Strengths and Pitfalls of Whole-Heart Atlas-Based Segmentation in Congenital Heart Disease Patients

Zuluaga, María A.; Biffi, Benedetta; Schievano, Silvia; Vercauteren, Tom; Ourselin, Sébastien

doi:10.1007/978-3-319-52280-7_14

Cited by 3 publications

(2 citation statements)

References 18 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An atlas-based segmentation approach with a two-stage registration pipeline, where the majority voting and STEPS algorithms were used for the merging of the labels [23] 2017 HVSMR-2016 0.900 0.182 − A method having three crucial actions: heart identification from landmark detection, heart isolation using mathematical shape model, and segmentation using learning-based voxel classification and local phase analysis [24] 2018 [26], where the student model acquired precisely the knowledge of unlabeled target data from intra-domain teachers by fostering prediction texture and the shape priors embedded in labeled source data from inter-domain teachers via information distillation. The authors also examined the utility of concurrently leveraging unlabeled data and well-known cross-modality data for the segmentation.…”

Section: Metrics Different Methodsmentioning

confidence: 99%

Multi-Class Probabilistic Atlas-Based Whole Heart Segmentation Method in Cardiac CT and MRI

et al. 2021

View full text Add to dashboard Cite

Accurate and robust whole heart substructure segmentation is crucial in developing clinical applications, such as computer-aided diagnosis and computer-aided surgery. However, the segmentation of different heart substructures is challenging because of inadequate edge or boundary information, the complexity of the background and texture, and the diversity in different substructures' sizes and shapes. This article proposes a framework for multi-class whole heart segmentation employing non-rigid registrationbased probabilistic atlas incorporating the Bayesian framework. We also propose a non-rigid registration pipeline utilizing a multi-resolution strategy for obtaining the highest attainable mutual information between the moving and fixed images. We further incorporate non-rigid registration into the expectationmaximization algorithm and implement different deep convolutional neural network-based encoder-decoder networks for ablation studies. All the extensive experiments are conducted utilizing the publicly available dataset for the whole heart segmentation containing 20 MRI and 20 CT cardiac images. The proposed approach exhibits an encouraging achievement, yielding a mean volume overlapping error of 14.5 % for CT scans exceeding the state-of-the-art results by a margin of 1.3 % in terms of the same metric. As the proposed approach provides better results to delineate the different substructures of the heart, it can be a medical diagnostic aiding tool for helping experts with quicker and more accurate results.

show abstract

Section: Metrics Different Methodsmentioning

confidence: 99%

Multi-Class Probabilistic Atlas-Based Whole Heart Segmentation Method in Cardiac CT and MRI

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Segmentation of the congenitally malformed heart from CMR images is a challenging task due to inhomogeneity in signal intensity, limited contrast-tonoise ratio and the presence of image artefacts [5]. Furthermore, significant variation in the structural presentation of disease limits the success of conventional methods such as atlas-based strategies [9]. Finally, patient-specific 3D printing demands a high fidelity representation of disease, demonstrating anatomy at the limit of spatial resolution.…”

Section: Introductionmentioning

confidence: 99%

Topology-Preserving Augmentation for CNN-Based Segmentation of Congenital Heart Defects from 3D Paediatric CMR

Byrne

Clough

Valverde

et al. 2019

Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis

View full text Add to dashboard Cite

Patient-specific 3D printing of congenital heart anatomy demands an accurate segmentation of the thin tissue interfaces which characterise these diagnoses. Even when a label set has a high spatial overlap with the ground truth, inaccurate delineation of these interfaces can result in topological errors. These compromise the clinical utility of such models due to the anomalous appearance of defects. CNNs have achieved state-of-the-art performance in segmentation tasks. Whilst data augmentation has often played an important role, we show that conventional image resampling schemes used therein can introduce topological changes in the ground truth labelling of augmented samples. We present a novel pipeline to correct for these changes, using a fast-marching algorithm to enforce the topology of the ground truth labels within their augmented representations. In so doing, we invoke the idea of cardiac contiguous topology to describe an arbitrary combination of congenital heart defects and develop an associated, clinically meaningful metric to measure the topological correctness of segmentations. In a series of five-fold cross-validations, we demonstrate the performance gain produced by this pipeline and the relevance of topological considerations to the segmentation of congenital heart defects. We speculate as to the applicability of this approach to any segmentation task involving morphologically complex targets.

show abstract

Deep learning network for fully automatic left ventricle segmentation

Rostami

Raie

2018

2018 4th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS)

View full text Add to dashboard Cite

Strengths and Pitfalls of Whole-Heart Atlas-Based Segmentation in Congenital Heart Disease Patients

Cited by 3 publications

References 18 publications

Multi-Class Probabilistic Atlas-Based Whole Heart Segmentation Method in Cardiac CT and MRI

Multi-Class Probabilistic Atlas-Based Whole Heart Segmentation Method in Cardiac CT and MRI

Topology-Preserving Augmentation for CNN-Based Segmentation of Congenital Heart Defects from 3D Paediatric CMR

Deep learning network for fully automatic left ventricle segmentation

Contact Info

Product

Resources

About