Verte-Box: A Novel Convolutional Neural Network for Fully Automatic Segmentation of Vertebrae in CT Image

Due to the complex shape of the vertebrae and the background containing a lot of interference information, it is difficult to accurately segment the vertebrae from the computed tomography (CT) volume by manual segmentation. This paper proposes a convolutional neural network for vertebrae segmentatio...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Tomography (Ann Arbor) Ročník 8; číslo 1; s. 45 - 58
Hlavní autori:	Li, Bing, Liu, Chuang, Wu, Shaoyong, Li, Guangqing
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Switzerland MDPI 01.01.2022 MDPI AG
Predmet:	Algorithms convolutional neural network CT image feature enhancement Image Processing, Computer-Assisted - methods multi-scale Neural Networks, Computer Spine - diagnostic imaging Tomography, X-Ray Computed vertebrae segmentation feature enhancement CT image multi-scale convolutional neural network vertebrae segmentation
ISSN:	2379-139X, 2379-1381, 2379-139X
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Due to the complex shape of the vertebrae and the background containing a lot of interference information, it is difficult to accurately segment the vertebrae from the computed tomography (CT) volume by manual segmentation. This paper proposes a convolutional neural network for vertebrae segmentation, named Verte-Box. Firstly, in order to enhance feature representation and suppress interference information, this paper places a robust attention mechanism on the central processing unit, including a channel attention module and a dual attention module. The channel attention module is used to explore and emphasize the interdependence between channel graphs of low-level features. The dual attention module is used to enhance features along the location and channel dimensions. Secondly, we design a multi-scale convolution block to the network, which can make full use of different combinations of receptive field sizes and significantly improve the network’s perception of the shape and size of the vertebrae. In addition, we connect the rough segmentation prediction maps generated by each feature in the feature box to generate the final fine prediction result. Therefore, the deep supervision network can effectively capture vertebrae information. We evaluated our method on the publicly available dataset of the CSI 2014 Vertebral Segmentation Challenge and achieved a mean Dice similarity coefficient of 92.18 ± 0.45%, an intersection over union of 87.29 ± 0.58%, and a 95% Hausdorff distance of 7.7107 ± 0.5958, outperforming other algorithms.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	2379-139X 2379-1381 2379-139X
DOI:	10.3390/tomography8010005