Deep Learning-Based Prediction of Hepatic Decompensation in Patients With Primary Sclerosing Cholangitis With Computed Tomography

Abstract

ObjectiveTo investigate a deep learning model for predicting hepatic decompensation using Computed Tomography (CT) imaging in patients with primary sclerosing cholangitis (PSC). Patients and MethodsRetrospective cohort study involving 277 adult patients with large duct PSC who underwent an abdominal CT scan. The portal venous phase CT images were used as input to a 3D Densenet121 model, which was trained using five-fold cross-validation to classify hepatic decompensation. To further investigate the role of each anatomic region in the model's decision-making process, we trained the model on different sections of 3D CT images. This included training on the right, left, anterior, posterior, inferior, and superior halves of the image dataset. For each half, as well as for the entire scan, we performed AUROC analysis. ResultsHepatic decompensation occurred in 128 individuals after a median (interquartile range) of 1.5 years days (142-1318) following the CT scan. The deep learning model exhibited promising results, with a mean ± standard deviation (SD) AUROC of 0.89 ± 0.04 for the baseline model. The mean ± SD AUROC for left, right, anterior, posterior, superior, and inferior halves were 0.83 ± 0.03, 0.83 ± 0.03, 0.82 ± 0.09, 0.79 ± 0.02, 0.78 ± 0.02, and 0.76 ± 0.04 respectively. ConclusionThe study illustrates the potential of examining CT imaging via 3D DenseNet 121 deep learning model to predict hepatic decompensation in patients with PSC.