Mixture of Probabilistic Principal Component Analyzers for Shapes from Point Sets

Fully Automatic initialization and segmentation of left and right ventricles for large-scale cardiac MRI using a deeply supervised network and 3D-ASM

BACKGROUND AND OBJECTIVE

The sheer volume of data generated by population imaging studies is unparalleled by current capabilities to extract objective and quantitative cardiac phenotypes; subjective and time-consuming manual image analysis remains the gold standard. Automated image analytics to compute quantitative imaging biomarkers of cardiac function are desperately needed. Data volumes and their variability pose a challenge to most state-of-the-art methods for endo- and epicardial contours, which lack robustness when applied to very large datasets. Our aim is to develop an analysis pipeline for the automatic quantification of cardiac function from cine magnetic resonance imaging data.

METHOD

This work adopt 4,638 cardiac MRI cases coming from UK Biobank with ground truth available for left and RV contours. A hybrid and robust algorithm is proposed to improve the accuracy of automatic left and right ventricle segmentation by harnessing the localization accuracy of deep learning and the morphological accuracy of 3D-ASM (three-dimensional active shape models). The contributions of this paper are three-fold. First, a fully automatic method is proposed for left and right ventricle initialization and cardiac MRI segmentation by taking full advantage of spatiotemporal constraint. Second, a deeply supervised network is introduced to train and segment the heart. Third, the 3D-ASM image search procedure is improved by combining image intensity models with convolutional neural network (CNN) derived distance maps improving endo- and epicardial edge localization.

RESULTS

The proposed architecture outperformed the state of the art for cardiac MRI segmentation from UK Biobank. The statistics of RV landmarks detection errors for Triscuspid valve and RV apex are 4.17 mm and 5.58 mm separately. The overlap metric, mean contour distance, Hausdorff distance and cardiac functional parameters are calculated for the LV (Left Ventricle) and RV (Right Ventricle) contour segmentation. Bland-Altman analysis for clinical parameters shows that the results from our automated image analysis pipelines are in good agreement with results from expert manual analysis.

CONCLUSIONS

Our hybrid scheme combines deep learning and statistical shape modeling for automatic segmentation of the LV/RV from cardiac MRI datasets is effective and robust and can compute cardiac functional indexes from population imaging.

Artificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy

In many cardiovascular pathologies, the shape and motion of the heart provide important clues to understanding the mechanisms of the disease and how it progresses over time. With the advent of large-scale cardiac data, statistical modeling of cardiac anatomy has become a powerful tool to provide automated, precise quantification of the status of patient-specific heart geometry with respect to reference populations. Powered by supervised or unsupervised machine learning algorithms, statistical cardiac shape analysis can be used to automatically identify and quantify the severity of heart diseases, to provide morphometric indices that are optimally associated with clinical factors, and to evaluate the likelihood of adverse outcomes. Recently, statistical cardiac atlases have been integrated with deep neural networks to enable anatomical consistency of cardiac segmentation, registration, and automated quality control. These combinations have already shown significant improvements in performance and avoid gross anatomical errors that could make the results unusable. This current trend is expected to grow in the near future. Here, we aim to provide a mini review highlighting recent advances in statistical atlasing of cardiac function in the context of artificial intelligence in cardiac imaging.

A model order reduction approach to create patient-specific mechanical models of human liver in computational medicine applications

BACKGROUND AND OBJECTIVE

This paper focuses on computer simulation aspects of Digital Twin models in the medical framework. In particular, it addresses the need of fast and accurate simulators for the mechanical response at tissue and organ scale and the capability of integrating patient-specific anatomy from medical images to pinpoint the individual variations from standard anatomical models.

METHODS

We propose an automated procedure to create mechanical models of the human liver with patient-specific geometry and real time capabilities. The method hinges on the use of Statistical Shape Analysis to extract the relevant anatomical features from a database of medical images and Model Order Reduction to compute an explicit parametric solution for the mechanical response as a function of such features. The Sparse Subspace Learning, coupled with a Finite Element solver, was chosen to create low-rank solutions using a non-intrusive sparse sampling of the feature space.

RESULTS

In the application presented in the paper, the statistical shape model was trained on a database of 385 three dimensional liver shapes, extracted from medical images, in order to create a parametrized representation of the liver anatomy. This parametrization and an additional parameter describing the breathing motion in linear elasticity were then used as input in the reduced order model. Results show a consistent agreement with the high fidelity Finite Element models built from liver images that were excluded from the training dataset. However, we evidence in the discussion the difficulty of having compact shape parametrizations arising from the extreme variability of the shapes found in the dataset and we propose potential strategies to tackle this issue.

CONCLUSIONS

A method to represent patient-specific real-time liver deformations during breathing is proposed in linear elasticity. Since the proposed method does not require any adaptation to the direct Finite Element solver used in the training phase, the procedure can be easily extended to more complex non-linear constitutive behaviors - such as hyperelasticity - and more general load cases. Therefore it can be integrated with little intrusiveness to generic simulation software including more sophisticated and realistic models.

Clustering of Morphological Features for Identifying Femur Cavity Subtypes With Difficulties of Intramedullary Nail Implantation

Intramedullary (IM) nail implantation is currently the standard treatment for femoral intertrochanteric fractures. However, individual differences in femur cavity bring a challenge in designing well-matched IM nails and cause difficulties in IM nail implantation. Therefore, there is an intense need to analyze femur cavities to predict difficulties in IM nail implantation to assist the design of IM nails. This study proposed a method to automatically identify subtypes of femur cavities that exhibit differences in potential difficulties in nail implantation by clustering the morphological features of femur models. The unsupervised subtype extraction method offers a scientific approach to stratify patients for designing and choosing well-matched IM nails. First, the quantitative morphological features of 422 femur cavities were extracted from computed tomography patient models. Second, 422 femur cavities were clustered into three distinct subtypes using a density peak-based k-means clustering method to provide a possible solution for the scientific design of IM nails. The effectiveness of the identified subtypes was validated by comparing subtype differences associated with IM nail implantation and the natural attributes of the patient. Quantitative evaluation of the mismatch degree and real clinical cases confirmed that the clustering results were clinically effective, with clear differences in the subtypes. Therefore, particular IM nails designed from the identified subtypes will potentially facilitate IM nail implantation and reduce complications. Compared with state-of-the-art methods, we used the largest scale dataset and unsupervised clustering to achieve subtype identification of femur cavities with clinical significance.