Lung 4D CT Image Registration Based on High-Order Markov Random Field

Xue, Peng; Dong, Enqing; Ji, Huizhong

doi:10.1109/tmi.2019.2937458

Cited by 19 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results in Table 3 demonstrate that the CAM can not only suppress the irrelevant background region and pay attention to the ROI but also deal with the lack of non-linear ability caused by the skipconnection directly. Compared with the supervised registration method which employs post-processing 40 to cope with the unrealistic folding problem of the DVF, the DAU-Net utilizes an objective function with folding penalty regularization term to promote the smoothness of the DVF is efficient. By promoting the smoothness of the DVF, the reliability of the registration results is improved.…”

Section: Discussionmentioning

confidence: 99%

“…Compared with the supervised registration method which employs post‐processing 40 to cope with the unrealistic folding problem of the DVF, the DAU‐Net utilizes an objective function with folding penalty regularization term to promote the smoothness of the DVF is efficient. By promoting the smoothness of the DVF, the reliability of the registration results is improved.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

DAU‐Net: An unsupervised 3D brain MRI registration model with dual‐attention mechanism

Bai

Cui

Gong

et al. 2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Medical image registration plays an important role in clinical treatment. However, the convolution-based registration frameworks fail to address the local excessive deformation between images. Furthermore, the folding point in the displacement vector field (DVF) reduces the reliability of registration results.In this study, we propose a dual-attention mechanism-based U-shaped registration framework (dubbed DAU-Net). Firstly, the multi-scale attention mechanism is introduced to extract the long-range dependence to deal with the local excessive deformation. Then, the channel attention mechanism is proposed to enhance the information fusion between channels, which not only fuses the features between different layers in the dual-attention network but also improves the non-linear mapping ability of the registration network. In the end, the objective function with the folding penalty regularization term is designed to improve the smoothness of the DVF. The model is evaluated on LPBA40 and Mindboggle101 open datasets. The registration accuracy in LPBA40 and Mindboggle101 datasets has been increased by 2.9% and 3.1%, respectively, while the folding rate is reduced by nearly 40 times compared with VoxelMorph. Combined multi-scale attention mechanism with channel attention mechanism, the registration accuracy of DAU-Net is improved. By utilizing the folding penalty regularization term, the folding rate is decreased significantly.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

DAU‐Net: An unsupervised 3D brain MRI registration model with dual‐attention mechanism

Bai

Cui

Gong

et al. 2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Image registration is the procedure that pursues to spatially align a set of images for subsequent processing. Many applications rely on an accurate registration procedure (see, for instance, [1,2] and references therein). Image registration methods may also be applied for motion estimation in dynamic images, where the goal is to quantify the function of moving organs or the elasticity of vessels [3],…”

Section: Introductionmentioning

confidence: 99%

Fast 4D elastic group-wise image registration. Convolutional interpolation revisited

Menchón-Lara

Royuela-del-Val²,

Simmross-Wattenberg

et al. 2021

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

“…In the past few decades, machine learning methods [3][4][5][6][7][8][9][10] have been widely used in the field of medical imaging and researchers proposed a variety of computer-aided diagnosis (CAD) methods [8][9][10] to characterize pulmonary nodules as benign or malignant with the help of artificial intelligence technology. Early studies mainly focused on utilizing the analysis of texture features, such as the Haralick texture features, 11 local binary model features, 12 Gabor features, 13 and so on, to classify the pulmonary nodules.…”

Section: Introductionmentioning

confidence: 99%

3D multi‐resolution deep learning model for diagnosis of multiple pathological types on pulmonary nodules

Xue

Zhao

et al. 2021

Int J Imaging Syst Tech

Self Cite

View full text Add to dashboard Cite

To accurately diagnose multiple pathological types of pulmonary nodules based on lung computed tomography (CT) images, a multi‐resolution three‐dimensional (3D) multi‐classification deep learning model (Mr‐Mc) was proposed. The Mr‐Mc model was constructed by using our own constructed lung CT image dataset of pulmonary nodules with clinical pathological information (LCID‐CPI), which can accurately diagnose inflammation, squamous cell carcinoma, adenocarcinoma, and other benign diseases. In order to process nodules with different sizes, a multi‐resolution extraction method was proposed to extract 3D volume data with different resolutions from lung CT images. The Mr‐Mc was composed of three different resolution networks, each of which has input volume data of a specific resolution. Experiments showed that the constructed Mr‐Mc model can achieve an average accuracy of 0.81 on LCID‐CPI. Besides, the Mr‐Mc model can also achieve a high accuracy of 0.87 on the Lung Image Database Consortium and Image Database Resource Initiative dataset.

show abstract

Lung 4D CT Image Registration Based on High-Order Markov Random Field

Cited by 19 publications

References 39 publications

DAU‐Net: An unsupervised 3D brain MRI registration model with dual‐attention mechanism

DAU‐Net: An unsupervised 3D brain MRI registration model with dual‐attention mechanism

Fast 4D elastic group-wise image registration. Convolutional interpolation revisited

3D multi‐resolution deep learning model for diagnosis of multiple pathological types on pulmonary nodules

Contact Info

Product

Resources

About