ABSTRACT
Segmentation of the liver from 3D computer tomography (CT) images is one of the most frequently performed operations in medical image analysis. In the past decade, Deep Learning Models (DMs) have offered significant improvements over previous methods for liver segmentation. The success of DMs is usually owed to the user’s expertise in deep learning as well as to intricate training procedures. The need for bespoke expertise limits the reproducibility of empirical studies involving DMs. Today’s consensus is that an ensemble of DMs works better than the individual component DMs. In this study we set off to explore the potential of ensembles of publicly available, ‘vanilla style DM segmenters. Our ensembles were created from four off-the-shelf DMs: U-Net, Deepmedic, V-Net, and Dense V-Networks. To prevent further overfitting and to keep the overall model simple, we use basic non-trainable ensemble combiners: majority vote, average, product and min/max. Our results with two publicly available data sets (CHAOS and 3Dircadb1) demonstrate that ensembles are significantly better than the individual segmenters on four widely used metrics.
