PlumX Metrics
Embed PlumX Metrics

A novel transformer-based aggregation model for predicting gene mutations in lung adenocarcinoma

Medical and Biological Engineering and Computing, ISSN: 1741-0444, Vol: 62, Issue: 5, Page: 1427-1440
2024
  • 2
    Citations
  • 0
    Usage
  • 5
    Captures
  • 0
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

Article Description

Abstract: In recent years, predicting gene mutations on whole slide imaging (WSI) has gained prominence. The primary challenge is extracting global information and achieving unbiased semantic aggregation. To address this challenge, we propose a novel Transformer-based aggregation model, employing a self-learning weight aggregation mechanism to mitigate semantic bias caused by the abundance of features in WSI. Additionally, we adopt a random patch training method, which enhances model learning richness by randomly extracting feature vectors from WSI, thus addressing the issue of limited data. To demonstrate the model’s effectiveness in predicting gene mutations, we leverage the lung adenocarcinoma dataset from Shandong Provincial Hospital for prior knowledge learning. Subsequently, we assess TP53, CSMD3, LRP1B, and TTN gene mutations using lung adenocarcinoma tissue pathology images and clinical data from The Cancer Genome Atlas (TCGA). The results indicate a notable increase in the AUC (Area Under the ROC Curve) value, averaging 4%, attesting to the model’s performance improvement. Our research offers an efficient model to explore the correlation between pathological image features and molecular characteristics in lung adenocarcinoma patients. This model introduces a novel approach to clinical genetic testing, expected to enhance the efficiency of identifying molecular features and genetic testing in lung adenocarcinoma patients, ultimately providing more accurate and reliable results for related studies. Graphical abstract: Novel aggregation model based on transformer. The WSI selects tumor patches via the tumor classification model and then inputs them into the Swin Transformer backbone network to extract tumor vectors. The extracted vectors are trained using the random patch training method, and then processed through a transformer encoder and weighted pooling layer to converge into a feature vector that represents global information. The predicted results are then outputted. (Figure presented.).

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know