# BUSTR: Descriptor-Aware Vision-Language Learning for Breast Ultrasound Report Generation

arXiv: https://arxiv.org/abs/2511.20956 · HTML: https://mlsanity.com/paper/2511.20956/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 26 Nov 2025.

## Builds on (most cited first, 16 of 16)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Generating Radiology Reports via Memory-driven Transformer](https://mlsanity.com/paper/2010.16056/) (2020)
- [Cross-modal Memory Networks for Radiology Report Generation](https://mlsanity.com/paper/2204.13258/) (2022)
- [R2GenGPT: Radiology Report Generation with Frozen LLMs](https://mlsanity.com/paper/2309.09812/) (2023)
- [METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens](https://mlsanity.com/paper/2304.02211/) (2023)
- [Improving Radiology Report Generation Systems by Removing Hallucinated References to Non-existent Priors](https://mlsanity.com/paper/2210.06340/) (2022)
- [BUSIS: A Benchmark for Breast Ultrasound Image Segmentation](https://mlsanity.com/paper/1801.03182/) (2018)
- [Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & Hallucinations](https://mlsanity.com/paper/2402.07023/) (2024)
- [Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance](https://mlsanity.com/paper/2406.00644/) (2024)
- [RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment](https://mlsanity.com/paper/2501.07525/) (2025)
- [ESTAN: Enhanced Small Tumor-Aware Network for Breast Ultrasound Image Segmentation](https://mlsanity.com/paper/2009.12894/) (2020)
- [DART: Disease-aware Image-Text Alignment and Self-correcting Re-alignment for Trustworthy Radiology Report Generation](https://mlsanity.com/paper/2504.11786/) (2025)
- [Breast Ultrasound Tumor Classification Using a Hybrid Multitask CNN-Transformer Network](https://mlsanity.com/paper/2308.02101/) (2023)
- [AI assisted method for efficiently generating breast ultrasound screening reports](https://mlsanity.com/paper/2107.13431/) (2021)

## Abstract (arXiv)

Breast ultrasound (BUS) reporting relies on clinically meaningful lesion descriptors, including BI-RADS category, lesion shape, margin, echogenicity, posterior features, pathology, and histology. However, many public BUS datasets provide structured annotations and lesion masks without paired radiologist-written reports, limiting the development of vision--language models for BUS report generation. We propose BUSTR, a descriptor-aware vision--language framework that uses structured lesion information to enable report generation under limited report supervision. BUSTR first constructs descriptor-derived reports from available annotations and radiomics features extracted from lesion masks. It then trains a multi-head Swin Transformer encoder with multitask supervision to learn descriptor-aware visual representations across datasets with partially overlapping annotation sets. The projected visual tokens condition a frozen LLaMA-based language model, and training is guided by a dual-level objective combining token-level cross-entropy with representation-level cosine alignment. At inference, BUSTR generates reports from BUS images without access to structured descriptors, lesion masks, or radiomics features. We evaluate BUSTR on the public BrEaST and BUS-BRA datasets using natural language generation and clinical efficacy metrics. BUSTR improves report similarity and descriptor recovery compared with representative report-generation baselines, with notable gains for lesion shape, margin, posterior features, and pathology, as well as improved BI-RADS sensitivity and F1-score on BrEaST. These results suggest that structured BUS descriptors, lesion masks, and radiomics features can provide useful supervision for descriptor-aware BUS report generation when paired radiologist-written reports are unavailable.