Multi-atlas label fusion using hybrid of discriminative and generative classifiers for segmentation of cardiac MR images

A fast right ventricle segmentation in cine-MRI from a dense hough representation

Segmentation of the right ventricle (RV) is essential for the diagnosis of multiple cardiac pathologies and conditions. However, its manual delineation is a tedious task and computational support is complex due to geometric and dynamic variability.  This work introduces a dense Hough transform and representation (HT) that allows a nonparametric characterization of the shape, encoding each voxel by its curvature and orientation. This representation is integrated into a bayesian tracking approach, which efficiently segments the RV structure throughout the cardiac cycle. The proposed approach was evaluated on a public dataset, with 16 patients, achieving a Sørensen-Dice coefficient of 0.87 and 0.92, for complete volumes and basal structures, respectively. These results evidence an adequate fit of the proposed model with respect to RV shape throughout the entire cardiac cycle. La segmentación del Ventrículo Derecho (VD) es esencial para el diagnóstico de múltiples patologías y condiciones cardiacas. Sin embargo, su delineación manual es una tarea tediosa y el soporte computacional resulta complejo debido a la variabilidad geométrica y dinámica.  Este trabajo introduce una transformación y representación densa de Hough (TH) que permite una caracterización no paramétrica de la forma, codificando cada vóxel por su curvatura y orientación. Esta representación es integrada en un enfoque de seguimiento bayesiano, que logra de forma eficiente segmentar la estructura del VD, a lo largo del ciclo cardíaco. El enfoque propuesto fue evaluado en un conjunto de datos públicos, con 16 pacientes, logrando un coeficiente Sørensen-Dice de 0,87 y 0,92, para volúmenes completos y estructuras basales, respectivamente. Estos resultados evidencian una adecuada adaptación del modelo propuesto respecto a la forma del VD a lo largo de todo el ciclo cardíaco.

Fully automatic multi-atlas segmentation of CTA for partial volume correction in cardiac SPECT/CT

Anatomical-based partial volume correction (PVC) has been shown to improve image quality and quantitative accuracy in cardiac SPECT/CT. However, this method requires manual segmentation of various organs from contrast-enhanced computed tomography angiography (CTA) data. In order to achieve fully automatic CTA segmentation for clinical translation, we investigated the most common multi-atlas segmentation methods. We also modified the multi-atlas segmentation method by introducing a novel label fusion algorithm for multiple organ segmentation to eliminate overlap and gap voxels. To evaluate our proposed automatic segmentation, eight canine ^99mTc-labeled red blood cell SPECT/CT datasets that incorporated PVC were analyzed, using the leave-one-out approach. The Dice similarity coefficient of each organ was computed. Compared to the conventional label fusion method, our proposed label fusion method effectively eliminated gaps and overlaps and improved the CTA segmentation accuracy. The anatomical-based PVC of cardiac SPECT images with automatic multi-atlas segmentation provided consistent image quality and quantitative estimation of intramyocardial blood volume, as compared to those derived using manual segmentation. In conclusion, our proposed automatic multi-atlas segmentation method of CTAs is feasible, practical, and facilitates anatomical-based PVC of cardiac SPECT/CT images.