Multiphase CT-based prediction of Child-Pugh classification: a machine learning approach

The aim of this study was to evaluate whether machine learning algorithms allow for the prediction of Child-Pugh classification on clinical multiphase computed tomography (CT). The authors found that the performance of convolutional neural networks (CNN) is comparable to that of experienced radiologists in assessing Child-Pugh class based on multiphase abdominal CT. Key points Established machine learning algorithms can predict the Child-Pugh class of a liver based on a clinical multiphase computed tomography. The predictive performance of a convolutional neural network in assessing liver parenchyma has the potential to be comparable to that of experienced radiologists. Machine learning algorithms, in particular convolutional neural networks, may constitute an adjunct quantitative and objective tool to assess the functional liver status based on imaging information. Article: Multiphase CT-based prediction of Child-Pugh classification: a machine learning approach Authors: Johannes Thüring, Oliver Rippel, Christoph Haarburger, Dorit Merhof, Philipp Schad, Philipp Bruners, Christiane K. Kuhl & Daniel Truhn