Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 49 min ago
Peer-reviewedCC BY 4.0Frontiers in Immunology

Pathology-guided multimodal transformer predicts postoperative survival benefit from adjuvant chemotherapy in glioma: from DNA damage repair to immune characterization

  • Zehui Li1,2
  • Xin Duan1,2
  • Junjie Lian2
  • Xuan Li1,2
  • Qian Liang1,2
  • Xu Liu2
  • Yan Tan1,2
  • Guoqiang Yang1,2
  • Jiangfeng Du1,2,3
  • Lina Wu4
  • Xiaochun Wang1,2
  • Hui Zhang1,2,3
4 affiliations
  1. 1Department of Radiology, First Hospital of Shanxi Medical University
  2. 2College of Medical Imaging, Shanxi Medical University
  3. 3Intelligent Imaging Big Data and Functional Nano-imaging Engineering Research Center of Shanxi Province, First Hospital of Shanxi Medical University
  4. 4Department of Pathology, First Hospital of Shanxi Medical University
Read full textPDFDOICite

Abstract

Introduction: High-grade gliomas (HGGs) are aggressive primary brain tumors with high recurrence rates and poor prognosis. Survival benefit from adjuvant temozolomide (TMZ) varies substantially across patients, and reliable preoperative biomarkers for treatment stratification remain limited. This study aims to develop an interpretable multimodal deep learning model integrating whole-slide histopathological images and multiparametric MRI to preoperatively predict survival benefit from adjuvant TMZ in HGG patients.

Methods: A Transformer-based multimodal fusion model was proposed. Key tumor regions were identified from whole-slide pathology images via weakly supervised clustering, and pathological features were extracted using attention-based multiple instance learning. Concurrently, 2.5D tumor subregional features were derived from multiparametric MRI sequences. These multimodal features were deeply fused using a Transformer encoder. The model was developed and validated on a multicenter cohort (504 patients), and its biological basis was explored through transcriptomic analysis, gene set enrichment analysis, protein-protein interaction networks, and immune deconvolution.

Results: The fusion model achieved AUCs of 0.910, 0.861, and 0.833 in the training, internal validation, and external validation cohorts, respectively. Transcriptomic analysis implicated DNA damage repair processes in high-benefit patients, suggesting that enhanced DNA repair capacity may contribute to TMZ sensitivity. Immune deconvolution showed higher M1 macrophage infiltration and lower regulatory T cell abundance in the high-benefit group, consistent with a less immunosuppressive tumor microenvironment. Importantly, low-benefit patients who completed TMZ chemotherapy had shorter survival than those treated with concurrent chemoradiotherapy alone or surgery alone.

Conclusion: This model identifies patients unlikely to benefit from standard TMZ chemotherapy, providing a tool for postoperative personalized treatment stratification and optimization of therapeutic strategies in HGGs.

Related

  1. Transformer-Based Multimodal Fusion Integrating Computed Tomography, Pathology, and Clinical Features for Oral Squamous Cell Carcinoma Recurrence Prediction
    Shuwen Yang, Fuyong Sui, Zhuang Liang +4
    International Dental JournalPeer-reviewedCC BYFull textMedical imaging & radiologyDOAJ
  2. Postoperative malnutrition predicts severe chemotherapy toxicity after gastrectomy: evaluation of an inflammation-anemia phenotype
    Jiangtao Zhao, Zhengyu Jin
    Open MedicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  3. Multimodal prediction of neoadjuvant chemotherapy response in locally advanced gastric cancer: a multicenter cohort study
    Ping’an Ding, Honghai Guo, Jiaxuan Yang +12
    BMC MedicinePeer-reviewedCC BY 4.0General medicineCrossref
  4. Chemotherapy Use, Healthcare Resource Utilisation, and Direct Costs in High-Risk Early-Stage ER+/HER2– Breast Cancer in Italy: A Real-World Study Linking Administrative and Pathology Data
    Carmen Criscitiello, Valentina Perrone, Luca Degli Esposti +4
    CancersPeer-reviewedCC BY 4.0OncologyCrossref
  5. Multi-Scale MRI, Radiology Reports, and Blood Biomarker–Guided Multimodal Deep Learning for Predicting Postoperative Recurrence in Cervical Cancer: A Multicenter Study
    Yiyang Wu, Yao Ai, Yangyang Zhang +8
    CancersPeer-reviewedCC BYFull textOncologyEurope PMC

Cite

BibTeXRIS
BibTeX
@article{li2026pathologyguided,
  title = {{Pathology-guided multimodal transformer predicts postoperative survival benefit from adjuvant chemotherapy in glioma: from DNA damage repair to immune characterization}},
  author = {Zehui Li and Xin Duan and Junjie Lian and Xuan Li and Qian Liang and Xu Liu and Yan Tan and Guoqiang Yang and Jiangfeng Du and Lina Wu and Xiaochun Wang and Hui Zhang},
  journal = {Frontiers in Immunology},
  year = {2026},
  month = oct,
  doi = {10.3389/fimmu.2026.1845251},
  url = {https://www.frontiersin.org/articles/10.3389/fimmu.2026.1845251/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Pathology-guided multimodal transformer predicts postoperative survival benefit from adjuvant chemotherapy in glioma: from DNA damage repair to immune characterization
AU  - Zehui Li
AU  - Xin Duan
AU  - Junjie Lian
AU  - Xuan Li
AU  - Qian Liang
AU  - Xu Liu
AU  - Yan Tan
AU  - Guoqiang Yang
AU  - Jiangfeng Du
AU  - Lina Wu
AU  - Xiaochun Wang
AU  - Hui Zhang
PY  - 2026
DA  - 2026/10/16
JO  - Frontiers in Immunology
DO  - 10.3389/fimmu.2026.1845251
UR  - https://www.frontiersin.org/articles/10.3389/fimmu.2026.1845251/full
AB  - Introduction: High-grade gliomas (HGGs) are aggressive primary brain tumors with high recurrence rates and poor prognosis. Survival benefit from adjuvant temozolomide (TMZ) varies substantially across patients, and reliable preoperative biomarkers for treatment stratification remain limited. This study aims to develop an interpretable multimodal deep learning model integrating whole-slide histopathological images and multiparametric MRI to preoperatively predict survival benefit from adjuvant TMZ in HGG patients.  Methods: A Transformer-based multimodal fusion model was proposed. Key tumor regions were identified from whole-slide pathology images via weakly supervised clustering, and pathological features were extracted using attention-based multiple instance learning. Concurrently, 2.5D tumor subregional features were derived from multiparametric MRI sequences. These multimodal features were deeply fused using a Transformer encoder. The model was developed and validated on a multicenter cohort (504 patients), and its biological basis was explored through transcriptomic analysis, gene set enrichment analysis, protein-protein interaction networks, and immune deconvolution.  Results: The fusion model achieved AUCs of 0.910, 0.861, and 0.833 in the training, internal validation, and external validation cohorts, respectively. Transcriptomic analysis implicated DNA damage repair processes in high-benefit patients, suggesting that enhanced DNA repair capacity may contribute to TMZ sensitivity. Immune deconvolution showed higher M1 macrophage infiltration and lower regulatory T cell abundance in the high-benefit group, consistent with a less immunosuppressive tumor microenvironment. Importantly, low-benefit patients who completed TMZ chemotherapy had shorter survival than those treated with concurrent chemoradiotherapy alone or surgery alone.  Conclusion: This model identifies patients unlikely to benefit from standard TMZ chemotherapy, providing a tool for postoperative personalized treatment stratification and optimization of therapeutic strategies in HGGs.
SN  - 1664-3224
ER  -