Automatic extraction of vertebral endplates from scoliotic radiographs using customized filter

Anitha, H; Karunakar, A. K.; Dinesh, K. V. N.

doi:10.1007/s13534-014-0129-z

Cited by 27 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In previous studies, the reliabilities of computer-aided methods [ 5 , 6 , 8 ] were less than 3° for the Cobb angle measurements. For the model radiographs, the results of the proposed method are comparable to those reported in previous studies (i.e., ≤3°).…”

Section: Resultsmentioning

confidence: 99%

“…They also investigated the applicability of their method to the X-ray image of a human spine, and they believed that their method could be a good solution for low-quality human X-ray images. Anitha et al [ 8 ] proposed an automated system that extracted vertebral endplates using a customized filter that combined anisotropic, sigmoid, and differential filters. Samuvel et al [ 9 ] proposed a mask-based segmentation algorithm for automatic Cobb angle measurement.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer-Aided Cobb Measurement Based on Automatic Detection of Vertebral Slopes Using Deep Neural Network

Zhang

et al. 2017

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

Objective To develop a computer-aided method that reduces the variability of Cobb angle measurement for scoliosis assessment. Methods A deep neural network (DNN) was trained with vertebral patches extracted from spinal model radiographs. The Cobb angle of the spinal curve was calculated automatically from the vertebral slopes predicted by the DNN. Sixty-five in vivo radiographs and 40 model radiographs were analyzed. An experienced surgeon performed manual measurements on the aforementioned radiographs. Two examiners used both the proposed and the manual measurement methods to analyze the aforementioned radiographs. Results For model radiographs, the intraclass correlation coefficients were greater than 0.98, and the mean absolute differences were less than 3°. This indicates that the proposed system showed high repeatability for measurements of model radiographs. For the in vivo radiographs, the reliabilities were lower than those from the model radiographs, and the differences between the computer-aided measurement and the manual measurement by the surgeon were higher than 5°. Conclusion The variability of Cobb angle measurements can be reduced if the DNN system is trained with enough vertebral patches. Training data of in vivo radiographs must be included to improve the performance of DNN. Significance Vertebral slopes can be predicted by DNN. The computer-aided system can be used to perform automatic measurements of Cobb angle, which is used to make reliable and objective assessments of scoliosis.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Computer-Aided Cobb Measurement Based on Automatic Detection of Vertebral Slopes Using Deep Neural Network

Zhang

et al. 2017

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

show abstract

“…In this case, the segmentation-based method cannot provide the slope of the vertebra since it requires highly accurate boundary segmentation. The segmentation-based methods require additional edge detection method such as hough transform [2], [3] to identify the vertebral endplates. On the other hand, the proposed method shown in Fig.…”

Section: G Comparison Between the Proposed Methods And Segmentation-bmentioning

confidence: 99%

“…These can be divided roughly into two categories: segmentation-based methods and direct estimation methods. Segmentation-based methods use an active contour model [1], customized filter [2], and charged-particle models [26] for vertebral segmentation to calculate the Cobb angle. Unfortunately, these methods are not robust because an accurate segmentation of the vertebra is extremely difficult owing to an unclear vertebral boundary in the radiographs.…”

Section: Introductionmentioning

confidence: 99%

Automation of Spine Curve Assessment in Frontal Radiographs Using Deep Learning of Vertebral-Tilt Vector

et al. 2020

View full text Add to dashboard Cite

In this paper, an automated and visually explainable system is proposed for a scoliosis assessment from spinal radiographs, which deals with the drawback of manual measurements, which are known to be time-consuming, cumbersome, and operator dependent. Deep learning techniques have been successfully applied in the accurate extraction of Cobb angle measurements, which is the gold standard for a scoliosis assessment. Such deep learning methods directly estimate the Cobb angle without providing structural information of the spine which can be used for diagnosis. Although conventional segmentation-based methods can provide the spine structure, they still have limitations in the accurate measurement of the Cobb angle. It would be desirable to build a clinician-friendly diagnostic system for scoliosis that provides not only an automated Cobb angle assessment but also local and global structural information of the spine. This paper addresses this need through the development of a hierarchical method which consisting of three major parts. (1) A confidence map is used to selectively localize and identify all vertebrae in an accurate and robust manner, (2) vertebral-tilt field is used to estimate the slope of an individual vertebra, and (3) the Cobb angle is determined by combining the vertebral centroids with the previously obtained vertebral-tilt field. The performance of the proposed method was validated, resulting in circular mean absolute error of 3.51 • and symmetric mean absolute percentage error of 7.84% for the Cobb angle.

