A multi-task dual-stream attention network for the identification of KRAS mutation in colorectal cancer.

Researchers

Journal

Modalities

Models

Abstract

It is of great significance to accurately identify the KRAS gene mutation status for patients in tumor prognosis and personalized treatment. Although the computer-aided diagnosis system based on deep learning has gotten all-round development, its performance still cannot meet the current clinical application requirements due to the inherent limitations of small-scale medical image dataset and inaccurate lesion feature extraction. Therefore, our aim is to propose a deep learning model based on T2 MRI of colorectal cancer patients to identify whether KRAS gene is mutated.In this research, a multi-task attentive model is proposed to identify KRAS gene mutations in patients, which is mainly composed of a segmentation sub-network and an identification sub-network. Specifically, at first, the features extracted by the encoder of segmentation model are used as guidance information to guide the two attention modules in the identification network for precise activation of the lesion area. Then the original image of the lesion and the segmentation result are concatenated for feature extraction. Finally, features extracted from the second step are combined with features activated by the attention modules to identify the gene mutation status. In this process, we introduce the inter-layer loss function to encourage the similarity of the two sub-network parameters and ensure that the key features are fully extracted to alleviate the overfitting problem caused by small dataset to some extent.The proposed identification model is benchmarked primarily using 15-fold cross validation. 382 images from 36 clinical cases were used to test the model. For the identification of KRAS mutation status, the average accuracy is 89.95±1.23%, the average sensitivity is 89.29±1.79%, the average specificity is 90.53±2.45%, and the average AUC is 95.73±5.02%. For segmentation of lesions, the average dice is 88.11 ± 0.86% CONCLUSIONS: We developed a novel deep learning-based model to identify the KRAS status in colorectal cancer. We demonstrated the excellent properties of the proposed identification through comparison with ground truth gene mutation status of 36 clinical cases. And all these results show that the novel method has great potential for clinical application. This article is protected by copyright. All rights reserved.This article is protected by copyright. All rights reserved.