Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models
Background<b>:</b> Currently, surgical decisions for hepatocellular carcinoma (HCC) resection are difficult and not sufficiently personalized. We aimed to develop and validate data driven prediction models to assist surgeons in selecting the optimal surgical procedure for patients. Metho...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/15/6/1784 |
| _version_ | 1797612979331530752 |
|---|---|
| author | Liyang Wang Danjun Song Wentao Wang Chengquan Li Yiming Zhou Jiaping Zheng Shengxiang Rao Xiaoying Wang Guoliang Shao Jiabin Cai Shizhong Yang Jiahong Dong |
| author_facet | Liyang Wang Danjun Song Wentao Wang Chengquan Li Yiming Zhou Jiaping Zheng Shengxiang Rao Xiaoying Wang Guoliang Shao Jiabin Cai Shizhong Yang Jiahong Dong |
| author_sort | Liyang Wang |
| collection | DOAJ |
| description | Background<b>:</b> Currently, surgical decisions for hepatocellular carcinoma (HCC) resection are difficult and not sufficiently personalized. We aimed to develop and validate data driven prediction models to assist surgeons in selecting the optimal surgical procedure for patients. Methods<b>:</b> Retrospective data from 361 HCC patients who underwent radical resection in two institutions were included. End-to-end deep learning models were built to automatically segment lesions from the arterial phase (AP) of preoperative dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). Clinical baseline characteristics and radiomic features were rigorously screened. The effectiveness of radiomic features and radiomic-clinical features was also compared. Three ensemble learning models were proposed to perform the surgical procedure decision and the overall survival (OS) and recurrence-free survival (RFS) predictions after taking different solutions, respectively. Results<b>:</b> SegFormer performed best in terms of automatic segmentation, achieving a Mean Intersection over Union (mIoU) of 0.8860. The five-fold cross-validation results showed that inputting radiomic-clinical features outperformed using only radiomic features. The proposed models all outperformed the other mainstream ensemble models. On the external test set, the area under the receiver operating characteristic curve (AUC) of the proposed decision model was 0.7731, and the performance of the prognostic prediction models was also relatively excellent. The application web server based on automatic lesion segmentation was deployed and is available online. Conclusions<b>:</b> In this study, we developed and externally validated the surgical decision-making procedures and prognostic prediction models for HCC for the first time, and the results demonstrated relatively accurate predictions and strong generalizations, which are expected to help clinicians optimize surgical procedures. |
| first_indexed | 2024-03-11T06:48:29Z |
| format | Article |
| id | doaj.art-432f87bce64d4f69b2712d8d12f0ea5a |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-11T06:48:29Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-432f87bce64d4f69b2712d8d12f0ea5a2023-11-17T10:07:09ZengMDPI AGCancers2072-66942023-03-01156178410.3390/cancers15061784Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning ModelsLiyang Wang0Danjun Song1Wentao Wang2Chengquan Li3Yiming Zhou4Jiaping Zheng5Shengxiang Rao6Xiaoying Wang7Guoliang Shao8Jiabin Cai9Shizhong Yang10Jiahong Dong11School of Clinical Medicine, Tsinghua University, Beijing 100084, ChinaDepartment of Interventional Therapy, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou 310022, ChinaDepartment of Radiology, Zhongshan Hospital, Fudan University, Shanghai 200032, ChinaSchool of Clinical Medicine, Tsinghua University, Beijing 100084, ChinaDepartment of Hepatobiliary and Pancreatic Surgery, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou 310022, ChinaDepartment of Interventional Therapy, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou 310022, ChinaDepartment of Radiology, Zhongshan Hospital, Fudan University, Shanghai 200032, ChinaDepartment of Liver Surgery, Key Laboratory of Carcinogenesis and Cancer Invasion of Ministry of Education, Liver Cancer Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, ChinaDepartment of Interventional Therapy, The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou 310022, ChinaDepartment of Liver Surgery, Key Laboratory of Carcinogenesis and Cancer Invasion of Ministry of Education, Liver Cancer Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, ChinaHepato-Pancreato-Biliary Center, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing 102218, ChinaSchool of Clinical Medicine, Tsinghua University, Beijing 100084, ChinaBackground<b>:</b> Currently, surgical decisions for hepatocellular carcinoma (HCC) resection are difficult and not sufficiently personalized. We aimed to develop and validate data driven prediction models to assist surgeons in selecting the optimal surgical procedure for patients. Methods<b>:</b> Retrospective data from 361 HCC patients who underwent radical resection in two institutions were included. End-to-end deep learning models were built to automatically segment lesions from the arterial phase (AP) of preoperative dynamic contrast enhanced magnetic resonance imaging (DCE-MRI). Clinical baseline characteristics and radiomic features were rigorously screened. The effectiveness of radiomic features and radiomic-clinical features was also compared. Three ensemble learning models were proposed to perform the surgical procedure decision and the overall survival (OS) and recurrence-free survival (RFS) predictions after taking different solutions, respectively. Results<b>:</b> SegFormer performed best in terms of automatic segmentation, achieving a Mean Intersection over Union (mIoU) of 0.8860. The five-fold cross-validation results showed that inputting radiomic-clinical features outperformed using only radiomic features. The proposed models all outperformed the other mainstream ensemble models. On the external test set, the area under the receiver operating characteristic curve (AUC) of the proposed decision model was 0.7731, and the performance of the prognostic prediction models was also relatively excellent. The application web server based on automatic lesion segmentation was deployed and is available online. Conclusions<b>:</b> In this study, we developed and externally validated the surgical decision-making procedures and prognostic prediction models for HCC for the first time, and the results demonstrated relatively accurate predictions and strong generalizations, which are expected to help clinicians optimize surgical procedures.https://www.mdpi.com/2072-6694/15/6/1784surgical proceduredecision-makingprognostic predictiondeep learningensemble learning |
| spellingShingle | Liyang Wang Danjun Song Wentao Wang Chengquan Li Yiming Zhou Jiaping Zheng Shengxiang Rao Xiaoying Wang Guoliang Shao Jiabin Cai Shizhong Yang Jiahong Dong Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models Cancers surgical procedure decision-making prognostic prediction deep learning ensemble learning |
| title | Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models |
| title_full | Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models |
| title_fullStr | Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models |
| title_full_unstemmed | Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models |
| title_short | Data-Driven Assisted Decision Making for Surgical Procedure of Hepatocellular Carcinoma Resection and Prognostic Prediction: Development and Validation of Machine Learning Models |
| title_sort | data driven assisted decision making for surgical procedure of hepatocellular carcinoma resection and prognostic prediction development and validation of machine learning models |
| topic | surgical procedure decision-making prognostic prediction deep learning ensemble learning |
| url | https://www.mdpi.com/2072-6694/15/6/1784 |
| work_keys_str_mv | AT liyangwang datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT danjunsong datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT wentaowang datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT chengquanli datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT yimingzhou datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT jiapingzheng datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT shengxiangrao datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT xiaoyingwang datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT guoliangshao datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT jiabincai datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT shizhongyang datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels AT jiahongdong datadrivenassisteddecisionmakingforsurgicalprocedureofhepatocellularcarcinomaresectionandprognosticpredictiondevelopmentandvalidationofmachinelearningmodels |