@inproceedings{liu-etal-2026-breastgpt,
title = "{B}reast{GPT}: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine",
author = "Liu, Yang and
Zhang, Jiajin and
Tu, Danyang and
Hu, Yaojun and
Qu, Jiao and
Zhang, Jiuyu and
Shi, Yu and
Fang, Wei and
Gu, Shi and
Zhang, Ling and
Xia, Yingda",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.740/",
pages = "17144--17178",
ISBN = "979-8-89176-459-0",
abstract = "Breast cancer care requires multimodal reasoning across a clinical workflow spanning \textit{screening}, \textit{diagnosis}, and \textit{treatment planning}. However, existing medical MLLMs are typically limited to isolated modalities or narrow task settings, restricting their ability to support workflow-level clinical reasoning. To address this gap, we introduce \textbf{BreastStage}, a workflow-aligned breast imaging instruction corpus containing 1.86M instruction-following pairs from 17 sub-datasets, 5 imaging modalities, and 136 task templates, together with \textbf{BreastStage-Bench}, a benchmark for evaluating multimodal reasoning across the breast cancer care continuum. Built upon this corpus, we propose \textbf{BreastGPT}, a unified MLLM with a dual-branch visual encoder and concept-preserving token compression to bridge standard radiology and gigapixel pathology. On BreastStage-Bench, BreastGPT achieves 75.66{\%} closed-ended accuracy and 89.92{\%} open-ended score, outperforming both general-purpose and medical-specific MLLMs across clinical stages and task formats. Data, code, and model checkpoints are publicly released at \url{https://anonymous.4open.science/w/BreastGPT_io/}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-breastgpt">
<titleInfo>
<title>BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danyang</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaojun</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiao</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiuyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingda</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Breast cancer care requires multimodal reasoning across a clinical workflow spanning screening, diagnosis, and treatment planning. However, existing medical MLLMs are typically limited to isolated modalities or narrow task settings, restricting their ability to support workflow-level clinical reasoning. To address this gap, we introduce BreastStage, a workflow-aligned breast imaging instruction corpus containing 1.86M instruction-following pairs from 17 sub-datasets, 5 imaging modalities, and 136 task templates, together with BreastStage-Bench, a benchmark for evaluating multimodal reasoning across the breast cancer care continuum. Built upon this corpus, we propose BreastGPT, a unified MLLM with a dual-branch visual encoder and concept-preserving token compression to bridge standard radiology and gigapixel pathology. On BreastStage-Bench, BreastGPT achieves 75.66% closed-ended accuracy and 89.92% open-ended score, outperforming both general-purpose and medical-specific MLLMs across clinical stages and task formats. Data, code, and model checkpoints are publicly released at https://anonymous.4open.science/w/BreastGPT_io/.</abstract>
<identifier type="citekey">liu-etal-2026-breastgpt</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.740/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>17144</start>
<end>17178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine
%A Liu, Yang
%A Zhang, Jiajin
%A Tu, Danyang
%A Hu, Yaojun
%A Qu, Jiao
%A Zhang, Jiuyu
%A Shi, Yu
%A Fang, Wei
%A Gu, Shi
%A Zhang, Ling
%A Xia, Yingda
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F liu-etal-2026-breastgpt
%X Breast cancer care requires multimodal reasoning across a clinical workflow spanning screening, diagnosis, and treatment planning. However, existing medical MLLMs are typically limited to isolated modalities or narrow task settings, restricting their ability to support workflow-level clinical reasoning. To address this gap, we introduce BreastStage, a workflow-aligned breast imaging instruction corpus containing 1.86M instruction-following pairs from 17 sub-datasets, 5 imaging modalities, and 136 task templates, together with BreastStage-Bench, a benchmark for evaluating multimodal reasoning across the breast cancer care continuum. Built upon this corpus, we propose BreastGPT, a unified MLLM with a dual-branch visual encoder and concept-preserving token compression to bridge standard radiology and gigapixel pathology. On BreastStage-Bench, BreastGPT achieves 75.66% closed-ended accuracy and 89.92% open-ended score, outperforming both general-purpose and medical-specific MLLMs across clinical stages and task formats. Data, code, and model checkpoints are publicly released at https://anonymous.4open.science/w/BreastGPT_io/.
%U https://aclanthology.org/2026.emnlp-main.740/
%P 17144-17178
Markdown (Informal)
[BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine](https://aclanthology.org/2026.emnlp-main.740/) (Liu et al., EMNLP 2026)
ACL
- Yang Liu, Jiajin Zhang, Danyang Tu, Yaojun Hu, Jiao Qu, Jiuyu Zhang, Yu Shi, Wei Fang, Shi Gu, Ling Zhang, and Yingda Xia. 2026. BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 17144–17178, Budapest, Hungary. Association for Computational Linguistics.