Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos
Abstract Background Transcatheter arterial chemoembolization (TACE) is the mainstay of therapy for intermediate-stage hepatocellular carcinoma (HCC); yet its efficacy varies between patients with the same tumor stage. Accurate prediction of TACE response remains a major concern to avoid overtreatmen...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-05-01
|
| Series: | Cancer Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40644-022-00457-3 |
| _version_ | 1811235433807347712 |
|---|---|
| author | Lu Zhang Yicheng Jiang Zhe Jin Wenting Jiang Bin Zhang Changmiao Wang Lingeng Wu Luyan Chen Qiuying Chen Shuyi Liu Jingjing You Xiaokai Mo Jing Liu Zhiyuan Xiong Tao Huang Liyang Yang Xiang Wan Ge Wen Xiao Guang Han Weijun Fan Shuixing Zhang |
| author_facet | Lu Zhang Yicheng Jiang Zhe Jin Wenting Jiang Bin Zhang Changmiao Wang Lingeng Wu Luyan Chen Qiuying Chen Shuyi Liu Jingjing You Xiaokai Mo Jing Liu Zhiyuan Xiong Tao Huang Liyang Yang Xiang Wan Ge Wen Xiao Guang Han Weijun Fan Shuixing Zhang |
| author_sort | Lu Zhang |
| collection | DOAJ |
| description | Abstract Background Transcatheter arterial chemoembolization (TACE) is the mainstay of therapy for intermediate-stage hepatocellular carcinoma (HCC); yet its efficacy varies between patients with the same tumor stage. Accurate prediction of TACE response remains a major concern to avoid overtreatment. Thus, we aimed to develop and validate an artificial intelligence system for real-time automatic prediction of TACE response in HCC patients based on digital subtraction angiography (DSA) videos via a deep learning approach. Methods This retrospective cohort study included a total of 605 patients with intermediate-stage HCC who received TACE as their initial therapy. A fully automated framework (i.e., DSA-Net) contained a U-net model for automatic tumor segmentation (Model 1) and a ResNet model for the prediction of treatment response to the first TACE (Model 2). The two models were trained in 360 patients, internally validated in 124 patients, and externally validated in 121 patients. Dice coefficient and receiver operating characteristic curves were used to evaluate the performance of Models 1 and 2, respectively. Results Model 1 yielded a Dice coefficient of 0.75 (95% confidence interval [CI]: 0.73–0.78) and 0.73 (95% CI: 0.71–0.75) for the internal validation and external validation cohorts, respectively. Integrating the DSA videos, segmentation results, and clinical variables (mainly demographics and liver function parameters), Model 2 predicted treatment response to first TACE with an accuracy of 78.2% (95%CI: 74.2–82.3), sensitivity of 77.6% (95%CI: 70.7–84.0), and specificity of 78.7% (95%CI: 72.9–84.1) for the internal validation cohort, and accuracy of 75.1% (95% CI: 73.1–81.7), sensitivity of 50.5% (95%CI: 40.0–61.5), and specificity of 83.5% (95%CI: 79.2–87.7) for the external validation cohort. Kaplan-Meier curves showed a significant difference in progression-free survival between the responders and non-responders divided by Model 2 (p = 0.002). Conclusions Our multi-task deep learning framework provided a real-time effective approach for decoding DSA videos and can offer clinical-decision support for TACE treatment in intermediate-stage HCC patients in real-world settings. |
| first_indexed | 2024-04-12T11:50:51Z |
| format | Article |
| id | doaj.art-cc5fa7a11f2540b0b233d0fd2d117b51 |
| institution | Directory Open Access Journal |
| issn | 1470-7330 |
| language | English |
| last_indexed | 2024-04-12T11:50:51Z |
| publishDate | 2022-05-01 |
| publisher | BMC |
| record_format | Article |
| series | Cancer Imaging |
| spelling | doaj.art-cc5fa7a11f2540b0b233d0fd2d117b512022-12-22T03:34:11ZengBMCCancer Imaging1470-73302022-05-0122111410.1186/s40644-022-00457-3Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videosLu Zhang0Yicheng Jiang1Zhe Jin2Wenting Jiang3Bin Zhang4Changmiao Wang5Lingeng Wu6Luyan Chen7Qiuying Chen8Shuyi Liu9Jingjing You10Xiaokai Mo11Jing Liu12Zhiyuan Xiong13Tao Huang14Liyang Yang15Xiang Wan16Ge Wen17Xiao Guang Han18Weijun Fan19Shuixing Zhang20Department of Radiology, The First Affiliated Hospital of Jinan UniversityShenzhen Research Institute of Big DataDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityShenzhen Research Institute of Big DataDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityShenzhen Research Institute of Big DataDepartment of Interventional Therapy, The Second Affiliated Hospital of Guangzhou University of Traditional Chinese MedicineDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityDepartment of Minimally Invasive Intervention, Sun Yat-sen University Cancer Center; State Key Laboratory of Oncology in South China; Collaborative Innovation Center for Cancer MedicineMedical Imaging Center, Nanfang Hospital, Southern Medical UniversityShenzhen Research Institute of Big DataMedical Imaging Center, Nanfang Hospital, Southern Medical UniversityShenzhen Research Institute of Big DataDepartment of Minimally Invasive Intervention, Sun Yat-sen University Cancer