Application of a deep learning algorithm for the diagnosis of HCC
Background & Aims: Hepatocellular carcinoma (HCC) is characterized by a high mortality rate. The Liver Imaging Reporting and Data System (LI-RADS) results in a considerable number of indeterminate observations, rendering an accurate diagnosis difficult. Methods: We developed four deep learni...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | JHEP Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589555924002234 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550723246981120 |
|---|---|
| author | Philip Leung Ho Yu Keith Wan-Hang Chiu Jianliang Lu Gilbert C.S. Lui Jian Zhou Ho-Ming Cheng Xianhua Mao Juan Wu Xin-Ping Shen King Ming Kwok Wai Kuen Kan Y.C. Ho Hung Tat Chan Peng Xiao Lung-Yi Mak Vivien W.M. Tsui Cynthia Hui Pui Mei Lam Zijie Deng Jiaqi Guo Li Ni Jinhua Huang Sarah Yu Chengzhi Peng Wai Keung Li Man-Fung Yuen Wai-Kay Seto |
| author_facet | Philip Leung Ho Yu Keith Wan-Hang Chiu Jianliang Lu Gilbert C.S. Lui Jian Zhou Ho-Ming Cheng Xianhua Mao Juan Wu Xin-Ping Shen King Ming Kwok Wai Kuen Kan Y.C. Ho Hung Tat Chan Peng Xiao Lung-Yi Mak Vivien W.M. Tsui Cynthia Hui Pui Mei Lam Zijie Deng Jiaqi Guo Li Ni Jinhua Huang Sarah Yu Chengzhi Peng Wai Keung Li Man-Fung Yuen Wai-Kay Seto |
| author_sort | Philip Leung Ho Yu |
| collection | DOAJ |
| description | Background & Aims: Hepatocellular carcinoma (HCC) is characterized by a high mortality rate. The Liver Imaging Reporting and Data System (LI-RADS) results in a considerable number of indeterminate observations, rendering an accurate diagnosis difficult. Methods: We developed four deep learning models for diagnosing HCC on computed tomography (CT) via a training–validation–testing approach. Thin-slice triphasic CT liver images and relevant clinical information were collected and processed for deep learning. HCC was diagnosed and verified via a 12-month clinical composite reference standard. CT observations among at-risk patients were annotated using LI-RADS. Diagnostic performance was assessed by internal validation and independent external testing. We conducted sensitivity analyses of different subgroups, deep learning explainability evaluation, and misclassification analysis. Results: From 2,832 patients and 4,305 CT observations, the best-performing model was Spatio-Temporal 3D Convolution Network (ST3DCN), achieving area under receiver-operating-characteristic curves (AUCs) of 0.919 (95% CI, 0.903–0.935) and 0.901 (95% CI, 0.879–0.924) at the observation (n = 1,077) and patient (n = 685) levels, respectively during internal validation, compared with 0.839 (95% CI, 0.814–0.864) and 0.822 (95% CI, 0.790–0.853), respectively for standard of care radiological interpretation. The negative predictive values of ST3DCN were 0.966 (95% CI, 0.954–0.979) and 0.951 (95% CI, 0.931–0.971), respectively. The observation-level AUCs among at-risk patients, 2–5-cm observations, and singular portovenous phase analysis of ST3DCN were 0.899 (95% CI, 0.874–0.924), 0.872 (95% CI, 0.838–0.909) and 0.912 (95% CI, 0.895–0.929), respectively. In external testing (551/717 patients/observations), the AUC of ST3DCN was 0.901 (95% CI, 0.877–0.924), which was non-inferior to radiological interpretation (AUC 0.900; 95% CI, 0.877–-923). Conclusions: ST3DCN achieved strong, robust performance for accurate HCC diagnosis on CT. Thus, deep learning can expedite and improve the process of diagnosing HCC. Impact and implications:: The clinical applicability of deep learning in HCC diagnosis is potentially huge, especially considering the expected increase in the incidence and mortality of HCC worldwide. Early diagnosis through deep learning can lead to earlier definitive management, particularly for at-risk patients. The model can be broadly deployed for patients undergoing a triphasic contrast CT scan of the liver to reduce the currently high mortality rate of HCC. |
| format | Article |
| id | doaj-art-e310a2c520834a86801fd57090659381 |
| institution | Kabale University |
| issn | 2589-5559 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | JHEP Reports |
