Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma
Objectives: Combination therapy of lenvatinib and immune checkpoint inhibitors (CLICI) has emerged as a promising approach for managing unresectable hepatocellular carcinoma (HCC). However, the response to such treatment is observed in only a subset of patients, underscoring the pressing need for re...
| Main Authors: | , , , , , , , |
|---|---|
| 格式: | 文件 |
| 语言: | English |
| 出版: |
Elsevier
2024-12-01
|
| 丛编: | Computational and Structural Biotechnology Journal |
| 主题: | |
| 在线阅读: | http://www.sciencedirect.com/science/article/pii/S2001037024000849 |
| _version_ | 1826927738002341888 |
|---|---|
| author | Nan-Qing Liao Zhu-Jian Deng Wei Wei Jia-Hui Lu Min-Jun Li Liang Ma Qing-Feng Chen Jian-Hong Zhong |
| author_facet | Nan-Qing Liao Zhu-Jian Deng Wei Wei Jia-Hui Lu Min-Jun Li Liang Ma Qing-Feng Chen Jian-Hong Zhong |
| author_sort | Nan-Qing Liao |
| collection | DOAJ |
| description | Objectives: Combination therapy of lenvatinib and immune checkpoint inhibitors (CLICI) has emerged as a promising approach for managing unresectable hepatocellular carcinoma (HCC). However, the response to such treatment is observed in only a subset of patients, underscoring the pressing need for reliable methods to identify potential responders. Materials & methods: This was a retrospective analysis involving 120 patients with unresectable HCC. They were divided into training (n = 72) and validation (n = 48) cohorts. We developed an interpretable deep learning model using multiphase computed tomography (CT) images to predict whether patients will respond or not to CLICI treatment, based on the Response Evaluation Criteria in Solid Tumors, version 1.1 (RECIST v1.1). We evaluated the models' performance and analyzed the impact of each CT phase. Critical regions influencing predictions were identified and visualized through heatmaps. Results: The multiphase model outperformed the best biphase and uniphase models, achieving an area under the curve (AUC) of 0.802 (95% CI = 0.780–0.824). The portal phase images were found to significantly enhance the model's predictive accuracy. Heatmaps identified six critical features influencing treatment response, offering valuable insights to clinicians. Additionally, we have made this model accessible via a web server at http://uhccnet.com/ for ease of use. Conclusions: The integration of multiphase CT images with deep learning-generated heatmaps for predicting treatment response provides a robust and practical tool for guiding CLICI therapy in patients with unresectable HCC. |
| first_indexed | 2024-04-24T12:51:20Z |
| format | Article |
| id | doaj.art-a1d4002266be4dea83b65bf6574fb13d |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2025-02-17T15:37:54Z |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-a1d4002266be4dea83b65bf6574fb13d2024-12-19T10:53:20ZengElsevierComputational and Structural Biotechnology Journal2001-03702024-12-0124247257Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinomaNan-Qing Liao0Zhu-Jian Deng1Wei Wei2Jia-Hui Lu3Min-Jun Li4Liang Ma5Qing-Feng Chen6Jian-Hong Zhong7School of Medical, Guangxi University, Nanning, China; Hepatobiliary Surgery Department, Guangxi Medical University Cancer Hospital, Nanning, ChinaHepatobiliary Surgery Department, Guangxi Medical University Cancer Hospital, Nanning, ChinaRadiology Department, Guangxi Medical University Cancer Hospital, Nanning, ChinaSchool of Computer, Electronics and Information, Guangxi University, Nanning, ChinaHepatobiliary Surgery Department, Guangxi Medical University Cancer Hospital, Nanning, ChinaHepatobiliary Surgery Department, Guangxi Medical University Cancer Hospital, Nanning, ChinaSchool of Computer, Electronics and Information, Guangxi University, Nanning, China; Correspondence to: School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China.Hepatobiliary Surgery Department, Guangxi Medical University Cancer Hospital, Nanning, China; Correspondence to: Hepatobiliary Surgery Department, Guangxi Medical University Cancer Hospital, Nanning 530021, China.Objectives: Combination therapy of lenvatinib and immune checkpoint inhibitors (CLICI) has emerged as a promising approach for managing unresectable hepatocellular carcinoma (HCC). However, the response to such treatment is observed in only a subset of patients, underscoring the pressing need for reliable methods to identify potential responders. Materials & methods: This was a retrospective analysis involving 120 patients with unresectable HCC. They were divided into training (n = 72) and validation (n = 48) cohorts. We developed an interpretable deep learning model using multiphase computed tomography (CT) images to predict whether patients will respond or not to CLICI treatment, based on the Response Evaluation Criteria in Solid Tumors, version 1.1 (RECIST v1.1). We evaluated the models' performance and analyzed the impact of each CT phase. Critical regions influencing predictions were identified and visualized through heatmaps. Results: The multiphase model outperformed the best biphase and uniphase models, achieving an area under the curve (AUC) of 0.802 (95% CI = 0.780–0.824). The portal phase images were found to significantly enhance the model's predictive accuracy. Heatmaps identified six critical features influencing treatment response, offering valuable insights to clinicians. Additionally, we have made this model accessible via a web server at http://uhccnet.com/ for ease of use. Conclusions: The integration of multiphase CT images with deep learning-generated heatmaps for predicting treatment response provides a robust and practical tool for guiding CLICI therapy in patients with unresectable HCC.http://www.sciencedirect.com/science/article/pii/S2001037024000849Deep learningHepatocellular carcinomaImmune checkpoint inhibitorsLenvatinibMultiphase computerized tomography |
| spellingShingle | Nan-Qing Liao Zhu-Jian Deng Wei Wei Jia-Hui Lu Min-Jun Li Liang Ma Qing-Feng Chen Jian-Hong Zhong Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma Computational and Structural Biotechnology Journal Deep learning Hepatocellular carcinoma Immune checkpoint inhibitors Lenvatinib Multiphase computerized tomography |
| title | Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma |
| title_full | Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma |
| title_fullStr | Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma |
| title_full_unstemmed | Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma |
| title_short | Deep learning of pretreatment multiphase CT images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma |
| title_sort | deep learning of pretreatment multiphase ct images for predicting response to lenvatinib and immune checkpoint inhibitors in unresectable hepatocellular carcinoma |
| topic | Deep learning Hepatocellular carcinoma Immune checkpoint inhibitors Lenvatinib Multiphase computerized tomography |
| url | http://www.sciencedirect.com/science/article/pii/S2001037024000849 |
| work_keys_str_mv | AT nanqingliao deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma AT zhujiandeng deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma AT weiwei deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma AT jiahuilu deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma AT minjunli deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma AT liangma deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma AT qingfengchen deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma AT jianhongzhong deeplearningofpretreatmentmultiphasectimagesforpredictingresponsetolenvatinibandimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma |