Abstract
Objective: In this study, we propose a neural network-based liver segmentation algorithm and evaluate its performance using abdominal computed tomography (CT) images. Methods: We develop a fully convolutional network to overcome the volumetric image segmentation problem. To guide a neural network to accurately delineate the target liver object, we deeply supervised our network by applying the adaptive self-supervision scheme to derive the essential contour which acts as a complement with the global shape. The discriminative contour, shape, and deep features are internally merged for the segmentation results. Results and Conclusion: We used 160 abdominal CT images for training and validation. The quantitative evaluation of our proposed network is performed through eight-fold cross-validation. The result showed that our method, which uses the contour feature, successfully segmented the liver more accurately and showed better generalization performance than any other state-of-the-art methods without expanding or deepening the neural network. The proposed approach can be easily extended to other imaging protocols (e.g., magnetic resonance imaging) or other target organ segmentation problems without any modifications of the framework. Significance: In this work, we introduce a new framework to guide a neural network to learn complementary contour features. Our proposed neural network demonstrates that the guided contour features can significantly improve the performance of the segmentation task.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1808.00739