Improving an Active Shape Model with Random Classification Forest for Segmentation of Cervical Vertebrae

Arif, Sheeraz; Gundry, Michael; Knapp, Karen; Slabaugh, Greg

doi:10.1007/978-3-319-55050-3_1

Cited by 15 publications

(11 citation statements)

References 19 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their DSCs are 0.774, 0.877, and 0.883. These results reveal that the performance of our proposed work is very close to the one in [24] and should be better than the abovementioned methods [21–23]. Additionally, the modifications of a U-Net such as Residual U-Net [24] and Dense U-Net architecture [25] were also applied to segment the thoracic and lumbar vertebra for comparison.…”

Section: Introductionmentioning

confidence: 52%

See 1 more Smart Citation

Cobb Angle Measurement of Spine from X-Ray Images Using Convolutional Neural Network

Horng

Kuok

et al. 2019

Computational and Mathematical Methods in Medicine

154

121

View full text Add to dashboard Cite

Scoliosis is a common spinal condition where the spine curves to the side and thus deforms the spine. Curvature estimation provides a powerful index to evaluate the deformation severity of scoliosis. In current clinical diagnosis, the standard curvature estimation method for assessing the curvature quantitatively is done by measuring the Cobb angle, which is the angle between two lines, drawn perpendicular to the upper endplate of the uppermost vertebra involved and the lower endplate of the lowest vertebra involved. However, manual measurement of spine curvature requires considerable time and effort, along with associated problems such as interobserver and intraobserver variations. In this article, we propose an automatic system for measuring spine curvature using the anterior-posterior (AP) view spinal X-ray images. Due to the characteristic of AP view images, we first reduced the image size and then used horizontal and vertical intensity projection histograms to define the region of interest of the spine which is then cropped for sequential processing. Next, the boundaries of the spine, the central spinal curve line, and the spine foreground are detected by using intensity and gradient information of the region of interest, and a progressive thresholding approach is then employed to detect the locations of the vertebrae. In order to reduce the influences of inconsistent intensity distribution of vertebrae in the spine AP image, we applied the deep learning convolutional neural network (CNN) approaches which include the U-Net, the Dense U-Net, and Residual U-Net, to segment the vertebrae. Finally, the segmentation results of the vertebrae are reconstructed into a complete segmented spine image, and the spine curvature is calculated based on the Cobb angle criterion. In the experiments, we showed the results for spine segmentation and spine curvature; the results were then compared to manual measurements by specialists. The segmentation results of the Residual U-Net were superior to the other two convolutional neural networks. The one-way ANOVA test also demonstrated that the three measurements including the manual records of two different physicians and our proposed measured record were not significantly different in terms of spine curvature measurement. Looking forward, the proposed system can be applied in clinical diagnosis to assist doctors for a better understanding of scoliosis severity and for clinical treatments.

show abstract

Section: Introductionmentioning

confidence: 52%

“…The authors modified the crop and copy operation into the concatenation operation that obtained an average Dice similarity coefficient (DSC) of 0.9438 for U-Net and 0.944 for shape-aware U-Net. The authors also compared with other methods such as ASM-G [21], ASM-M [22], and ASM-RF [23]. Their DSCs are 0.774, 0.877, and 0.883.…”

Section: Introductionmentioning

confidence: 99%

Cobb Angle Measurement of Spine from X-Ray Images Using Convolutional Neural Network

Horng

Kuok

et al. 2019

Computational and Mathematical Methods in Medicine

154

121

View full text Add to dashboard Cite

show abstract

“…We apply the proposed shape predictor network for segmentation of cervical vertebra in X-ray images where shape is of utmost importance and has constrained variation limits. Most of the work in vertebra segmentation involves shape prediction [10,11]. Given the fact that a vertebra in an X-ray image mostly consists of homogeneous and noisy image regions separated by edges, active shape model and level set-based methods can be used to evolve a shape to achieve a segmentation [1,2,12].…”

Section: Introductionmentioning

confidence: 99%

SPNet: Shape Prediction Using a Fully Convolutional Neural Network

Arif

Knapp

Slabaugh

2018

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

Self Cite

View full text Add to dashboard Cite

Shape has widely been used in medical image segmentation algorithms to constrain a segmented region to a class of learned shapes. Recent methods for object segmentation mostly use deep learning algorithms. The state-ofthe-art deep segmentation networks are trained with loss functions defined in a pixel-wise manner, which is not suitable for learning topological shape information and constraining segmentation results. In this paper, we propose a novel shape predictor network for object segmentation. The proposed deep fully convolutional neural network learns to predict shapes instead of learning pixel-wise classification. We apply the novel shape predictor network to X-ray images of cervical vertebra where shape is of utmost importance. The proposed network is trained with a novel loss function that computes the error in the shape domain. Experimental results demonstrate the effectiveness of the proposed method to achieve state-of-the-art segmentation, with correct topology and accurate fitting that matches expert segmentation.

show abstract

“…Segmenting the vertebrae correctly is a crucial part for further analysis in an injury detection system. Previous work in vertebrae segmentation has largely been dominated by statistical shape model (SSM) -based approaches [5][6][7][8][9][10][11][12]. These methods record statistical information about the shape and/or the appearance of the vertebrae based on a training set.…”

mentioning

confidence: 99%

“…Then the mean shape is initialized either manually or semi-automatically near the actual vertebra and a search procedure is performed to converge the shape on the actual vertebral boundary. Recent literature utilizes random forest -based machine learning models in order to achieve the shape convergence [9][10][11][12].However, to the best of our knowledge, a fully automatic method is absent from the literature. To fill this gap, in this work, we propose a fully automatic framework for vertebrae segmentation.…”

mentioning

confidence: 99%

Fully automatic cervical vertebrae segmentation framework for X-ray images

Arif

Knapp

Slabaugh

2018

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

The cervical spine is a highly flexible anatomy and therefore vulnerable to injuries. Unfortunately, a large number of injuries in lateral cervical X-ray images remain undiagnosed due to human errors. Computer-aided injury detection has the potential to reduce the risk of misdiagnosis. Towards building an automatic injury detection system, in this paper, we propose a deep learning-based fully automatic framework for segmentation of cervical vertebrae in X-ray images. The framework first localizes the spinal region in the image using a deep fully convolutional neural network. Then vertebra centers are localized using a novel deep probabilistic spatial regression network. Finally, a novel shape-aware deep segmentation network is used to segment the vertebrae in the image. The framework can take an X-ray image and produce a vertebrae segmentation result without any manual intervention. Each block of the fully automatic framework has been trained on a set of 124 X-ray images and tested on another 172 images, all collected from real-life hospital emergency rooms. A Dice similarity coefficient of 0.84 and a shape error of 1.69 mm have been achieved.

show abstract

Improving an Active Shape Model with Random Classification Forest for Segmentation of Cervical Vertebrae

Cited by 15 publications

References 19 publications

Cobb Angle Measurement of Spine from X-Ray Images Using Convolutional Neural Network

Cobb Angle Measurement of Spine from X-Ray Images Using Convolutional Neural Network

SPNet: Shape Prediction Using a Fully Convolutional Neural Network

Fully automatic cervical vertebrae segmentation framework for X-ray images

Contact Info

Product

Resources

About