Clinical Risk Predication for Hepatocellular Carcinoma Based on Swin Transformer

Le résumé fourni par la source

Hepatocellular Carcinoma (HCC), a common malignancy, remains a major health challenge worldwide. In order to accurately assess the severity of HCC patients and guide treatment choices, the BCLC (Barcelona Clinic Liver Cancer) staging system has become an important classification tool. However, traditional BCLC staging mainly relies on physicians’ subjective judgement and imaging characterisation, which may be subjective and inconsistent. This study categorizes the very early, early, and intermediate stages in the traditional BCLC staging system as low-risk categories, while classifying the advanced and end-stage stages as high-risk categories. On this basis, we propose a classification model based on the combination of Swin Transformer model and gradient penalty, where Swin Transformer can effectively extract the features of CT images, and gradient penalty can effectively prevent overfitting and improve the generalisation ability of the model. To evaluate our model, we conducted rigorous experiments on a public dataset. The experimental results show that our proposed model achieves superior performance in the HCC staging task compared to other classification models. In summary, the Swin Transformer-based classification model proposed in this paper provides a new and reliable way to assess the condition and treatment selection of HCC patients, which can provide decision support for physicians.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.