Recurrent convolutional neural networks for mandible segmentation from computed tomography

TL;DR

This paper introduces RSegCNN, a recurrent convolutional neural network that leverages slice-to-slice continuity to improve mandible segmentation accuracy in CT scans, effectively handling artifacts and shape variations.

Contribution

The paper presents a novel RSegCNN model that combines recurrent neural networks with segmentation CNNs for robust mandible segmentation in CT images, addressing shape variability and artifacts.

Findings

RSegCNN outperforms state-of-the-art models in mandible segmentation accuracy.

The recurrent structure effectively captures inter-slice continuity.

The method demonstrates robustness against metal artifacts and anatomical variations.

Abstract

Recently, accurate mandible segmentation in CT scans based on deep learning methods has attracted much attention. However, there still exist two major challenges, namely, metal artifacts among mandibles and large variations in shape or size among individuals. To address these two challenges, we propose a recurrent segmentation convolutional neural network (RSegCNN) that embeds segmentation convolutional neural network (SegCNN) into the recurrent neural network (RNN) for robust and accurate segmentation of the mandible. Such a design of the system takes into account the similarity and continuity of the mandible shapes captured in adjacent image slices in CT scans. The RSegCNN infers the mandible information based on the recurrent structure with the embedded encoder-decoder segmentation (SegCNN) components. The recurrent structure guides the system to exploit relevant and important information from adjacent slices, while the SegCNN component focuses on the mandible shapes from a single CT slice. We conducted extensive experiments to evaluate the proposed RSegCNN on two head and neck CT datasets. The experimental results show that the RSegCNN is significantly better than the state-of-the-art models for accurate mandible segmentation.