiology Report Generation](https://mlsanity.com/paper/2410.18135/) (2024)
- [On the Importance of Image Encoding in Automated Chest X-Ray Report Generation](https://mlsanity.com/paper/2211.13465/) (2022)

## Built on by (most cited first, 1 of 1)

- [Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset](https://mlsanity.com/paper/2610.08813/) (2026)

## Abstract (arXiv)

Automated Radiology report generation (RRG) aims at producing detailed descriptions of medical images, reducing radiologists' workload and improving access to high-quality diagnostic services. Existing encoder-decoder models only rely on visual features extracted from raw input images, which can limit the understanding of spatial structures and semantic relationships, often resulting in suboptimal text generation. To address this, we propose Anatomical Attention Alignment Network (A3Net), a framework that enhance visual-textual understanding by constructing hyper-visual representations. Our approach integrates a knowledge dictionary of anatomical structures with patch-level visual features, enabling the model to effectively associate image regions with their corresponding anatomical entities. This structured representation improves semantic reasoning, interpretability, and cross-modal alignment, ultimately enhancing the accuracy and clinical relevance of generated reports. Experimental results on IU X-Ray and MIMIC-CXR datasets demonstrate that A3Net significantly improves both visual perception and text generation quality. Our code is available at hrefhttps://github.com/Vinh-AI/A3NetGitHub.