Open AccessA flexible three‐dimensional heterophase computed tomography hepatocellular carcinoma detection algorithm for generalizable and practical screening
Author(s) -
Cheng ChiTung,
Cai Jinzheng,
Teng Wei,
Zheng Youjing,
Huang YuTing,
Wang YuChao,
Peng ChienWei,
Tang Youbao,
Lee WeiChen,
Yeh TaSen,
Xiao Jing,
Lu Le,
Liao ChienHung,
Harrison Adam P.
Publication year - 2022
Publication title -
hepatology communications
Language(s) - English
Resource type - Journals
ISSN - 2471-254X
DOI - 10.1002/hep4.2029
Subject(s) - false positive paradox , hepatocellular carcinoma , receiver operating characteristic , algorithm , computed tomography , medicine , radiology , confidence interval , artificial intelligence , flexibility (engineering) , sensitivity (control systems) , detector , true positive rate , contrast (vision) , clinical practice , computer science , nuclear medicine , machine learning , mathematics , engineering , telecommunications , statistics , family medicine , electronic engineering
Hepatocellular carcinoma (HCC) can be potentially discovered from abdominal computed tomography (CT) studies under varied clinical scenarios (e.g., fully dynamic contrast‐enhanced [DCE] studies, noncontrast [NC] plus venous phase [VP] abdominal studies, or NC‐only studies). Each scenario presents its own clinical challenges that could benefit from computer‐aided detection (CADe) tools. We investigate whether a single CADe model can be made flexible enough to handle different contrast protocols and whether this flexibility imparts performance gains. We developed a flexible three‐dimensional deep algorithm, called heterophase volumetric detection (HPVD), that can accept any combination of contrast‐phase inputs with adjustable sensitivity depending on the clinical purpose. We trained HPVD on 771 DCE CT scans to detect HCCs and evaluated it on 164 positives and 206 controls. We compared performance against six clinical readers, including two radiologists, two hepatopancreaticobiliary surgeons, and two hepatologists. The area under the curve of the localization receiver operating characteristic for NC‐only, NC plus VP, and full DCE CT yielded 0.71 (95% confidence interval [CI], 0.64–0.77), 0.81 (95% CI, 0.75–0.87), and 0.89 (95% CI, 0.84–0.93), respectively. At a high‐sensitivity operating point of 80% on DCE CT, HPVD achieved 97% specificity, which is comparable to measured physician performance. We also demonstrated performance improvements over more typical and less flexible nonheterophase detectors. Conclusion : A single deep‐learning algorithm can be effectively applied to diverse HCC detection clinical scenarios, indicating that HPVD could serve as a useful clinical aid for at‐risk and opportunistic HCC surveillance.