Evaluation of a multi‐atlas based method for segmentation of cardiac CTA data: a large‐scale, multicenter, and multivendor study

Kirişli, Hortense A.; Schaap, Michiel; Klein, Stefan; Papadopoulou, Stella-Lida; Bonardi, Mara; Chen, C. H.; Weustink, Annick C.; Mollet, Nico R.; Vonken, Evert-Jan; Geest, Rob J. van der; Walsum, Theo van; Niessen, Wiro J.

doi:10.1118/1.3512795

Cited by 90 publications

(112 citation statements)

References 35 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…Any accurate automatic (e.g. Zheng et al (2008); Kirişli et al (2010);Xiong et al (2015)) or manual segmentation could be employed. In this work, LV myocardium segmentation was performed automatically, and in a limited number of images the obtained quantitative evaluation demonstrated high segmentation performance.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

Zreik

Leßmann

Hamersvelt

et al. 2018

Medical Image Analysis

166

124

View full text Add to dashboard Cite

In patients with coronary artery stenoses of intermediate severity, the functional significance needs to be determined. Fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA), is most often used in clinical practice. To reduce the number of ICA procedures, we present a method for automatic identification of patients with functionally significant coronary artery stenoses, employing deep learning analysis of the left ventricle (LV) myocardium in rest coronary CT angiography (CCTA).The study includes consecutively acquired CCTA scans of 166 patients who underwent invasive FFR measurements. To identify patients with a functionally significant coronary artery stenosis, analysis is performed in several stages. First, the LV myocardium is segmented using a multiscale convolutional neural network (CNN). To characterize the segmented LV myocardium, it is subsequently encoded using unsupervised convolutional autoencoder (CAE). As ischemic changes are expected to appear locally, the LV myocardium is divided into a number of spatially connected clusters, and statistics of the encodings are computed as features. Thereafter, patients are classified according to the presence of functionally significant stenosis using an SVM classifier based on the extracted features.Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coefficient of 0.91 and an average mean absolute distance between the segmented and reference LV boundaries of 0.7 mm. Twenty CCTA images were used to train the LV myocardium encoder. Classification of patients was evaluated in the remaining 126 CCTA scans in 50 10-fold cross-validation experiments and resulted in an area under the receiver operating characteristic curve of 0.74 ± 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding specificity was 0.77, 0.71 and 0.59, respectively.The results demonstrate that automatic analysis of the LV myocardium in a single CCTA scan acquired at rest, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally significant coronary artery stenosis. This might reduce the number of patients undergoing unnecessary invasive FFR measurements.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Marie-Pierre (2006); Zheng et al (2008); Xiong et al (2015)) and voxel-based segmentations (e.g. Kirişli et al (2010)). The advantage of boundary-based approaches is their ability to perform subvoxel analysis.…”

Section: Myocardium Segmentationmentioning

confidence: 99%

Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

Zreik

Leßmann

Hamersvelt

et al. 2018

Medical Image Analysis

166

124

View full text Add to dashboard Cite

show abstract

“…Moreover, (Zuluaga et al, 2013) presented an atlas-based technique with global and deformable alignment for LA segmentation only. Nevertheless, the current solutions show inaccurate results in thin septal walls (Zhuang et al, 2010) or present a total merge/overlap between atrial contours (Kirişli et al, 2010;Zuluaga et al, 2013). Specifically, the atlasbased technique with a final majority voting per chamber approach presented by (Kirişli et al, 2010) was unable to prevent overlap between contours.…”

Section: Introductionmentioning

confidence: 99%

“…Since the manual approach is tedious, time-consuming and has a high intra-and inter-observer variability, automated segmentation processes have been widely explored and increasingly accepted in normal clinical practice. The majority of the applied methods are based on deformable models (Ecabert et al, 2011), atlas-based techniques (Kirişli et al, 2010;Zuluaga et al, 2013) and machine learning (Zheng et al, 2008), proving its high accuracy in a high number of cases with different pathologies. Some studies focused only on the left atrium (LA) due to its importance for atrial fibrillation, using a simple initialization strategy through a multi-atlas to obtain a rough contour alignment (Sandoval et al, 2013) or a probabilistic atlas (Stender et al, 2013), followed by a region growing and multiple 2D individual segmentations with circular shape descriptors (Ammar et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

“…Automatic and semi-automatic atrial region segmentation solutions have been explored and presented for multiple imaging modalities, such as computed tomography (CT, (Ecabert et al, 2011;Kirişli et al, 2010;Zheng et al, 2008)) and magnetic resonance imaging (MRI, (Zuluaga et al, 2013)). Since the manual approach is tedious, time-consuming and has a high intra-and inter-observer variability, automated segmentation processes have been widely explored and increasingly accepted in normal clinical practice.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A competitive strategy for atrial and aortic tract segmentation based on deformable models

