@inproceedings{guo-etal-2026-mm,
title = "{MM}-{N}euro{O}nco: A Multimodal Benchmark and Instruction Dataset for {MRI}-Based Brain Tumor Diagnosis",
author = "Guo, Feng and
Liu, Jiaxiang and
Li, Yang and
Shi, Qianqian and
Xu, Mingkun",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.128/",
pages = "2818--2845",
ISBN = "979-8-89176-439-2",
abstract = "Brain tumor MRI diagnosis requires models not only to identify lesions but also to perform fine-grained medical reasoning based on imaging modality, tumor location, and key imaging findings. However, existing medical multimodal datasets often lack structured diagnostic semantics, and closed-ended evaluations may overestimate model ability due to option cues or elimination shortcuts. To address this issue, we introduce MM-NeuroOnco, a large-scale multimodal instruction dataset and benchmark for brain tumor MRI diagnostic reasoning, containing 24,726 MRI slices from 20 public data sources and approximately 200,000 multimodal instructions grounded in imaging evidence. We develop a multi-model collaborative pipeline for semantic completion and quality control, which supplements original tumor labels and segmentation masks with key diagnostic attributes, and further construct MM-NeuroOnco-Bench with a no-LLM-inference policy for ground-truth labels. The benchmark adds a ``None of the above'' option to closed-ended questions to reduce evaluation bias caused by option shortcuts. Experiments show that existing general-purpose and medical-specialist multimodal large models remain limited on this task, with the strongest baseline achieving only 41.88{\%} accuracy on diagnosis-related questions. Fine-tuning on MM-NeuroOnco yields NeuroOnco-GPT, achieving a 27{\%} absolute accuracy improvement and demonstrating the effectiveness of our dataset in enhancing fine-grained multimodal medical reasoning. Code and dataset documentation are available at https://github.com/gfnnnb/MM-NeuroOnco."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-mm">
<titleInfo>
<title>MM-NeuroOnco: A Multimodal Benchmark and Instruction Dataset for MRI-Based Brain Tumor Diagnosis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingkun</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Brain tumor MRI diagnosis requires models not only to identify lesions but also to perform fine-grained medical reasoning based on imaging modality, tumor location, and key imaging findings. However, existing medical multimodal datasets often lack structured diagnostic semantics, and closed-ended evaluations may overestimate model ability due to option cues or elimination shortcuts. To address this issue, we introduce MM-NeuroOnco, a large-scale multimodal instruction dataset and benchmark for brain tumor MRI diagnostic reasoning, containing 24,726 MRI slices from 20 public data sources and approximately 200,000 multimodal instructions grounded in imaging evidence. We develop a multi-model collaborative pipeline for semantic completion and quality control, which supplements original tumor labels and segmentation masks with key diagnostic attributes, and further construct MM-NeuroOnco-Bench with a no-LLM-inference policy for ground-truth labels. The benchmark adds a “None of the above” option to closed-ended questions to reduce evaluation bias caused by option shortcuts. Experiments show that existing general-purpose and medical-specialist multimodal large models remain limited on this task, with the strongest baseline achieving only 41.88% accuracy on diagnosis-related questions. Fine-tuning on MM-NeuroOnco yields NeuroOnco-GPT, achieving a 27% absolute accuracy improvement and demonstrating the effectiveness of our dataset in enhancing fine-grained multimodal medical reasoning. Code and dataset documentation are available at https://github.com/gfnnnb/MM-NeuroOnco.</abstract>
<identifier type="citekey">guo-etal-2026-mm</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.128/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2818</start>
<end>2845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MM-NeuroOnco: A Multimodal Benchmark and Instruction Dataset for MRI-Based Brain Tumor Diagnosis
%A Guo, Feng
%A Liu, Jiaxiang
%A Li, Yang
%A Shi, Qianqian
%A Xu, Mingkun
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F guo-etal-2026-mm
%X Brain tumor MRI diagnosis requires models not only to identify lesions but also to perform fine-grained medical reasoning based on imaging modality, tumor location, and key imaging findings. However, existing medical multimodal datasets often lack structured diagnostic semantics, and closed-ended evaluations may overestimate model ability due to option cues or elimination shortcuts. To address this issue, we introduce MM-NeuroOnco, a large-scale multimodal instruction dataset and benchmark for brain tumor MRI diagnostic reasoning, containing 24,726 MRI slices from 20 public data sources and approximately 200,000 multimodal instructions grounded in imaging evidence. We develop a multi-model collaborative pipeline for semantic completion and quality control, which supplements original tumor labels and segmentation masks with key diagnostic attributes, and further construct MM-NeuroOnco-Bench with a no-LLM-inference policy for ground-truth labels. The benchmark adds a “None of the above” option to closed-ended questions to reduce evaluation bias caused by option shortcuts. Experiments show that existing general-purpose and medical-specialist multimodal large models remain limited on this task, with the strongest baseline achieving only 41.88% accuracy on diagnosis-related questions. Fine-tuning on MM-NeuroOnco yields NeuroOnco-GPT, achieving a 27% absolute accuracy improvement and demonstrating the effectiveness of our dataset in enhancing fine-grained multimodal medical reasoning. Code and dataset documentation are available at https://github.com/gfnnnb/MM-NeuroOnco.
%U https://aclanthology.org/2026.aacl-long.128/
%P 2818-2845
Markdown (Informal)
[MM-NeuroOnco: A Multimodal Benchmark and Instruction Dataset for MRI-Based Brain Tumor Diagnosis](https://aclanthology.org/2026.aacl-long.128/) (Guo et al., AACL-IJCNLP 2026)
ACL