Knowledge-based Fully Convolutional Network and Its Application in Segmentation of Lung CT Images

TL;DR

This paper introduces a knowledge-based fully convolutional network (KFCN) that incorporates prior medical image knowledge into the network structure, improving segmentation accuracy of lung CT images.

Contribution

The paper proposes a novel KFCN architecture that embeds prior knowledge into convolution kernels, enhancing segmentation performance over traditional FCNs.

Findings

KFCN achieves reasonable segmentation accuracy.

KFCN has an asymptotically stable region unlike traditional FCN.

Incorporating prior knowledge improves segmentation results.

Abstract

A variety of deep neural networks have been applied in medical image segmentation and achieve good performance. Unlike natural images, medical images of the same imaging modality are characterized by the same pattern, which indicates that same normal organs or tissues locate at similar positions in the images. Thus, in this paper we try to incorporate the prior knowledge of medical images into the structure of neural networks such that the prior knowledge can be utilized for accurate segmentation. Based on this idea, we propose a novel deep network called knowledge-based fully convolutional network (KFCN) for medical image segmentation. The segmentation function and corresponding error is analyzed. We show the existence of an asymptotically stable region for KFCN which traditional FCN doesn't possess. Experiments validate our knowledge assumption about the incorporation of prior knowledge into the convolution kernels of KFCN and show that KFCN can achieve a reasonable segmentation and a satisfactory accuracy.