2D-Densely Connected Convolution Neural Networks for automatic Liver and Tumor Segmentation

TL;DR

This paper introduces a fully automatic, two-stage cascaded DenseNet-based approach for liver and tumor segmentation in CT images, achieving high accuracy in liver segmentation and reasonable tumor detection performance.

Contribution

It presents a novel cascaded DenseNet framework with separate training for liver and tumor segmentation, improving accuracy in automated liver and tumor analysis.

Findings

Achieved a 0.923 dice score for liver segmentation.

Achieved a 0.625 dice score for tumor segmentation.

Tumor burden RMSE of 0.044.

Abstract

In this paper we propose a fully automatic 2-stage cascaded approach for segmentation of liver and its tumors in CT (Computed Tomography) images using densely connected fully convolutional neural network (DenseNet). We independently train liver and tumor segmentation models and cascade them for a combined segmentation of the liver and its tumor. The first stage involves segmentation of liver and the second stage uses the first stage's segmentation results for localization of liver and henceforth tumor segmentations inside liver region. The liver model was trained on the down-sampled axial slices $(256 \times 256)$, whereas for the tumor model no down-sampling of slices was done, but instead it was trained on the CT axial slices windowed at three different Hounsfield (HU) levels. On the test set our model achieved a global dice score of 0.923 and 0.625 on liver and tumor respectively. The computed tumor burden had an rmse of 0.044.