Deep Learning Model-Based Architectures for Lung Tumor Mutation Profiling: A Systematic Review

TL;DR

This paper reviews how deep learning models can predict genetic mutations in lung tumors using histopathology images, aiming to improve cancer diagnosis and treatment.

Contribution

A systematic review of deep learning architectures for lung tumor mutation profiling using histopathology data, highlighting performance and challenges.

Findings

Sixteen studies used deep learning to predict NSCLC mutations like EGFR, KRAS, and TP53 from histopathology images.

Model performance varied, with AUCs ranging from 0.65 to 0.95, indicating potential but inconsistent accuracy.

Challenges include limited data, lack of standardization, and poor external validation affecting reproducibility.

Abstract

Lung cancer is a leading cause of cancer-related deaths worldwide, and understanding the genetic mutations that drive tumor growth is crucial for improving diagnosis and treatment. This study systematically reviews recent research using deep learning approaches to analyze lung tumor mutations, particularly in non-small-cell lung cancer. We summarize the architectures, data sources, and performance outcomes of various models, highlighting their potential for accurate and automated mutation profiling. The review also discusses current challenges, such as limited data and model interpretability, and identifies promising directions for future research. Our findings aim to guide scientists and clinicians in adopting deep learning techniques for more precise and efficient lung cancer genomics.

Background/Objectives: Lung cancer (NSCLC), which accounts for approximately 85% of lung cancers, exhibits marked heterogeneity that complicates molecular characterization and treatment selection. Recent advances in deep learning (DL) have enabled the extraction of genomic-related morphological features directly from routine Hematoxylin and Eosin (H&E) histopathology, offering a potential complement to Next-Generation Sequencing (NGS) for precision oncology. This review aimed to evaluate how DL models have been applied to predict molecular alterations in NSCLC using H&E-stained slides. Methods: A systematic search following PRISMA 2020 guidelines was conducted across PubMed, Scopus, and Web of Science to identify studies published up to March 2025 that used DL models for mutation prediction in NSCLC. Eligible studies were screened, and data on model architectures, datasets, and performance metrics were extracted. Results: Sixteen studies met inclusion criteria. Most employed convolutional neural networks trained on publicly available datasets such as The Cancer Genome Atlas (TCGA) to infer key mutations including EGFR, KRAS, and TP53. Reported areas under the curve ranged from 0.65 to 0.95, demonstrating variable but promising predictive capability. Conclusions: DL-based histopathology shows strong potential for linking tissue morphology to molecular signatures in NSCLC. However, methodological heterogeneity, small sample sizes, and limited external validation constrain reproducibility and generalizability. Standardized protocols, larger multicenter cohorts, and transparent validation are needed before these models can be translated into clinical practice.

Figures