Jialin Chen, Juan Chen, Yamei Ye, Linbin Lu, Xinying Guo, Simiao Gao, Lifang Liu, Hongyi Yang, Chun Lin, Xiong Chen
{"title":"预处理多序列对比增强MRI预测不可切除肝细胞癌使用变压器免疫治疗的反应:一项多中心研究。","authors":"Jialin Chen, Juan Chen, Yamei Ye, Linbin Lu, Xinying Guo, Simiao Gao, Lifang Liu, Hongyi Yang, Chun Lin, Xiong Chen","doi":"10.7150/jca.111026","DOIUrl":null,"url":null,"abstract":"<p><p><b><i>Background:</i></b> Targeted combined immunotherapy (TCI) has shown certain antitumor effects in patients with unresectable hepatocellular carcinoma(uHCC), but only a subset of patients benefit. This study aims to develop a Transformer-based radiomics model to predict the objective response to combined therapy in patients with uHCC. <b><i>Methods:</i></b> This multicenter, retrospective study involved 264 HCC patients who underwent contrast-enhanced MRI prior to immunotherapy. The patients were divided into a training cohort(n=180) and a validation cohort(n=84). Using a multi-instance learning approach, tumor lesions in multi-sequence MRI were segmented into cross-sectional images, and features were extracted using the ResNet50 model. The Transformer model was then trained to predict the objective response rate (ORR). The prediction process was visualized using Grad-CAM and SHAP algorithms. Model performance was assessed using ROC and DCA curves, while survival analysis was conducted using Kaplan-Meier curves. <b><i>Results:</i></b> Among 264 patients, one achieved complete response (0.4%), 64 experienced partial response (24.2%). The ORR was 26.1% in the training group and 21.4% in the validation group. The model demonstrated high predictive accuracy, achieving a perfect area under the curve (AUC) of 1.000. Further validation using screenshot-based model inputs revealed an AUC of 0.929 (95% CI: 0.904, 0.947), confirming the model's clinical applicability. Kaplan-Meier analysis indicated that objective responders experienced better overall survival (OS) in both the training set (HR: 0.50, 95% CI: 0.27, 0.90) and the validation set (HR: 0.28, 95% CI: 0.08, 0.91). <b><i>Conclusion:</i></b> The deep learning framework combining ResNet50 and Transformer has proven its clinical applicability in predicting and assessing the efficacy of targeted combination immunotherapy in unresectable hepatocellular carcinoma, providing crucial guidance for clinical treatment decisions.</p>","PeriodicalId":15183,"journal":{"name":"Journal of Cancer","volume":"16 8","pages":"2663-2672"},"PeriodicalIF":3.3000,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12170994/pdf/","citationCount":"0","resultStr":"{\"title\":\"Pretreatment Multi-sequence Contrast-Enhanced MRI to Predict Response to Immunotherapy in Unresectable Hepatocellular Carcinoma Using Transformer: A Multicenter Study.\",\"authors\":\"Jialin Chen, Juan Chen, Yamei Ye, Linbin Lu, Xinying Guo, Simiao Gao, Lifang Liu, Hongyi Yang, Chun Lin, Xiong Chen\",\"doi\":\"10.7150/jca.111026\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><b><i>Background:</i></b> Targeted combined immunotherapy (TCI) has shown certain antitumor effects in patients with unresectable hepatocellular carcinoma(uHCC), but only a subset of patients benefit. This study aims to develop a Transformer-based radiomics model to predict the objective response to combined therapy in patients with uHCC. <b><i>Methods:</i></b> This multicenter, retrospective study involved 264 HCC patients who underwent contrast-enhanced MRI prior to immunotherapy. The patients were divided into a training cohort(n=180) and a validation cohort(n=84). Using a multi-instance learning approach, tumor lesions in multi-sequence MRI were segmented into cross-sectional images, and features were extracted using the ResNet50 model. The Transformer model was then trained to predict the objective response rate (ORR). The prediction process was visualized using Grad-CAM and SHAP algorithms. Model performance was assessed using ROC and DCA curves, while survival analysis was conducted using Kaplan-Meier curves. <b><i>Results:</i></b> Among 264 patients, one achieved complete response (0.4%), 64 experienced partial response (24.2%). The ORR was 26.1% in the training group and 21.4% in the validation group. The model demonstrated high predictive accuracy, achieving a perfect area under the curve (AUC) of 1.000. Further validation using screenshot-based model inputs revealed an AUC of 0.929 (95% CI: 0.904, 0.947), confirming the model's clinical applicability. Kaplan-Meier analysis indicated that objective responders experienced better overall survival (OS) in both the training set (HR: 0.50, 95% CI: 0.27, 0.90) and the validation set (HR: 0.28, 95% CI: 0.08, 0.91). <b><i>Conclusion:</i></b> The deep learning framework combining ResNet50 and Transformer has proven its clinical applicability in predicting and assessing the efficacy of targeted combination immunotherapy in unresectable hepatocellular carcinoma, providing crucial guidance for clinical treatment decisions.</p>\",\"PeriodicalId\":15183,\"journal\":{\"name\":\"Journal of Cancer\",\"volume\":\"16 8\",\"pages\":\"2663-2672\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2025-06-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12170994/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Cancer\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.7150/jca.111026\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cancer","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.7150/jca.111026","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
Pretreatment Multi-sequence Contrast-Enhanced MRI to Predict Response to Immunotherapy in Unresectable Hepatocellular Carcinoma Using Transformer: A Multicenter Study.
Background: Targeted combined immunotherapy (TCI) has shown certain antitumor effects in patients with unresectable hepatocellular carcinoma(uHCC), but only a subset of patients benefit. This study aims to develop a Transformer-based radiomics model to predict the objective response to combined therapy in patients with uHCC. Methods: This multicenter, retrospective study involved 264 HCC patients who underwent contrast-enhanced MRI prior to immunotherapy. The patients were divided into a training cohort(n=180) and a validation cohort(n=84). Using a multi-instance learning approach, tumor lesions in multi-sequence MRI were segmented into cross-sectional images, and features were extracted using the ResNet50 model. The Transformer model was then trained to predict the objective response rate (ORR). The prediction process was visualized using Grad-CAM and SHAP algorithms. Model performance was assessed using ROC and DCA curves, while survival analysis was conducted using Kaplan-Meier curves. Results: Among 264 patients, one achieved complete response (0.4%), 64 experienced partial response (24.2%). The ORR was 26.1% in the training group and 21.4% in the validation group. The model demonstrated high predictive accuracy, achieving a perfect area under the curve (AUC) of 1.000. Further validation using screenshot-based model inputs revealed an AUC of 0.929 (95% CI: 0.904, 0.947), confirming the model's clinical applicability. Kaplan-Meier analysis indicated that objective responders experienced better overall survival (OS) in both the training set (HR: 0.50, 95% CI: 0.27, 0.90) and the validation set (HR: 0.28, 95% CI: 0.08, 0.91). Conclusion: The deep learning framework combining ResNet50 and Transformer has proven its clinical applicability in predicting and assessing the efficacy of targeted combination immunotherapy in unresectable hepatocellular carcinoma, providing crucial guidance for clinical treatment decisions.
期刊介绍:
Journal of Cancer is an open access, peer-reviewed journal with broad scope covering all areas of cancer research, especially novel concepts, new methods, new regimens, new therapeutic agents, and alternative approaches for early detection and intervention of cancer. The Journal is supported by an international editorial board consisting of a distinguished team of cancer researchers. Journal of Cancer aims at rapid publication of high quality results in cancer research while maintaining rigorous peer-review process.