Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated 28 min ago
Peer-reviewedCC BY 4.0Frontiers in Neurology

Explainable volumetric deep learning from contrast-enhanced T1-weighted MRI for preoperative IDH prediction in adult-type diffuse gliomas: a two-center study

  • Chenghong Zheng1
  • Qijie Zhang1
  • Deqiang Li1,2
  • Hongyu Wang1
  • Jinlin Yang1,3
  • Fajin Lv1
  • Tianyou Luo1
  • Huiyue Chen1
  • Weidong Fang1
  1. 1Department of Radiology, The First Affiliated Hospital of Chongqing Medical University
  2. 2Department of Radiology, The First Affiliated Hospital of Army Medical University (Southwest Hospital)
  3. 3Department of Radiology, University-Town Hospital of Chongqing Medical University
Open at sourceDOICite

Abstract

Objective: To evaluate contrast-enhanced T1-weighted MRI (CE-T1WI) models for preoperative prediction of isocitrate dehydrogenase (IDH) mutation status in adult-type diffuse gliomas and explore phenotype associations of influential latent features.

Methods: This retrospective study included 462 patients. Center 1 provided training ( n = 259) and internal-test ( n = 65) cohorts, and Center 2 provided external validation ( n = 138). Five input–architecture combinations and six classifiers were evaluated against an interpretable logistic benchmark combining age and Visually Accessible Rembrandt Images (VASARI) descriptors. For each architecture, the classifier with the highest observed external area under the curve (AUC) was selected for reporting. Performance was assessed using discrimination, calibration, decision curves, and 100 downstream refits with fixed deep features. Shapley additive explanations (SHAP) and phenotype association analyses examined influential latent features and their relationships with clinical and imaging phenotypes.

Results: Region-of-interest (ROI)-constrained three-dimensional vision Transformer (3D ViT) with a support vector machine (SVM) achieved an external AUC of 0.929 (95% CI, 0.885–0.973), accuracy of 0.848, sensitivity of 0.838, specificity of 0.857, and Brier score of 0.106. The age–VASARI benchmark achieved an external AUC of 0.782. Across downstream refits, the ROI-constrained model had a mean external AUC of 0.930 and the smallest mean training-minus-external AUC difference (0.019). The same 10 features formed the highest-importance SHAP set across cohorts, with different rank orders. Feature_546 correlated with age ( r = 0.461), postoperative Ki-67 ( r = 0.562), and enhancement quality ( r = 0.678; all adjusted p < 0.001).

Conclusion: ROI-constrained volumetric learning from CE-T1WI showed promising cross-center IDH discrimination using one routine MRI sequence. Influential latent features were associated with postoperative Ki-67 and recognizable imaging phenotypes. SHAP attribution and these exploratory associations provide complementary perspectives on model behavior in preoperative IDH assessment.

Related

  1. Explainable machine learning for preoperative prediction of acute kidney injury after intertrochanteric fracture surgery in older adults
    Weizhang Lin, Ximing Lin, Hongpeng Gao
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Interpretable machine learning for preoperative prediction of WHO/ISUP grade in clear cell renal cell carcinoma using contrast-enhanced CT–derived extracellular volume fraction
    Yating Wang, Ying Wang, Genji Bai +3
    Frontiers in OncologyPeer-reviewedCC BY 4.0Full textMedical imaging & radiologyCrossrefPMC
  3. Prediction of gross extrathyroidal extension in papillary thyroid carcinoma using a deep learning radiomics model based on post-processing techniques for multi-phase contrast-enhanced MRI images
    Yun Zeng, Xinyi Li, Lang Tang +3
    Frontiers in endocrinologyPeer-reviewedCC BYFull textEndocrinology & metabolismEurope PMC
  4. Development and validation of machine learning models for preoperative prediction of perioperative outcomes in patients with thymic epithelial tumors
    Yehong Li, Jianhao Qiu, Yue Zhao +3
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textNeurologyCrossref
  5. Development and validation of a machine learning model for preoperative prediction of intraoperative hypothermia in gynecological laparoscopic surgery: a two-center cohort study
    Chunping Li, Bo Liu, Jianping Zhang +2
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{zheng2026explainable,
  title = {{Explainable volumetric deep learning from contrast-enhanced T1-weighted MRI for preoperative IDH prediction in adult-type diffuse gliomas: a two-center study}},
  author = {Chenghong Zheng and Qijie Zhang and Deqiang Li and Hongyu Wang and Jinlin Yang and Fajin Lv and Tianyou Luo and Huiyue Chen and Weidong Fang},
  journal = {Frontiers in Neurology},
  year = {2026},
  month = nov,
  doi = {10.3389/fneur.2026.1966591},
  url = {https://www.frontiersin.org/articles/10.3389/fneur.2026.1966591/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Explainable volumetric deep learning from contrast-enhanced T1-weighted MRI for preoperative IDH prediction in adult-type diffuse gliomas: a two-center study
AU  - Chenghong Zheng
AU  - Qijie Zhang
AU  - Deqiang Li
AU  - Hongyu Wang
AU  - Jinlin Yang
AU  - Fajin Lv
AU  - Tianyou Luo
AU  - Huiyue Chen
AU  - Weidong Fang
PY  - 2026
DA  - 2026/11/04
JO  - Frontiers in Neurology
DO  - 10.3389/fneur.2026.1966591
UR  - https://www.frontiersin.org/articles/10.3389/fneur.2026.1966591/full
AB  - Objective: To evaluate contrast-enhanced T1-weighted MRI (CE-T1WI) models for preoperative prediction of isocitrate dehydrogenase (IDH) mutation status in adult-type diffuse gliomas and explore phenotype associations of influential latent features.  Methods: This retrospective study included 462 patients. Center 1 provided training ( n = 259) and internal-test ( n = 65) cohorts, and Center 2 provided external validation ( n = 138). Five input–architecture combinations and six classifiers were evaluated against an interpretable logistic benchmark combining age and Visually Accessible Rembrandt Images (VASARI) descriptors. For each architecture, the classifier with the highest observed external area under the curve (AUC) was selected for reporting. Performance was assessed using discrimination, calibration, decision curves, and 100 downstream refits with fixed deep features. Shapley additive explanations (SHAP) and phenotype association analyses examined influential latent features and their relationships with clinical and imaging phenotypes.  Results: Region-of-interest (ROI)-constrained three-dimensional vision Transformer (3D ViT) with a support vector machine (SVM) achieved an external AUC of 0.929 (95% CI, 0.885–0.973), accuracy of 0.848, sensitivity of 0.838, specificity of 0.857, and Brier score of 0.106. The age–VASARI benchmark achieved an external AUC of 0.782. Across downstream refits, the ROI-constrained model had a mean external AUC of 0.930 and the smallest mean training-minus-external AUC difference (0.019). The same 10 features formed the highest-importance SHAP set across cohorts, with different rank orders. Feature_546 correlated with age ( r = 0.461), postoperative Ki-67 ( r = 0.562), and enhancement quality ( r = 0.678; all adjusted p < 0.001).  Conclusion: ROI-constrained volumetric learning from CE-T1WI showed promising cross-center IDH discrimination using one routine MRI sequence. Influential latent features were associated with postoperative Ki-67 and recognizable imaging phenotypes. SHAP attribution and these exploratory associations provide complementary perspectives on model behavior in preoperative IDH assessment.
SN  - 1664-2295
ER  -