Automatic spinal cord segmentation from axial-view MRI slices using CNN with grayscale regularized active contour propagation

Zhang, Xiaoran; Li, Yan; Liu, Yicun; Liu, Xiaoguang; Punithakumar, Kumaradevan; Shi, Dawei

doi:10.1016/j.compbiomed.2021.104345

Cited by 9 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One is to design special network structures that emphasize geometric information. Zhang et al 28 proposed edge-attention guidance network. Specifically, the edge guidance module is used to learn the edge attention representation of the early coding layer, and then it is transferred to the multiscale decoding layer and fused by the weighted aggregation module.…”

Section: Medical Image Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

MsgeCNN: Multiscale geometric embedded convolutional neural network for ONFH segmentation and grading

Tong

et al. 2023

Medical Physics

View full text Add to dashboard Cite

Background:The incidence of osteonecrosis of the femoral head (ONFH) is increasing gradually, rapid and accurate grading of ONFH is critical. The existing Steinberg staging criteria grades ONFH according to the proportion of necrosis area to femoral head area. Purpose: In the clinical practice, the necrosis region and femoral head region are mainly estimated by the observation and experience of doctor. This paper proposes a two-stage segmentation and grading framework, which can be used to segment the femoral head and necrosis, as well as to diagnosis. Methods: The core of the proposed two-stage framework is the multiscale geometric embedded convolutional neural network (MsgeCNN), which integrates geometric information into the training process and accurately segments the femoral head region. Then, the necrosis regions are segmented by the adaptive threshold method taking femoral head as the background. The area and proportion of the two are calculated to determine the grade. Results:The accuracy of the proposed MsgeCNN for femoral head segmentation is 97.73%, sensitivity is 91.17%, specificity is 99.40%, dice score is 93.34%. And the segmentation performance is better than the existing five segmentation algorithms. The diagnostic accuracy of the overall framework is 90.80%. Conclusions: The proposed framework can accurately segment the femoral head region and the necrosis region. The area, proportion, and other pathological information of the framework output provide auxiliary strategies for subsequent clinical treatment.

show abstract

Section: Medical Image Segmentationmentioning

confidence: 99%

“…One is to design special network structures that emphasize geometric information. Zhang et al 28 . proposed edge‐attention guidance network.…”

Section: Related Workmentioning

confidence: 99%

MsgeCNN: Multiscale geometric embedded convolutional neural network for ONFH segmentation and grading

Tong

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Different approaches have been proposed in the literature to address these challenges. Some of the commonly used segmentation techniques are atlas-based segmentation [ 3 ], region-based segmentation [ 4 ], and active contour-based segmentation [ 5 ]. A spine segmentation procedure that creates anatomically correct 3D models can be hindered by certain factors such as the anatomic complexity of the spine, image noise, low intensity, and the partial volume effect [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

An Automated Deep Learning Approach for Spine Segmentation and Vertebrae Recognition Using Computed Tomography Images

Saeed,

Dikaios,

Dastgir

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Spine image analysis is based on the accurate segmentation and vertebrae recognition of the spine. Several deep learning models have been proposed for spine segmentation and vertebrae recognition, but they are very computationally demanding. In this research, a novel deep learning model is introduced for spine segmentation and vertebrae recognition using CT images. The proposed model works in two steps: (1) A cascaded hierarchical atrous spatial pyramid pooling residual attention U-Net (CHASPPRAU-Net), which is a modified version of U-Net, is used for the segmentation of the spine. Cascaded spatial pyramid pooling layers, along with residual blocks, are used for feature extraction, while the attention module is used for focusing on regions of interest. (2) A 3D mobile residual U-Net (MRU-Net) is used for vertebrae recognition. MobileNetv2 includes residual and attention modules to accurately extract features from the axial, sagittal, and coronal views of 3D spine images. The features from these three views are concatenated to form a 3D feature map. After that, a 3D deep learning model is used for vertebrae recognition. The VerSe 20 and VerSe 19 datasets were used to validate the proposed model. The model achieved more accurate results in spine segmentation and vertebrae recognition than the state-of-the-art methods.

show abstract

Incremental Learning Meets Transfer Learning: Application to Multi-site Prostate MRI Segmentation

You

Xiang

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Automatic spinal cord segmentation from axial-view MRI slices using CNN with grayscale regularized active contour propagation

Cited by 9 publications

References 30 publications

MsgeCNN: Multiscale geometric embedded convolutional neural network for ONFH segmentation and grading

MsgeCNN: Multiscale geometric embedded convolutional neural network for ONFH segmentation and grading

An Automated Deep Learning Approach for Spine Segmentation and Vertebrae Recognition Using Computed Tomography Images

Incremental Learning Meets Transfer Learning: Application to Multi-site Prostate MRI Segmentation

Contact Info

Product

Resources

About