| spelling | doaj-art-e310a2c520834a86801fd570906593812025-01-10T04:38:03ZengElsevierJHEP Reports2589-55592025-01-0171101219Application of a deep learning algorithm for the diagnosis of HCCPhilip Leung Ho Yu0Keith Wan-Hang Chiu1Jianliang Lu2Gilbert C.S. Lui3Jian Zhou4Ho-Ming Cheng5Xianhua Mao6Juan Wu7Xin-Ping Shen8King Ming Kwok9Wai Kuen Kan10Y.C. Ho11Hung Tat Chan12Peng Xiao13Lung-Yi Mak14Vivien W.M. Tsui15Cynthia Hui16Pui Mei Lam17Zijie Deng18Jiaqi Guo19Li Ni20Jinhua Huang21Sarah Yu22Chengzhi Peng23Wai Keung Li24Man-Fung Yuen25Wai-Kay Seto26Department of Computer Science, The University of Hong Kong, Hong Kong, China; Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, ChinaDepartment of Diagnostic Radiology, School of Clinical Medicine, The University of Hong Kong, Hong Kong, China; Department of Radiology and Imaging, Queen Elizabeth Hospital, Hong Kong, China; Department of Medical Imaging, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, ChinaDepartment of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, ChinaDepartment of Medical Imaging, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, ChinaDepartment of Medical Imaging, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, ChinaDepartment of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Medical Imaging, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Diagnostic and Interventional Radiology, Kwong Wah Hospital, Hong Kong, ChinaDepartment of Radiology, Pamela Youde Nethersole Eastern Hospital, Hong Kong, ChinaDepartment of Radiology, Queen Mary Hospital, Hong Kong, ChinaDepartment of Medical Imaging, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, China; State Key Laboratory of Liver Research, The University of Hong Kong, Hong Kong, ChinaDepartment of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, ChinaDepartment of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, ChinaDepartment of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, ChinaDepartment of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, ChinaDepartment of Minimal Invasive Interventional Therapy, Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, ChinaDepartment of Diagnostic Radiology, School of Clinical Medicine, The University of Hong Kong, Hong Kong, ChinaLi Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, ChinaDepartment of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong, ChinaDepartment of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, China; Department of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, China; State Key Laboratory of Liver Research, The University of Hong Kong, Hong Kong, China; Corresponding authors. Address: Department of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, China. Tel.: +86 75586913388.Department of Medicine, School of Clinical Medicine, The University of Hong Kong, Hong Kong, China; Department of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, China; State Key Laboratory of Liver Research, The University of Hong Kong, Hong Kong, China; Corresponding authors. Address: Department of Medicine, The University of Hong Kong-Shenzhen Hospital, Shenzhen, China. Tel.: +86 75586913388.Background & Aims: Hepatocellular carcinoma (HCC) is characterized by a high mortality rate. The Liver Imaging Reporting and Data System (LI-RADS) results in a considerable number of indeterminate observations, rendering an accurate diagnosis difficult. Methods: We developed four deep learning models for diagnosing HCC on computed tomography (CT) via a training–validation–testing approach. Thin-slice triphasic CT liver images and relevant clinical information were collected and processed for deep learning. HCC was diagnosed and verified via a 12-month clinical composite reference standard. CT observations among at-risk patients were annotated using LI-RADS. Diagnostic performance was assessed by internal validation and independent external testing. We conducted sensitivity analyses of different subgroups, deep learning explainability evaluation, and misclassification analysis. Results: From 2,832 patients and 4,305 CT observations, the best-performing model was Spatio-Temporal 3D Convolution Network (ST3DCN), achieving area under receiver-operating-characteristic curves (AUCs) of 0.919 (95% CI, 0.903–0.935) and 0.901 (95% CI, 0.879–0.924) at the observation (n = 1,077) and patient (n = 685) levels, respectively during internal validation, compared with 0.839 (95% CI, 0.814–0.864) and 0.822 (95% CI, 0.790–0.853), respectively for standard