Dataset Information

Deep learning for differential diagnosis of malignant hepatic tumors based on multi-phase contrast-enhanced CT and clinical data.

ABSTRACT:

Background

Liver cancer remains the leading cause of cancer death globally, and the treatment strategies are distinct for each type of malignant hepatic tumors. However, the differential diagnosis before surgery is challenging and subjective. This study aims to build an automatic diagnostic model for differentiating malignant hepatic tumors based on patients' multimodal medical data including multi-phase contrast-enhanced computed tomography and clinical features.

Methods

Our study consisted of 723 patients from two centers, who were pathologically diagnosed with HCC, ICC or metastatic liver cancer. The training set and the test set consisted of 499 and 113 patients from center 1, respectively. The external test set consisted of 111 patients from center 2. We proposed a deep learning model with the modular design of SpatialExtractor-TemporalEncoder-Integration-Classifier (STIC), which take the advantage of deep CNN and gated RNN to effectively extract and integrate the diagnosis-related radiological and clinical features of patients. The code is publicly available at https://github.com/ruitian-olivia/STIC-model .

Results

The STIC model achieved an accuracy of 86.2% and AUC of 0.893 for classifying HCC and ICC on the test set. When extended to differential diagnosis of malignant hepatic tumors, the STIC model achieved an accuracy of 72.6% on the test set, comparable with the diagnostic level of doctors' consensus (70.8%). With the assistance of the STIC model, doctors achieved better performance than doctors' consensus diagnosis, with an increase of 8.3% in accuracy and 26.9% in sensitivity for ICC diagnosis on average. On the external test set from center 2, the STIC model achieved an accuracy of 82.9%, which verify the model's generalization ability.

Conclusions

We incorporated deep CNN and gated RNN in the STIC model design for differentiating malignant hepatic tumors based on multi-phase CECT and clinical features. Our model can assist doctors to achieve better diagnostic performance, which is expected to serve as an AI assistance system and promote the precise treatment of liver cancer.

SUBMITTER: Gao R

PROVIDER: S-EPMC8474892 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeTo evaluate the feasibility of using contrast material-enhanced computed tomographic (CT) measurements of hepatic fractional extracellular space (fECS) and macromolecular contrast material (MMCM) uptake to measure severity of liver fibrosis.Materials and methodsAll procedures were approved by and executed in accordance with University of California, San Francisco, institutional animal care and use committee regulations. Twenty-one rats that received intragastric CCl(4) for 0-12 weeks were imaged with respiratory-gated micro-CT by using both a conventional contrast material and a novel iodinated MMCM. Histopathologic hepatic fibrosis was graded qualitatively by using the Ishak fibrosis score and quantitatively by using morphometry of the fibrosis area. Hepatic fECS and MMCM uptake were calculated for each examination and correlated with histopathologic findings by using uni- and multivariate linear regressions.ResultsIshak fibrosis scores ranged from a baseline of 0 in untreated animals to a maximum of 5. Histopathologic liver fibrosis area increased from 0.46% to 3.5% over the same interval. Strong correlations were seen between conventional contrast-enhanced CT measurements of fECS and both the Ishak fibrosis scores (R(2) = 0.751, P < .001) and the fibrosis area (R(2) = 0.801, P < .001). Strong negative correlations were observed between uptake of MMCM in the liver and Ishak fibrosis scores (R(2) = 0.827, P < .001), as well as between uptake of MMCM in the liver and fibrosis area (R(2) = 0.643, P = .001). Multivariate linear regression analysis showed a trend toward independence for fECS and MMCM uptake in the prediction of Ishak fibrosis scores, with an R(2) value of 0.86 (P = .081 and P = .033, respectively).ConclusionContrast-enhanced CT measurements of fECS and MMCM uptake are individually capable of being used to estimate the degree of early hepatic fibrosis in a rat model.Supplemental materialhttp://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.12112452/-/DC1.