Segmentation of Lung Nodules Using Improved 3D-UNet Neural Network

Abstract

Lung cancer has one of the highest morbidity and mortality rates in the world. Lung nodules are an early indicator of lung cancer. Therefore, accurate detection and image segmentation of lung nodules is of great significance to the early diagnosis of lung cancer. This paper proposes a CT (Computed Tomography) image lung nodule segmentation method based on 3D-UNet and Res2Net, and establishes a new convolutional neural network called 3D-Res2UNet. 3D-Res2Net has a symmetrical hierarchical connection network with strong multi-scale feature extraction capabilities. It enables the network to express multi-scale features with a finer granularity, while increasing the receptive field of each layer of the network. This structure solves the deep level problem. The network is not prone to gradient disappearance and gradient explosion problems, which improves the accuracy of detection and segmentation. The U-shaped network ensures the size of the feature map while effectively repairing the lost features. The method in this paper was tested on the LUNA16 public dataset, where the dice coefficient index reached 95.30% and the recall rate reached 99.1%, indicating that this method has good performance in lung nodule image segmentation.

Lung Nodule Segmentation with a Region-Based Fast Marching Method

“…For this reason, two of the works brought up in Section 1 were chosen. Cao et al 2019 (DBResNet) [ 29 ] and Xiao et al 2020 (3D-UNet) [ 32 ] both proposed lung nodule segmentation methods which obtained competitive results. Their proposals have been evaluated on the public LIDC dataset, and produced Dice scores of 82.74% and 95.30% respectively.…”

“…In most recent works the U-Net architecture has been popular with three-dimensional implementations that improve its performance. Funke et al [ 31 ] trained a 3D-UNet model using using the STAPLE algorithm, and Xiao et al [ 32 ] combined the 3D-UNet and Res2Net architectures to create a new model which reached a Dice score of 95.3% on the Lung Image Database Consortium (LIDC) dataset. In a different approach, Hu et al [ 33 ] utilized a hybrid attention mechanism and densely connected convolutional networks, reaching a Dice score of 94.6%.…”

COVID-MTL: Multitask learning with Shift3D and random-weighted loss for COVID-19 diagnosis and severity assessment

“…Lung segmentation is a necessary and critical step for the diagnosis and treatment of lung diseases, especially in the early stage. Conventionally, U-net, a symmetric model architecture that is widely used in medical image segmentation, is applied for lung [20] and lung lesion/nodule segmentation [21] . However, this method requires lung delineation masks that are paired to each input CT slice for training.…”

Palpation Localization of Radial Artery Based on 3-Dimensional Convolutional Neural Networks

“…In order to solve the problem of inaccurate positioning caused by insufficient information extraction in 2DCNN, we increase the temporal and spatial information by introducing a 3D convolution kernel The results Article show the comparison between the positioning prediction effect of 3DCNN and 2DCNN. In order to increase the credibility of the results, we also added four additional sets of comparative experiments, including three classic models, AlexNet [30],Vgg16 [31],Vgg19 [32], which have 2d convolution kernel structure and 3D-Unet [33] that also has 3d convolution kernel structure. The result shows that our proposed 3DCNN model on task of locating with improvements of 20%, 12%,12%,9%,7% on 20pixels than 2DCNN,AlexNet,Vgg16,Vgg19,3D-Unet, respectively.…”