Answers are grounded in this paper and cite their sources.
KRAS is a pathogenic gene frequently implicated in non-small cell lung cancer (NSCLC). However, biopsy as a diagnostic method has practical limitations. Therefore, it is important to accurately determine the mutation status of the KRAS gene non-invasively by combining NSCLC CT images and genetic data for early diagnosis and subsequent targeted therapy of patients. This paper proposes a Semi-supervised Multimodal Multiscale Attention Model (S 2 MMAM). S 2 MMAM comprises a Supervised Multilevel Fusion Segmentation Network (SMF-SN) and a Semi-supervised Multimodal Fusion Classification Network (S 2 MF-CN). S 2 MMAM facilitates the execution of the classification task by transferring the useful information captured in SMF-SN to the S 2 MF-CN to improve the model prediction accuracy. In SMF-SN, we propose a Triple Attention-guided Feature Aggregation module for obtaining segmentation features that incorporate high-level semantic abstract features and low-level semantic detail features. Segmentation features provide pre-guidance and key information expansion for S 2 MF-CN. S 2 MF-CN shares the encoder and decoder parameters of SMF-SN, which enables S 2 MF-CN to obtain rich classification features. S 2 MF-CN uses the proposed Intra and Inter Mutual Guidance Attention Fusion (I 2 MGAF) module to first guide segmentation and classification feature fusion to extract hidden multi-scale contextual information. I 2 MGAF then guides the multidimensional fusion of genetic data and CT image data to compensate for the lack of information in single modality data. S 2 MMAM achieved 83.27% AUC and 81.67% accuracy in predicting KRAS gene mutation status in NSCLC. This method uses medical image CT and genetic data to effectively improve the accuracy of predicting KRAS gene mutation status in NSCLC.
No takes yet. Share an insight, caveat, or question.
Xue et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: