EUVIMEDEUVIMED entdecken
Crossref

Tackling Tumor Heterogeneity Issue: Transformer-Based Multiple Instance Enhancement Learning for Predicting EGFR Mutation via CT Images

Yulin Fang, Minghui Wang, Qilong Song, Chi Cao, Ziyu Gao, Biao Song, Xuhong Min, Ao Li

IEEE Transactions on Medical Imaging · 2025-11 · 44 (11) · 4524-4535

DOI: 10.1109/tmi.2025.3578995 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-11. Verfasst von Yulin Fang und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Mutation, Lung Neoplasms, Carcinoma, Non-Small-Cell Lung, Tomography, X-Ray Computed. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Anhui Provincial Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and non-invasive prediction of epidermal growth factor receptor (EGFR) mutation is crucial for the diagnosis and treatment of non-small cell lung cancer (NSCLC). While computed tomography (CT) imaging shows promise in identifying EGFR mutation, current prediction methods heavily rely on fully supervised learning, which overlooks the substantial heterogeneity of tumors and therefore leads to suboptimal results. To tackle tumor heterogeneity issue, this study introduces a novel weakly supervised method named TransMIEL, which leverages multiple instance learning techniques for accurate EGFR mutation prediction. Specifically, we first propose an innovative instance enhancement learning (IEL) strategy that strengthens the discriminative power of instance features for complex tumor CT images by exploring self-derived soft pseudo-labels. Next, to improve tumor representation capability, we design a spatial-aware transformer (SAT) that fully captures inter-instance relationships of different pathological subregions to mirror the diagnostic processes of radiologists. Finally, an instance adaptive gating (IAG) module is developed to effectively emphasize the contribution of informative instance features in heterogeneous tumors, facilitating dynamic instance feature aggregation and increasing model generalization performance. Experimental results demonstrate that TransMIEL significantly outperforms existing fully and weakly supervised methods on both public and in-house NSCLC datasets. Additionally, visualization results show that our approach can highlight intra-tumor and peri-tumor areas relevant to EGFR mutation status. Therefore, our method holds significant potential as an effective tool for EGFR prediction and offers a novel perspective for future research on tumor heterogeneity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MutationLung NeoplasmsCarcinoma, Non-Small-Cell LungTomography, X-Ray ComputedRadiographic Image Interpretation, Computer-AssistedHumansErbB Receptors

Substanzen

ErbB ReceptorsEGFR protein, human

Förderung

  • National Natural Science Foundation of China
  • Anhui Provincial Natural Science Foundation

Zitieren

APA

Fang, Y., Wang, M., Song, Q., Cao, C., Gao, Z., Song, B., Min, X., & Li, A. (2025). Tackling Tumor Heterogeneity Issue: Transformer-Based Multiple Instance Enhancement Learning for Predicting EGFR Mutation via CT Images. IEEE Transactions on Medical Imaging, 44(11), 4524-4535. https://doi.org/10.1109/tmi.2025.3578995

Vancouver

Fang Y, Wang M, Song Q, Cao C, Gao Z, Song B, et al. Tackling Tumor Heterogeneity Issue: Transformer-Based Multiple Instance Enhancement Learning for Predicting EGFR Mutation via CT Images. IEEE Transactions on Medical Imaging. 2025;44(11):4524-4535. doi:10.1109/tmi.2025.3578995

BibTeX
@article{Fang2025,
  author = {Fang, Yulin and Wang, Minghui and Song, Qilong and Cao, Chi and Gao, Ziyu and Song, Biao and Min, Xuhong and Li, Ao},
  title = {Tackling Tumor Heterogeneity Issue: Transformer-Based Multiple Instance Enhancement Learning for Predicting EGFR Mutation via CT Images},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  volume = {44},
  number = {11},
  pages = {4524--4535},
  doi = {10.1109/tmi.2025.3578995}
}
Kostenlos starten →