Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection

Zhuang, Xiahai; Bai, Wenjia; Jin, Zhen; Zhan, Songhua; Qian, Xiaohua; Shi, Wenzhe; Lian, Yanyun; Rueckert, Daniel

doi:10.1118/1.4921366

Cited by 75 publications

(52 citation statements)

References 44 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inconsistency between results for coronary CTA and CT PET is also clearly demonstrated by the Box-and-Whisker plots in Figure 4. Compared to the segmentation results from Kirisli et al 27 and Zhuang et al, 30 the results in this article are satisfactory.…”

Section: Resultssupporting

confidence: 51%

3D Fusion Framework for Infarction and Angiogenesis Analysis in a Myocardial Infarct Minipig Model

Tao

Liu

et al. 2017

Mol Imaging

View full text Add to dashboard Cite

The combination of different modality images can provide detailed and comprehensive information for the prognostic assessment and therapeutic strategy of patients with ischemic heart disease. In this study, a 3D fusion framework is designed to integrate coronary computed tomography (CT) angiography (CTA), 2-deoxy-2-[18F]fluoro-D-glucose ([18F]DG) positron emission tomography (PET)/CT, and [68Ga]-1,4,7-triazacyclononane-1,4,7-triacetic acid-(Arg-Gly-Asp)2 ([68Ga]-NOTA-PRGD2) PET/CT images of the myocardial infarction model in minipigs. First, the structural anatomy of the heart in coronary CTA and CT is segmented using a multi-atlas-based method. Then, the hearts are registered using the B-spline-based free form deformation. Finally, the [18F]DG and [68Ga]-NOTA-PRGD2 signals are mapped into the heart in coronary CTA, which produces a single fusion image to delineate both the cardiac structural anatomy and the functional information of myocardial viability and angiogenesis. Heart segmentation demonstrates high accuracy with good agreement between manual delineation and automatic segmentation. The fusion result intuitively reflects the extent of the [18F]DG uptake defect as well as the location where the [68Ga]-NOTA-PRGD2 signal appears. The fusion result verified the occurrence of angiogenesis based on the in vivo noninvasive molecular imaging approach. The presented framework is helpful in facilitating the study of the relationship between infarct territories and blocked coronary arteries as well as angiogenesis.

show abstract

Section: Resultssupporting

confidence: 51%

3D Fusion Framework for Infarction and Angiogenesis Analysis in a Myocardial Infarct Minipig Model

Tao

Liu

et al. 2017

Mol Imaging

View full text Add to dashboard Cite

show abstract

“…In our study, all images had slice spacing of 2.5 mm, which may limit distance-based assessment. By considering the limitation of image resolution, our auto-segmentation approach is comparable to state-of-the-art cardiac segmentation methods [29–31], which were applied to contrast CT images with sub-millimeter resolution for diagnosis of cardiovascular diseases. On the other hand, this showed that the atlases we developed are useful for auto-contouring the cardiac substructures.…”

Section: Discussionmentioning

confidence: 99%

Cardiac atlas development and validation for automatic segmentation of cardiac substructures

Zhou

Liao

Pan

et al. 2017

Radiotherapy and Oncology

View full text Add to dashboard Cite

Purpose To develop and validate a set of atlases for auto-contouring cardiac substructures. Methods Eight radiation oncologists manually and independently delineated 15 cardiac substructures from noncontrast CT images of 6 patients by referring to their respective fused contrast CT images. Individual contours were fused together for each structure, edited by 2 physicians, and became atlases to delineate other 6 patients. The auto-delineated contours of the 6 additional patients became templates for manual contouring. These 12 patients with well-defined contours composed the final atlases for multi-atlas segmentation. Results The average time for manually contouring the 15 cardiac substructures was about 40 minutes. Inter-observer variability was small for the heart, the chambers, and the aorta compared with that for other structures that were not clearly distinguishable in CT images. The mean Dice similarity coefficient and mean surface distance of auto-segmented contours were within one standard deviation of expert contouring variability. Good agreement between auto-segmented and manual contours was observed for the heart, the chambers, and the great vessels. Independent validation on other 19 patients showed reasonable agreement for the heart chambers. Conclusions A set of cardiac atlases was created for auto-contouring from noncontrast CT images. The accuracy of auto-contouring for the heart, chambers, and great vessels was validated for potential clinical use.

show abstract

“…With both approaches, considerable research effort has been directed toward the construction of brain atlases . A variety of methods have been also proposed for the segmentation of other organs or anatomical structures by means of atlases . However, the number of studies related to the construction of spinal atlases is limited and some of them are centred on structures like the intervertebral discs or the spinal canal .…”

Section: Introductionmentioning

confidence: 99%

“…35 A variety of methods have been also proposed for the segmentation of other organs or anatomical structures by means of atlases. [36][37][38][39][40][41][42] However, the number of studies related to the construction of spinal atlases is limited and some of them are centred on structures like the intervertebral discs 43 or the spinal canal. 44,45 Regarding vertebrae, Hardisty et al 46 presented an algorithm to perform the segmentation of tumorinvolved vertebrae using demons deformable image registration and level set methods.…”

Section: Introductionmentioning

confidence: 99%

Automatic segmentation of the spine by means of a probabilistic atlas with a special focus on ribs suppression

et al. 2017

View full text Add to dashboard Cite

show abstract

Multiatlas whole heart segmentation of CT data using conditional entropy for atlas ranking and selection

Cited by 75 publications

References 44 publications

3D Fusion Framework for Infarction and Angiogenesis Analysis in a Myocardial Infarct Minipig Model

3D Fusion Framework for Infarction and Angiogenesis Analysis in a Myocardial Infarct Minipig Model

Cardiac atlas development and validation for automatic segmentation of cardiac substructures

Automatic segmentation of the spine by means of a probabilistic atlas with a special focus on ribs suppression

Contact Info

Product

Resources

About