Application of a deep learning algorithm for the diagnosis of HCC

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Oncology

Background:

• Hepatocellular carcinoma (HCC) presents a high mortality rate.
• The Liver Imaging Reporting and Data System (LI-RADS) often yields indeterminate observations, complicating accurate HCC diagnosis.
• There is a need for improved diagnostic accuracy in HCC detection.

Purpose of the Study:

• To develop and evaluate deep learning models for diagnosing HCC using computed tomography (CT) images.
• To compare the diagnostic performance of deep learning models against standard radiological interpretation.
• To assess the robustness and clinical applicability of deep learning in HCC diagnosis.

Main Methods:

• Four deep learning models were developed using a training-validation-testing approach on thin-slice triphasic CT liver images and clinical data.
• The Spatio-Temporal 3D Convolution Network (ST3DCN) was identified as the best-performing model.
• Diagnostic performance was evaluated using internal validation and independent external testing, with HCC diagnosis verified by a 12-month clinical composite reference standard.

Main Results:

• The ST3DCN model achieved an area under the receiver-operating-characteristic curve (AUC) of 0.919 at the observation level and 0.901 at the patient level during internal validation.
• ST3DCN demonstrated superior performance compared to standard radiological interpretation (AUCs of 0.839 and 0.822, respectively).
• In external testing, ST3DCN achieved an AUC of 0.901, demonstrating non-inferiority to radiological interpretation (AUC 0.900).

Conclusions:

• The ST3DCN deep learning model exhibits strong and robust performance for accurate HCC diagnosis on CT.
• Deep learning approaches can expedite and enhance the diagnostic process for HCC.
• The findings support the potential for broad clinical deployment of deep learning to improve HCC detection and reduce mortality.