Dual-branch residual network for lung nodule segmentation

Cao, Haichao; Liu, Hong; Hung, Chih‐Cheng; Ma, Guangzhi; Xu, Xiangyang; Jin, Renchao; Lü, Jianguo

doi:10.1016/j.asoc.2019.105934

Cited by 111 publications

(64 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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.…”

Section: Resultsmentioning

confidence: 99%

“…However, due to the fact that CT images are originally three-dimensional, the down-sampling and subsequent up-sampling causes spatial information to be lost. Variations of CNN, such as the central focused convolutional neural network (CF-CNN) proposed by Wang et al [ 28 ], and the dual-branch residual network (DBResNet) for lung nodule segmentation proposed by Cao et al [ 29 ], have achieved competitive performance. By targeting pure GGO nodules specifically, Qi et al [ 30 ] performed segmentation on initial and follow-up CT scans using a CAD system based on CCN, and subsequently measuring and analyzing the nodules to determine growth and risk factors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lung Nodule Segmentation with a Region-Based Fast Marching Method

Savić

Ramponi

et al. 2021

Sensors

View full text Add to dashboard Cite

When dealing with computed tomography volume data, the accurate segmentation of lung nodules is of great importance to lung cancer analysis and diagnosis, being a vital part of computer-aided diagnosis systems. However, due to the variety of lung nodules and the similarity of visual characteristics for nodules and their surroundings, robust segmentation of nodules becomes a challenging problem. A segmentation algorithm based on the fast marching method is proposed that separates the image into regions with similar features, which are then merged by combining regions growing with k-means. An evaluation was performed with two distinct methods (objective and subjective) that were applied on two different datasets, containing simulation data generated for this study and real patient data, respectively. The objective experimental results show that the proposed technique can accurately segment nodules, especially in solid cases, given the mean Dice scores of 0.933 and 0.901 for round and irregular nodules. For non-solid and cavitary nodules the performance dropped—0.799 and 0.614 mean Dice scores, respectively. The proposed method was compared to active contour models and to two modern deep learning networks. It reached better overall accuracy than active contour models, having comparable results to DBResNet but lesser accuracy than 3D-UNet. The results show promise for the proposed method in computer-aided diagnosis applications.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Lung Nodule Segmentation with a Region-Based Fast Marching Method

Savić

Ramponi

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…where L cls represents the loss function of the classification network. The cross-entropy loss is selected and improved for the nodules' binary classification problem as shown in (5).…”

Section: Improved Hybrid Lossmentioning

confidence: 99%

“…Liu et al [4] combined superpixel and random forest algorithm to detect the subdivision of features through multi-scale edges, which achieved an accuracy of 92% in 2019. Cao et al [5] designed a weighted strategy for…”

Section: Introductionmentioning

confidence: 99%

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

Sun

Lei²,

He³

2020

IEEE Access

View full text Add to dashboard Cite

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.

show abstract

“…Marcin et al uses local variance and probabilistic neural networks to complete the detection of lung nodules, and achieves a high accuracy [14]. Cao et al propose a Dual-branch Residual Network (DB-ResNet) to segment lung nodules, which can effectively capture multi-view and multi-scale features of different nodules in CT images [15]. Ilaria used a 3d convolutional neural network to assess nodule malignancy and integrated it in an automated end-to-end existing pipeline of lung cancer detection [16].…”

Section: Introductionmentioning

confidence: 99%