EUVIMEDAtklāt EUVIMED
Crossref

A deep‐learning model for predicting tyrosine kinase inhibitor response from histology in gastrointestinal stromal tumor

Xue Kong iD, Jun Shi, Dongdong Sun, Lanqing Cheng, Can Wu, Zhiguo Jiang, Yushan Zheng, Wei Wang, Haibo Wu

The Journal of Pathology · 2025

DOI: 10.1002/path.6399 ↗

At a glance

Journal article in The Journal of Pathology, 2025. Written by Xue Kong and 8 co-authors. Institution: Department of Pathology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of PR Ch…. Major MEDLINE topics: Gastrointestinal Stromal Tumors, Protein Kinase Inhibitors, Deep Learning, Imatinib Mesylate. Cited 6 times so far (Crossref); 35 references. Funded by: Scientific Research Project of Anhui Provincial Education Department, Joint Fund for Medical Artificial Intelligence, Natural Science Foundation of Anhui Province.

AbstraktsSubjectsBibliogrāfiskie datiCiteRelated studies

Abstract (original language)

Over 90% of gastrointestinal stromal tumors (GISTs) harbor mutations in KIT or PDGFRA that can predict response to tyrosine kinase inhibitor (TKI) therapies, as recommended by NCCN (National Comprehensive Cancer Network) guidelines. However, gene sequencing for mutation testing is expensive and time‐consuming and is susceptible to a variety of preanalytical factors. To overcome the challenges associated with genetic screening by sequencing, in the current study we developed an artificial intelligence‐based deep‐learning (DL) model that uses convolutional neural networks (CNN) to analyze digitized hematoxylin and eosin staining in tumor histological sections to predict potential response to imatinib or avapritinib treatment in GIST patients. Assessment with an independent testing set showed that our DL model could predict imatinib sensitivity with an area under the curve (AUC) of 0.902 in case‐wise analysis and 0.807 in slide‐wise analysis. Case‐level AUCs for predicting imatinib‐dose‐adjustment cases, avapritinib‐sensitive cases, and wildtype GISTs were 0.920, 0.958, and 0.776, respectively, while slide‐level AUCs for these respective groups were 0.714, 0.922, and 0.886, respectively. Our model showed comparable or better prediction of actual response to TKI than sequencing‐based screening (accuracy 0.9286 versus 0.8929; DL model versus sequencing), while predictions of nonresponse to imatinib/avapritinib showed markedly higher accuracy than sequencing (0.7143 versus 0.4286). These results demonstrate the potential of a DL model to improve predictions of treatment response to TKI therapy from histology in GIST patients. © 2025 The Pathological Society of Great Britain and Ireland.

Subjects

MeSH terms (MEDLINE)

Gastrointestinal Stromal TumorsProtein Kinase InhibitorsDeep LearningImatinib MesylateGastrointestinal NeoplasmsHumansFemaleMaleMutationMiddle AgedAgedTreatment OutcomePyrazolesProto-Oncogene Proteins c-kitReceptor, Platelet-Derived Growth Factor alphaTyrosine Kinase InhibitorsPyrrolesTriazinesAvapritinib

Author keywords

GISTKITPDGFRAavapritinibdeep learningimatinib

Substances

Protein Kinase InhibitorsImatinib MesylatePyrazolesProto-Oncogene Proteins c-kitReceptor, Platelet-Derived Growth Factor alphaTyrosine Kinase InhibitorsPyrrolesTriazinesAvapritinib

Authors and institutions

  • Department of Pathology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of PR China, Hefei, PR China.
  • Intelligent Pathology Institute, Division of Life Sciences and Medicine, University of Science and Technology of PR China, Hefei, PR China.
  • School of Software, Hefei University of Technology, Hefei, PR China.
  • School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, PR China.
  • Image Processing Center, School of Astronautics, Beihang University, Beijing, PR China.
  • School of Engineering Medicine, Beijing Advanced Innovation Center on Biomedical Engineering, Beihang University, Beijing, PR China.

ORCID profiles: Xue Kong

Funding

  • Scientific Research Project of Anhui Provincial Education Department
  • Joint Fund for Medical Artificial Intelligence
  • Natural Science Foundation of Anhui Province
  • Anhui Provincial Health and Medical Research Project
  • National Natural Science Foundation of China

Cite

APA

Kong, X., Shi, J., Sun, D., Cheng, L., Wu, C., Jiang, Z., Zheng, Y., Wang, W., & Wu, H. (2025). A deep‐learning model for predicting tyrosine kinase inhibitor response from histology in gastrointestinal stromal tumor. The Journal of Pathology. https://doi.org/10.1002/path.6399

Vancouver

Kong X, Shi J, Sun D, Cheng L, Wu C, Jiang Z, et al. A deep‐learning model for predicting tyrosine kinase inhibitor response from histology in gastrointestinal stromal tumor. The Journal of Pathology. 2025. doi:10.1002/path.6399

BibTeX
@article{Kong2025,
  author = {Kong, Xue and Shi, Jun and Sun, Dongdong and Cheng, Lanqing and Wu, Can and Jiang, Zhiguo and Zheng, Yushan and Wang, Wei and Wu, Haibo},
  title = {A deep‐learning model for predicting tyrosine kinase inhibitor response from histology in gastrointestinal stromal tumor},
  journal = {The Journal of Pathology},
  year = {2025},
  doi = {10.1002/path.6399}
}
Start for free →