R2U3D: Recurrent Residual 3D U-Net for Lung Segmentation

TL;DR

This paper introduces R2U3D, a novel recurrent residual 3D U-Net model that effectively captures spatial dependencies for lung segmentation, achieving state-of-the-art results on public datasets with limited training data.

Contribution

The paper presents a new 3D lung segmentation model integrating recurrent residual learning into U-Net, improving volumetric information propagation and performance.

Findings

Achieves Soft-DSC of 0.9920 with only 100 scans without data augmentation.

Outperforms existing models on LUNA16 and VESSEL12 datasets.

Demonstrates effectiveness with limited training data.

Abstract

3D lung segmentation is essential since it processes the volumetric information of the lungs, removes the unnecessary areas of the scan, and segments the actual area of the lungs in a 3D volume. Recently, the deep learning model, such as U-Net outperforms other network architectures for biomedical image segmentation. In this paper, we propose a novel model, namely, Recurrent Residual 3D U-Net (R2U3D), for the 3D lung segmentation task. In particular, the proposed model integrates 3D convolution into the Recurrent Residual Neural Network based on U-Net. It helps learn spatial dependencies in 3D and increases the propagation of 3D volumetric information. The proposed R2U3D network is trained on the publicly available dataset LUNA16 and it achieves state-of-the-art performance on both LUNA16 (testing set) and VESSEL12 dataset. In addition, we show that training the R2U3D model with a smaller number of CT scans, i.e., 100 scans, without applying data augmentation achieves an outstanding result in terms of Soft Dice Similarity Coefficient (Soft-DSC) of 0.9920.