show abstract

“…Alguns autores [27][28][29] descreveram metodologias utilizando computador e formulações geométricas sofisticadas para estimar a rotação vertebral a partir de imagens de raio X no plano frontal. Observa-se que a intenção é registrar o objeto de reconstrução (isto é, a coluna vertebral) por dois diferentes ângulos.…”

Section: Rotação Vertebralunclassified

Avaliação da curvatura escoliótica utilizando reconhecimento de padrões elípticos em imagens de raio X.

Coelho¹

View full text Add to dashboard Cite

Dedico este trabalho à minha companheira Karine Cristine de Almeida, que me apoiou em todos os momentos. AGRADECIMENTOS A Deus, por fazer tudo possível. À minha amada esposa Karine Cristine de Almeida, pelo amor, carinho, companheirismo e incentivo. À minha família, meu pai Jeová Coelho de Souza e minha mãe Alda Maria Barbosa Coelho pelo incentivo para sempre ir tocando em frente; meu irmão e minhas irmãs, meus sobrinhos que sempre me apoiaram. Meu sogro e sogra pela ajuda, acolhida, carinho e atenção. Ao meu orientador Prof. Dr. Paschoarelli, por acreditar em mim e pelo apoio. Ao meu co-orientador Prof. Dr. Alan Petrônio Pinheiro, pela amizade, pela luta, pelas conquistas e pelo companheirismo. Ao prof. Dr. Tomaz Vrtovec, que contribuiu no artigo publicado. Aos meus ex-alunos, alunos que me inspiraram e me fizeram crescer como profissional. A todos da Faculdade de Engenharia Elétrica da UFU que me deram suporte e apoio, em especial os meus colegas do Campus Patos de Minas. A todos que, direta ou indiretamente, contribuíram com este trabalho. "Sonho que se sonha só é só um sonho; sonho que se sonha junto é realidade". Raul Seixas RESUMO A escoliose é uma doença caracterizada pela deformação da coluna vertebral. Essa deformação é composta por uma curvatura lateral anormal e uma rotação axial de algumas vértebras. O método mais utilizado de medição do grau de escoliose é o ângulo de Cobb. Foram pesquisadas várias formas para se medir essa deformidade, assim como ângulos, afastamentos, áreas, raios de círculos e, por fim, elipses. Este trabalho propõe uma metodologia capaz de comparar a deformação da coluna com uma elipse, fornecendo, assim, parâmetros matemáticos e visuais suficientes para uma visão auxiliar sobre o grau de curvatura da coluna e sua progressão. Esta pesquisa utilizou uma técnica de algoritmo genético capaz de testar várias possibilidades de elipses candidatas ao "encaixe" ótimo da curvatura da coluna e, também, a determinação de parâmetros visuais e matemáticos que são compostos pelos parâmetros característicos da elipse que formam um índice capaz de fornecer uma visão geral da deformidade. Os resultados desta pesquisa apontam que a técnica proposta é capaz de reconhecer, com exatidão, os padrões elípticos em diferentes tipos (e graus) de colunas com escoliose a partir de imagens de raio X. Palavras-chave: Encaixe de elipse. Algoritmo genético. Vértebras. Escoliose. Reconhecimento de padrões. Processamento digital de imagem.

show abstract

Automatic extraction of vertebral endplates from scoliotic radiographs using customized filter

Cited by 27 publications

References 11 publications

Computer-Aided Cobb Measurement Based on Automatic Detection of Vertebral Slopes Using Deep Neural Network

Computer-Aided Cobb Measurement Based on Automatic Detection of Vertebral Slopes Using Deep Neural Network

Automation of Spine Curve Assessment in Frontal Radiographs Using Deep Learning of Vertebral-Tilt Vector

Avaliação da curvatura escoliótica utilizando reconhecimento de padrões elípticos em imagens de raio X.

Contact Info

Product

Resources

About