Abstract A048: Weakly supervised prediction of <i>EGFR</i> mutation status and early metastasis of lung adenocarcinoma whole slide histopathology images using artificial intelligence
Bibliographic record
Abstract
Abstract Lung cancer is the leading cause of cancer-related mortality worldwide. Adenocarcinoma is the most common histological subtype, followed by squamous cell carcinoma. Treatment of lung cancer depends on clinical stage and pathological types. Current guidelines for lung adenocarcinoma recommend testing for EGFR mutations, as patients with these mutations may respond to tyrosine kinase inhibitors. Screening for brain metastasis using magnetic resonance imaging (MRI) is also recommended in all patients with newly diagnosed lung adenocarcinoma. Digital pathology and artificial intelligence (AI) methods have shown promise benefits in analyzing histopathology images. In this study, we developed annotation-free, whole slide image AI algorithms to predict EGFR mutation status and early metastasis of lung adenocarcinoma. The algorithms were trained using a weakly supervised framework on digitalized pathology images. Results showed that the model differentiated adenocarcinoma and squamous cell carcinoma with AUC of 0.9634 and 0.9495, respectively, surpassing previous 4x magnification models. For predicting EGFR mutation status in lung adenocarcinoma, the model trained on 1,572 images achieved an AUC of 0.6824 in the same-site test set and 0.6563 in an independent cross-site set, showing varying performance across different histologic subtypes. Lastly, a weakly supervised algorithm was developed to predict distant metastasis within six months, achieving an AUC of 0.7460 in the test set and 0.7330 in an independent cross-site set. Our results demonstrate that AI can successfully predict EGFR mutation status and early metastasis of lung adenocarcinoma directly from histopathology images without additional annotations, which could enable more efficient diagnosis and treatment planning clinically. Our AI algorithms have the potential to improve patient outcomes by assisting pathologists in making critical diagnostic decisions for lung adenocarcinoma patients. Citation Format: Chi-Long Chen, Chi-Chung Chen, Tzu-Hao Chang, Ming-Shu Hsieh, Chao-Yuan Yeh, Cheng-Yu Chen. Weakly supervised prediction of EGFR mutation status and early metastasis of lung adenocarcinoma whole slide histopathology images using artificial intelligence [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A048.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".