ML p(r)ior | Improving Vertebra Segmentation through Joint Vertebra-Rib Atlases

Improving Vertebra Segmentation through Joint Vertebra-Rib Atlases

2016-02-01
Accurate spine segmentation allows for improved identification and quantitative characterization of abnormalities of the vertebra, such as vertebral fractures. However, in existing automated vertebra segmentation methods on computed tomography (CT) images, leakage into nearby bones such as ribs occurs due to the close proximity of these visibly intense structures in a 3D CT volume. To reduce this error, we propose the use of joint vertebra-rib atlases to improve the segmentation of vertebrae via multi-atlas joint label fusion. Segmentation was performed and evaluated on CTs containing 106 thoracic and lumbar vertebrae from 10 pathological and traumatic spine patients on an individual vertebra level basis. Vertebra atlases produced errors where the segmentation leaked into the ribs. The use of joint vertebra-rib atlases produced a statistically significant increase in the Dice coefficient from 92.5 $\pm$ 3.1% to 93.8 $\pm$ 2.1% for the left and right transverse processes and a decrease in the mean and max surface distance from 0.75 $\pm$ 0.60mm and 8.63 $\pm$ 4.44mm to 0.30 $\pm$ 0.27mm and 3.65 $\pm$ 2.87mm, respectively.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2017-09-01

A cascade of fully convolutional neural networks is proposed to segment multi-modal Magnetic Resonan… show more
PDF

Highlights - Most important sentences from the article

2016-11-16

This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an… show more
PDF

Highlights - Most important sentences from the article

2018-02-14

White matter hyperintensities (WMH) are commonly found in the brains of healthy elderly individuals … show more
PDF

Highlights - Most important sentences from the article

2018-06-01

Whole brain segmentation on a structural magnetic resonance imaging (MRI) is essential in non-invasi… show more
PDF

Highlights - Most important sentences from the article

2018-01-03

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The cup to disc ratio (CDR… show more
PDF

Highlights - Most important sentences from the article

2019-03-28

Detailed whole brain segmentation is an essential quantitative technique, which provides a non-invas… show more
PDF

Highlights - Most important sentences from the article

2017-08-08

Semantic instance segmentation remains a challenging task. In this work we propose to tackle the pro… show more
PDF

Highlights - Most important sentences from the article

2016-12-12
1612.03925 | cs.CV

This study investigates a 3D and fully convolutional neural network (CNN) for subcortical brain stru… show more
PDF

Highlights - Most important sentences from the article

2018-07-27

Thalamic alterations are relevant to many neurological disorders including Alzheimer's disease, Park… show more
PDF

Highlights - Most important sentences from the article

2017-12-14

Precise 3D segmentation of infant brain tissues is an essential step towards comprehensive volumetri… show more
PDF

Highlights - Most important sentences from the article

2018-10-15

A key limitation of deep convolutional neural networks (DCNN) based image segmentation methods is th… show more
PDF

Highlights - Most important sentences from the article

2019-04-25

Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentat… show more
PDF

Highlights - Most important sentences from the article

2018-01-19

Accurate brain tissue segmentation in Magnetic Resonance Imaging (MRI) has attracted the attention o… show more
PDF

Highlights - Most important sentences from the article

2019-03-19

Image segmentation plays an essential role in medicine for both diagnostic and interventional tasks.… show more
PDF

Highlights - Most important sentences from the article

2019-03-26

It is usually hard for a learning system to predict correctly on rare events that never occur in the… show more
PDF