Automatic Segmentation of the Body and the Spinal Canal in CT Images Based on A Priori Information

Huang, Shanqing; Jia, Jing; Cao, Ruifen; Gui, Li; Cheng, Ming; Wu, Yican

doi:10.1109/icbbe.2011.5780349

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Subsequently, the CT table was removed from the scan, using a similar approach as proposed by Zhu et al . and the body outline of the patient was identified using a thresholding approach (threshold: −250 HU), as proposed by Huang et al . This allowed the removal of image artifacts present outside the patient's body.…”

Section: Methodsmentioning

confidence: 99%

Automated patient‐specific transperineal ultrasound probe setups for prostate cancer patients undergoing radiotherapy

et al. 2018

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Automated patient‐specific transperineal ultrasound probe setups for prostate cancer patients undergoing radiotherapy

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The spinal canal is a tube formed by a series of vertebral foramina of all vertebrae, which contains the spinal cord, nerves, blood vessels, etc. The spinal cord is the main channel for transmitting information between the brain and peripheral nerves [1]. Laminectomy is performed using bone drilling to remove the spinous process to expand the space of the spinal canal, release the oppressed nerves and spinal cord, and restore its normal function [2].…”

Section: Introductionmentioning

confidence: 99%

Research on Spinal Canal Generation Method based on Vertebral Foramina Inpainting of Spinal CT Images by using BEGAN

Ding¹,

Sun²,

Li³

et al. 2020

jist

View full text Add to dashboard Cite

Abstract Spinal surgery is of high risk due to the possibility of neurologic damage, which may cause life-threatening sequelae. Although the emerging robotic-assisted spinal surgery provides better accuracy compared with traditional surgery, the construction of boundary constraints around the spinal canal for safety in surgery is still required. The establishment of a three-dimensional (3D) model of the spinal canal during preoperative preparation can facilitate the generation of surgical boundary constraints. This article presents a novel framework for spinal canal generation based on spinal CT image inpainting by using the boundary equilibrium generative adversarial network (BEGAN). First, U-net is used to simplify the image features and then ResNet50 is applied to classify the vertebral foramen features and mark the area to be restored. Finally, BEGAN generates the target features to complete the vertebral foramina inpainting for the generation of the spinal canal. The experimental results show that the average accuracies (Mean Intersection over Union) of the vertebral foramina and spine inpainting are 0.9396 and 0.9332, respectively, and the accuracy of image inpainting decreases with increase in the inpainting area. The proposed method can accurately generate the vertebral contours and complete the 3D reconstruction of the spinal canal.

show abstract

“…Em modelos paramétricos de segmentação é assumido anteriormente uma distribuição de tons de cinza da imagem cujos parâmetros controlam um ajuste da imagem (HUANG;LIN;HU, 2011). Já modelos não-paramétricos maximizam uma função objetiva, seja ela a variância entre classes ou a entropia (Silvano Di Zenzo et.…”

Section: Filtro Múltiplo De Otsuunclassified

Construção de modelos geométricos quadráticos específicos a partir de imagens de tomografia computadorizada para aplicações em simulações Monte Carlo visando o planejamento radioterápico

Scatena

View full text Add to dashboard Cite

A simulação de Monte Carlo é o algoritmo computacional de referência para o transporte de radiação no contexto da radioterapia. Embora o algoritmo de Monte Carlo seja muito lento para ser usado no ambiente clínico, nós o aceleramos usando um código híbrido personalizado de CPU e GPU chamado PaRtIcle-matter SiMulATIon Cuda (PRISMMATIC) baseado no PENELOPE. O objetivo principal desta pesquisa foi construir uma geometria quadrática torácica de voxels específica para pacientes com câncer de pulmão construída utilizando segmentação automática a partir de imagens de tomografia computadorizada. Métodos simples de processamento de imagem foram utilizados para segmentação. As regiões delimitadas por voxels foram simplificadas e convertidas automaticamente em geometrias quadráticas compatíveis com os softwares Monte Carlo PENELOPE e PRIS-MATIC. Foram feitas simulações de tratamentos de câncer de pulmão com o software PENELOPE e pelo PRISMATIC. Foram calculadas as doses integrais nos órgãos de risco e as restrições de doses sobre volume foram computadas pelo software SLIICER-RT. Os resultados mostraram que é possível obter mapas de doses precisamente compatíveis entre CPU e GPU com aceleração de 3,86 x para o cenário de radiocirurgia e 4,11 x no cenário do acelerador True Beam. Os resultados obtidos permitem prever a viabilidade da simulação Monte Carlo no cenário clínico usando modelos geométricos específicos para o paciente em tempo clinicamente aceitável.

show abstract

Automatic Segmentation of the Body and the Spinal Canal in CT Images Based on A Priori Information

Cited by 4 publications

References 21 publications

Automated patient‐specific transperineal ultrasound probe setups for prostate cancer patients undergoing radiotherapy

Automated patient‐specific transperineal ultrasound probe setups for prostate cancer patients undergoing radiotherapy

Research on Spinal Canal Generation Method based on Vertebral Foramina Inpainting of Spinal CT Images by using BEGAN

Construção de modelos geométricos quadráticos específicos a partir de imagens de tomografia computadorizada para aplicações em simulações Monte Carlo visando o planejamento radioterápico

Contact Info

Product

Resources

About

Automatic Segmentation of the Body and the Spinal Canal in CT Images Based on A Priori Information

Cited by 4 publications

References 21 publications

Automated patient‐specific transperineal ultrasound probe setups for prostate cancer patients undergoing radiotherapy

Automated patient‐specific transperineal ultrasound probe setups for prostate cancer patients undergoing radiotherapy

Research on Spinal Canal Generation Method based on Vertebral Foramina Inpainting of Spinal CT Images by using&#xA0;BEGAN

Construção de modelos geométricos quadráticos específicos a partir de imagens de tomografia computadorizada para aplicações em simulações Monte Carlo visando o planejamento radioterápico

Contact Info

Product

Resources

About

Research on Spinal Canal Generation Method based on Vertebral Foramina Inpainting of Spinal CT Images by using BEGAN