Interactive Whole-Heart Segmentation in Congenital Heart Disease

Abstract

We present an interactive algorithm to segment the heart chambers and epicardial surfaces, including the great vessel walls, in pediatric cardiac MRI of congenital heart disease. Accurate whole-heart segmentation is necessary to create patient-specific 3D heart models for surgical planning in the presence of complex heart defects. Anatomical variability due to congenital defects precludes fully automatic atlas-based segmentation. Our interactive segmentation method exploits expert segmentations of a small set of short-axis slice regions to automatically delineate the remaining volume using patch-based segmentation. We also investigate the potential of active learning to automatically solicit user input in areas where segmentation error is likely to be high. Validation is performed on four subjects with double outlet right ventricle, a severe congenital heart defect. We show that strategies asking the user to manually segment regions of interest within short-axis slices yield higher accuracy with less user input than those querying entire short-axis slices.

3d Modelling and Rapid Prototyping for Cardiovascular Surgical Planning – Two Case Studies

“…At the end of the segmentation process, the operator interaction is still required for error corrections (Olabarriaga & Smeulders, 2001). Interactive segmentation methods, employing for example manual segmentations in a small set of slices and automatic classification of the remaining volume using patch-based approach (Pace et al, 2015), provide promising results.…”

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

“…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].…”

“…Inaccurate interface segmentation introduces anomalous topological features that may falsely indicate the presence of congenital heart defects. Consequently, exponents of patient-specific 3D printed heart models have hitherto relied on manual and semi-automated segmentation methods, typically requiring at least an hour of manual interaction per patient [5].…”

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

“…However, when applied in the context of CHD patients, they are not as successful. This might be explained by the substantial changes in heart topology and high anatomical variability in CHD that lead to poor segmentations [2,10,16]. In an ideal scenario, this could be solved by using as many atlas databases as pathological conditions.…”

“…In the context of the Whole-Heart and Great Vessel Segmentation from 3D Cardiovascular MRI in Congenital Heart Disease Challenge (HVSMR) [10], this work focuses on atlas-based segmentation techniques and aims to assess the strengths and limitations of these methods in CHD patients. In the remaining of this paper, Section 2 provides a more detailed overview of atlas-based approaches, Section 3 describes the materials and methods used and Section 4 presents the obtained results.…”