Publication detail

Learning–based vertebra localization and labeling in 3D CT data of possibly incomplete and pathological spines

JAKUBÍČEK, R. CHMELÍK, J. JAN, J. OUŘEDNÍČEK, P. LAMBERT, L. GAVELLI, G.

Original Title

Learning–based vertebra localization and labeling in 3D CT data of possibly incomplete and pathological spines

English Title

Learning–based vertebra localization and labeling in 3D CT data of possibly incomplete and pathological spines

Type

journal article

Language

en

Original Abstract

Background and objective We present a fully automatic system based on learning approaches, which aims to localization and identification (labeling) of vertebrae in 3D computed tomography (CT) scans of possibly incomplete spines in patients with bone metastases and vertebral compressions. Methods The framework combines a set of 3D algorithms for i) spine detection using a convolution neural network (CNN) ii) spinal cord tracking based on combination of a CNN and a novel growing sphere method with a population optimization, iii) intervertebral discs localization using a novel approach of spatially variant filtering of intensity profiles and iv) vertebra labeling using a CNN-based classification combined with global dynamic optimization. Results The proposed algorithm has been validated in testing databases, including also a publicly available dataset. The mean error of intervertebral discs localization is 4.4 mm, and for vertebra labeling, the average rate of correctly identified vertebrae is 87.1%, which can be considered a good result with respect to the large share of highly distorted spines and incomplete spine scans. Conclusions The proposed framework, which combines several advanced methods including also three CNNs, works fully automatically even with incomplete spine scans and with distorted pathological cases. The achieved results allow including the presented algorithms as the first phase to the fully automated computer-aided diagnosis (CAD) system for automatic spine-bone lesion analysis in oncological patients.

English abstract

Background and objective We present a fully automatic system based on learning approaches, which aims to localization and identification (labeling) of vertebrae in 3D computed tomography (CT) scans of possibly incomplete spines in patients with bone metastases and vertebral compressions. Methods The framework combines a set of 3D algorithms for i) spine detection using a convolution neural network (CNN) ii) spinal cord tracking based on combination of a CNN and a novel growing sphere method with a population optimization, iii) intervertebral discs localization using a novel approach of spatially variant filtering of intensity profiles and iv) vertebra labeling using a CNN-based classification combined with global dynamic optimization. Results The proposed algorithm has been validated in testing databases, including also a publicly available dataset. The mean error of intervertebral discs localization is 4.4 mm, and for vertebra labeling, the average rate of correctly identified vertebrae is 87.1%, which can be considered a good result with respect to the large share of highly distorted spines and incomplete spine scans. Conclusions The proposed framework, which combines several advanced methods including also three CNNs, works fully automatically even with incomplete spine scans and with distorted pathological cases. The achieved results allow including the presented algorithms as the first phase to the fully automated computer-aided diagnosis (CAD) system for automatic spine-bone lesion analysis in oncological patients.

Keywords

Vertebra detection; Learning-based approach; Convolution neural network; Pathological vertebrae

Released

24.09.2019

Publisher

Elsevier B.V.

Location

Amsterdam, The Netherlands

Pages from

1

Pages to

9

Pages count

9

URL

BibTex


@article{BUT159177,
  author="Roman {Jakubíček} and Jiří {Chmelík} and Jiří {Jan} and Petr {Ouředníček} and Lukáš {Lambert} and Giampaolo {Gavelli}",
  title="Learning–based vertebra localization and labeling in 3D CT data of possibly incomplete and pathological spines",
  annote="Background and objective
We present a fully automatic system based on learning approaches, which aims to localization and identification (labeling) of vertebrae in 3D computed tomography (CT) scans of possibly incomplete spines in patients with bone metastases and vertebral compressions.

Methods
The framework combines a set of 3D algorithms for i) spine detection using a convolution neural network (CNN) ii) spinal cord tracking based on combination of a CNN and a novel growing sphere method with a population optimization, iii) intervertebral discs localization using a novel approach of spatially variant filtering of intensity profiles and iv) vertebra labeling using a CNN-based classification combined with global dynamic optimization.

Results
The proposed algorithm has been validated in testing databases, including also a publicly available dataset. The mean error of intervertebral discs localization is 4.4 mm, and for vertebra labeling, the average rate of correctly identified vertebrae is 87.1%, which can be considered a good result with respect to the large share of highly distorted spines and incomplete spine scans.

Conclusions
The proposed framework, which combines several advanced methods including also three CNNs, works fully automatically even with incomplete spine scans and with distorted pathological cases. The achieved results allow including the presented algorithms as the first phase to the fully automated computer-aided diagnosis (CAD) system for automatic spine-bone lesion analysis in oncological patients.",
  address="Elsevier B.V.",
  chapter="159177",
  doi="10.1016/j.cmpb.2019.105081",
  howpublished="online",
  institution="Elsevier B.V.",
  number="105081",
  volume="183",
  year="2019",
  month="september",
  pages="1--9",
  publisher="Elsevier B.V.",
  type="journal article"
}