3D Segmentation of Pulmonary Nodules Based on Multi-View and Semi-Supervised

Abstract

For large-scale CT images, the automatic segmentation of nodules is the foundation for diagnosis of various pulmonary diseases. Most existing methods have made great progress in pulmonary segmentation. But because of the similar structure between vessels and nodules in 2D, it lacks the ability to extract more discriminative features. The accuracy is still not satisfying. And the task remains challenging due to the lack of voxel labels and training strategies to balance foreground and background. To solve these problems, a 3D segmentation network of pulmonary nodules based on semi-supervised was proposed. Firstly, a framework of multi-view feature extraction was designed to solve the problem of high similarity between nodules and other tissues. It extracted features from three different views to improve precision. And three parallel dilated convolutions were added for multi-scale feature extraction. Hence, the spatial and semantic information of different sizes can be better obtained. Secondly, for the problem of identifying difficult samples, a hybrid loss function with an adjustment factor was proposed. It magnifies the loss of difficult samples, which will attract more attention from the network. And a new regularization term was introduced to avoid overfitting. The entire network was trained with a few labeled CT data set through an improved semi-supervised learning strategy, which was optimized with a new self-paced regularization. Experimental results show that the average sensitivity of the proposed method is 95.81%. It is superior to other methods in terms of precision and Dice index especially when the data set is not satisfied.

A Systematic Review of Automated Segmentation Methods and Public Datasets for the Lung and its Lobes and Findings on Computed Tomography Images

“…Many variations and small modifications of the original UNet architecture have been proposed [33,[152][153][154][155][156][157][158][159][160][161][162][163][164][165], including 3D variations coined VNet or 3D UNet [166][167][168][169][170][171][172][173][174][175][176][177][178][179] that are able to process cube patches. Some research fuses features or results from multiple views (2.5D) or multiple 2D and 3D networks attempting to capture information from different angles and dimensionalities [180][181][182][183][184][185][186][187][188][189][190]. Although UNet is prevalent in the literature, different architectures originated from the field of natural imaging segmentation, such as SegNet, DeepLab and Region CNNs, are also employed.…”

Improved Complementary Pulmonary Nodule Segmentation Model Based on Multi-Feature Fusion

“…Shi et al [ 34 ] presented a lung nodule segmentation model multi-scale residual U-Net (MCA-ResUNet), which applies Atrous Spatial Pyramid Pooling (ASPP) as a bridging module and adds three adjacent smaller-scale guided Layer-crossed Context Attention (LCA) mechanisms. A semi-supervised three-view segmentation network with detection branches was proposed by Sun et al [ 35 ], but three parallel dilated convolutions for multi-scale feature extraction were performed in the detection and classification modules. Based on the encoder-decoder model, Wang et al [ 36 ] changed skip connections to multiple long and short skip connections.…”

HR-MPF: high-resolution representation network with multi-scale progressive fusion for pulmonary nodule segmentation and classification

“…Wang et al [11] adopted a 3D segmentation network for pulmonary nodules to obtain the three-dimensional global features of pulmonary nodules. Sun et al [12] and Dong et al [13] took the slices of different views in CT scans as input to realize multi-view collaborative learning.…”