Morais

Vilaça

Queirós

et al. 2017

Medical Image Analysis

View full text Add to dashboard Cite

A competitive strategy for atrial and aortic tract segmentation based on deformable models AbstractMultiple strategies have previously been described for atrial region (i.e. atrial bodies and aortic tract) segmentation. Although these techniques have proven their accuracy, inadequate results in the mid atrial walls are common, restricting their application for specific cardiac interventions. In this work, we introduce a novel competitive strategy to perform atrial region segmentation with correct delineation of the thin mid walls, and integrated it into the B-spline Explicit Active Surfaces framework. A double-stage segmentation process is used, which starts with a fast contour growing followed by a refinement stage with local descriptors. Independent functions are used to define each region, being afterward combined to compete for the optimal boundary. The competition locally constrains the surface evolution, prevents overlaps and allows refinement to the walls. Three different scenarios were used to demonstrate the advantages of the proposed approach, through the evaluation of its segmentation accuracy, and its performance for heterogeneous mid walls. Both computed tomography and magnetic resonance imaging datasets were used, presenting results similar to the state-of-the-art methods for both atria and aorta. The competitive strategy showed its superior performance with statistically significant differences against the traditional freeevolution approach in cases with bad image quality or missed atrial/aortic walls. Moreover, only the competitive approach was able to accurately segment the atrial/aortic wall. Overall, the proposed strategy showed to be suitable for atrial region segmentation with a correct segmentation of the mid thin walls, demonstrating its added value with respect to the traditional techniques.

show abstract

Quantitative assessment of intra‐ and inter‐modality deformable image registration of the heart, left ventricle, and thoracic aorta on longitudinal 4D‐CT and MR images

Omidi

Weiss

Wilson

et al. 2021

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose Magnetic resonance imaging (MRI)‐based investigations into radiotherapy (RT)‐induced cardiotoxicity require reliable registrations of magnetic resonance (MR) imaging to planning computed tomography (CT) for correlation to regional dose. In this study, the accuracy of intra‐ and inter‐modality deformable image registration (DIR) of longitudinal four‐dimensional CT (4D‐CT) and MR images were evaluated for heart, left ventricle (LV), and thoracic aorta (TA). Methods and materials Non‐cardiac‐gated 4D‐CT and T1 volumetric interpolated breath‐hold examination (T1‐VIBE) MRI datasets from five lung cancer patients were obtained at two breathing phases (inspiration/expiration) and two time points (before treatment and 5 weeks after initiating RT). Heart, LV, and TA were manually contoured. Each organ underwent three intramodal DIRs ((A) CT modality over time, (B) MR modality over time, and (C) MR contrast effect at the same time) and two intermodal DIRs ((D) CT/MR multimodality at same time and (E) CT/MR multimodality over time). Hausdorff distance (HD), mean distance to agreement (MDA), and Dice were evaluated and assessed for compliance with American Association of Physicists in Medicine (AAPM) Task Group (TG)‐132 recommendations. Results Mean values of HD, MDA, and Dice under all registration scenarios for each region of interest ranged between 8.7 and 16.8 mm, 1.0 and 2.6 mm, and 0.85 and 0.95, respectively, and were within the TG‐132 recommended range (MDA < 3 mm, Dice > 0.8). Intramodal DIR showed slightly better results compared to intermodal DIR. Heart and TA demonstrated higher registration accuracy compared to LV for all scenarios except for HD and Dice values in Group A. Significant differences for each metric and tissue of interest were noted between Groups B and D and between Groups B and E. MDA and Dice significantly differed between LV and heart in all registrations except for MDA in Group E. Conclusions DIR of the heart, LV, and TA between non‐cardiac‐gated longitudinal 4D‐CT and MRI across two modalities, breathing phases, and pre/post‐contrast is acceptably accurate per AAPM TG‐132 guidelines. This study paves the way for future evaluation of RT‐induced cardiotoxicity and its related factors using multimodality DIR.

show abstract

Evaluation of a multi‐atlas based method for segmentation of cardiac CTA data: a large‐scale, multicenter, and multivendor study

Abstract: A fully automatic method for whole heart and cardiac chamber segmentation was presented and evaluated using multicenter/multivendor CTA data. The accuracy and robustness of the method were demonstrated by successfully applying the method to 1420 multicenter/ multivendor data sets.

Cited by 90 publications

References 35 publications

Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

A competitive strategy for atrial and aortic tract segmentation based on deformable models

Quantitative assessment of intra‐ and inter‐modality deformable image registration of the heart, left ventricle, and thoracic aorta on longitudinal 4D‐CT and MR images

Contact Info

Product

Resources

About