of care radiological interpretation. The negative predictive values of ST3DCN were 0.966 (95% CI, 0.954–0.979) and 0.951 (95% CI, 0.931–0.971), respectively. The observation-level AUCs among at-risk patients, 2–5-cm observations, and singular portovenous phase analysis of ST3DCN were 0.899 (95% CI, 0.874–0.924), 0.872 (95% CI, 0.838–0.909) and 0.912 (95% CI, 0.895–0.929), respectively. In external testing (551/717 patients/observations), the AUC of ST3DCN was 0.901 (95% CI, 0.877–0.924), which was non-inferior to radiological interpretation (AUC 0.900; 95% CI, 0.877–-923). Conclusions: ST3DCN achieved strong, robust performance for accurate HCC diagnosis on CT. Thus, deep learning can expedite and improve the process of diagnosing HCC. Impact and implications:: The clinical applicability of deep learning in HCC diagnosis is potentially huge, especially considering the expected increase in the incidence and mortality of HCC worldwide. Early diagnosis through deep learning can lead to earlier definitive management, particularly for at-risk patients. The model can be broadly deployed for patients undergoing a triphasic contrast CT scan of the liver to reduce the currently high mortality rate of HCC.http://www.sciencedirect.com/science/article/pii/S2589555924002234HCCAILiver cancerCTLIRADSImaging |
| spellingShingle | Philip Leung Ho Yu Keith Wan-Hang Chiu Jianliang Lu Gilbert C.S. Lui Jian Zhou Ho-Ming Cheng Xianhua Mao Juan Wu Xin-Ping Shen King Ming Kwok Wai Kuen Kan Y.C. Ho Hung Tat Chan Peng Xiao Lung-Yi Mak Vivien W.M. Tsui Cynthia Hui Pui Mei Lam Zijie Deng Jiaqi Guo Li Ni Jinhua Huang Sarah Yu Chengzhi Peng Wai Keung Li Man-Fung Yuen Wai-Kay Seto Application of a deep learning algorithm for the diagnosis of HCC JHEP Reports HCC AI Liver cancer CT LIRADS Imaging |
| title | Application of a deep learning algorithm for the diagnosis of HCC |
| title_full | Application of a deep learning algorithm for the diagnosis of HCC |
| title_fullStr | Application of a deep learning algorithm for the diagnosis of HCC |
| title_full_unstemmed | Application of a deep learning algorithm for the diagnosis of HCC |
| title_short | Application of a deep learning algorithm for the diagnosis of HCC |
| title_sort | application of a deep learning algorithm for the diagnosis of hcc |
| topic | HCC AI Liver cancer CT LIRADS Imaging |
| url | http://www.sciencedirect.com/science/article/pii/S2589555924002234 |
| work_keys_str_mv | AT philipleunghoyu applicationofadeeplearningalgorithmforthediagnosisofhcc AT keithwanhangchiu applicationofadeeplearningalgorithmforthediagnosisofhcc AT jianlianglu applicationofadeeplearningalgorithmforthediagnosisofhcc AT gilbertcslui applicationofadeeplearningalgorithmforthediagnosisofhcc AT jianzhou applicationofadeeplearningalgorithmforthediagnosisofhcc AT homingcheng applicationofadeeplearningalgorithmforthediagnosisofhcc AT xianhuamao applicationofadeeplearningalgorithmforthediagnosisofhcc AT juanwu applicationofadeeplearningalgorithmforthediagnosisofhcc AT xinpingshen applicationofadeeplearningalgorithmforthediagnosisofhcc AT kingmingkwok applicationofadeeplearningalgorithmforthediagnosisofhcc AT waikuenkan applicationofadeeplearningalgorithmforthediagnosisofhcc AT ycho applicationofadeeplearningalgorithmforthediagnosisofhcc AT hungtatchan applicationofadeeplearningalgorithmforthediagnosisofhcc AT pengxiao applicationofadeeplearningalgorithmforthediagnosisofhcc AT lungyimak applicationofadeeplearningalgorithmforthediagnosisofhcc AT vivienwmtsui applicationofadeeplearningalgorithmforthediagnosisofhcc AT cynthiahui applicationofadeeplearningalgorithmforthediagnosisofhcc AT puimeilam applicationofadeeplearningalgorithmforthediagnosisofhcc AT zijiedeng applicationofadeeplearningalgorithmforthediagnosisofhcc AT jiaqiguo applicationofadeeplearningalgorithmforthediagnosisofhcc AT lini applicationofadeeplearningalgorithmforthediagnosisofhcc AT jinhuahuang applicationofadeeplearningalgorithmforthediagnosisofhcc AT sarahyu applicationofadeeplearningalgorithmforthediagnosisofhcc AT chengzhipeng applicationofadeeplearningalgorithmforthediagnosisofhcc AT waikeungli applicationofadeeplearningalgorithmforthediagnosisofhcc AT manfungyuen applicationofadeeplearningalgorithmforthediagnosisofhcc AT waikayseto applicationofadeeplearningalgorithmforthediagnosisofhcc |