Tackling Tumor Heterogeneity Issue: Transformer-Based Multiple Instance Enhancement Learning for Predicting EGFR Mutation via CT Images
- 12 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (11) , 4524-4535
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (62371435, 61971393, 61871361)
- Anhui Provincial Natural Science Foundation (2308085MF191)
This publication has 45 references indexed in Scilit:
- Multi-instance learning based on spatial continuous category representation for case-level meningioma grading in MRI imagesApplied Intelligence, 2022
- SETMIL: Spatial Encoding Transformer-Based Multiple Instance Learning for Pathological Image Analysis2022
- RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment2022
- Predicting EGFR mutation status by a deep learning approach in patients with non-small cell lung cancer brain metastasesJournal of Neuro-Oncology, 2022
- Accounting for Dependencies in Deep Learning Based Multiple Instance Learning for Whole Slide Imaging2021
- UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation2021
- Multiple Instance Learning with Center Embeddings for Histopathology Classification2020
- Toward automatic prediction of EGFR mutation status in pulmonary adenocarcinoma with 3D deep learningCancer Medicine, 2019
- Layer-Wise Weight Decay for Deep Neural Networks2018
- The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information RepositoryJournal of Digital Imaging, 2013