Robust Abdominal Organ Segmentation Using Regional Convolutional Neural Networks
Journal article, 2018

A fully automatic system for abdominal organ segmentation is presented. As a first step, an organ localization is obtained via a robust and efficient feature registration method where the center of the organ is estimated together with a region of interest surrounding the center. Then, a convolutional neural network performing voxelwise classification is applied. Two convolutional neural networks of different architecture are compared. The first one has a structure similar to networks used for classification and is applied using a sliding window approach. The second one has a structure allowing it to be applied in a fully convolutional manner reducing computation time. Despite limited training data, our experimental results are on par with state-of-the-art approaches that have been developed over many years. More specifically the method is applied to the MICCAI2015 challenge “Multi-Atlas Labeling Beyond the Cranial Vault” in the free competition for organ segmentation in the abdomen. The method performed well for both types of convolutional neural networks. For the fully convolutional network a mean Dice coefficient of 0.767 was achieved, for the network applied with sliding window this number was 0.757.

Medical Image Analysis

Segmentation

Convolutional Neural Networks

Author

Måns Larsson

Chalmers, Electrical Engineering, Signalbehandling och medicinsk teknik, Imaging and Image Analysis

Zhang Yuhang

Chalmers, Electrical Engineering, Signalbehandling och medicinsk teknik, Imaging and Image Analysis

Fredrik Kahl

Chalmers, Electrical Engineering, Signalbehandling och medicinsk teknik, Imaging and Image Analysis

Applied Soft Computing Journal

1568-4946 (ISSN)

Vol. 70 465-470

Areas of Advance

Information and Communication Technology

Subject Categories

Mathematics

Electrical Engineering, Electronic Engineering, Information Engineering

DOI

10.1016/j.asoc.2018.05.038

More information

Latest update

12/5/2018