Application of a deep learning algorithm for the diagnosis of HCC
Philip Leung Ho Yu1,2, Keith Wan-Hang Chiu3,4,5, Jianliang Lu6
1Department of Computer Science, The University of Hong Kong, Hong Kong, China.
Insights
Deep learning models, including the Spatio-Temporal 3D Convolution Network (ST3DCN), show strong performance in diagnosing hepatocellular carcinoma (HCC) on CT scans. This technology can improve early detection and management of HCC, a disease with high mortality.
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.
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.