Center; State Key Laboratory of Oncology in South China; Collaborative Innovation Center for Cancer MedicineDepartment of Radiology, The First Affiliated Hospital of Jinan UniversityAbstract Background Transcatheter arterial chemoembolization (TACE) is the mainstay of therapy for intermediate-stage hepatocellular carcinoma (HCC); yet its efficacy varies between patients with the same tumor stage. Accurate prediction of TACE response remains a major concern to avoid overtreatment. Thus, we aimed to develop and validate an artificial intelligence system for real-time automatic prediction of TACE response in HCC patients based on digital subtraction angiography (DSA) videos via a deep learning approach. Methods This retrospective cohort study included a total of 605 patients with intermediate-stage HCC who received TACE as their initial therapy. A fully automated framework (i.e., DSA-Net) contained a U-net model for automatic tumor segmentation (Model 1) and a ResNet model for the prediction of treatment response to the first TACE (Model 2). The two models were trained in 360 patients, internally validated in 124 patients, and externally validated in 121 patients. Dice coefficient and receiver operating characteristic curves were used to evaluate the performance of Models 1 and 2, respectively. Results Model 1 yielded a Dice coefficient of 0.75 (95% confidence interval [CI]: 0.73–0.78) and 0.73 (95% CI: 0.71–0.75) for the internal validation and external validation cohorts, respectively. Integrating the DSA videos, segmentation results, and clinical variables (mainly demographics and liver function parameters), Model 2 predicted treatment response to first TACE with an accuracy of 78.2% (95%CI: 74.2–82.3), sensitivity of 77.6% (95%CI: 70.7–84.0), and specificity of 78.7% (95%CI: 72.9–84.1) for the internal validation cohort, and accuracy of 75.1% (95% CI: 73.1–81.7), sensitivity of 50.5% (95%CI: 40.0–61.5), and specificity of 83.5% (95%CI: 79.2–87.7) for the external validation cohort. Kaplan-Meier curves showed a significant difference in progression-free survival between the responders and non-responders divided by Model 2 (p = 0.002). Conclusions Our multi-task deep learning framework provided a real-time effective approach for decoding DSA videos and can offer clinical-decision support for TACE treatment in intermediate-stage HCC patients in real-world settings.https://doi.org/10.1186/s40644-022-00457-3Hepatocellular carcinomaTranscatheter arterial chemoembolizationDeep learningDSA videos |
| spellingShingle | Lu Zhang Yicheng Jiang Zhe Jin Wenting Jiang Bin Zhang Changmiao Wang Lingeng Wu Luyan Chen Qiuying Chen Shuyi Liu Jingjing You Xiaokai Mo Jing Liu Zhiyuan Xiong Tao Huang Liyang Yang Xiang Wan Ge Wen Xiao Guang Han Weijun Fan Shuixing Zhang Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos Cancer Imaging Hepatocellular carcinoma Transcatheter arterial chemoembolization Deep learning DSA videos |
| title | Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos |
| title_full | Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos |
| title_fullStr | Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos |
| title_full_unstemmed | Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos |
| title_short | Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos |
| title_sort | real time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos |
| topic | Hepatocellular carcinoma Transcatheter arterial chemoembolization Deep learning DSA videos |
| url | https://doi.org/10.1186/s40644-022-00457-3 |
| work_keys_str_mv | AT luzhang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT yichengjiang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT zhejin realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT wentingjiang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT binzhang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT changmiaowang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT lingengwu realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT luyanchen realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT qiuyingchen realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT shuyiliu realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT jingjingyou realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT xiaokaimo realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT jingliu realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT zhiyuanxiong realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT taohuang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT liyangyang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT xiangwan realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT gewen realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT xiaoguanghan realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT weijunfan realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos AT shuixingzhang realtimeautomaticpredictionoftreatmentresponsetotranscatheterarterialchemoembolizationinpatientswithhepatocellularcarcinomausingdeeplearningbasedondigitalsubtractionangiographyvideos |