Voxelwise atlas rating for computer assisted diagnosis: Application to congenital heart diseases of the great arteries

From Accuracy to Reliability and Robustness in Cardiac Magnetic Resonance Image Segmentation: A Review

Since the rise of deep learning (DL) in the mid-2010s, cardiac magnetic resonance (CMR) image segmentation has achieved state-of-the-art performance. Despite achieving inter-observer variability in terms of different accuracy performance measures, visual inspections reveal errors in most segmentation results, indicating a lack of reliability and robustness of DL segmentation models, which can be critical if a model was to be deployed into clinical practice. In this work, we aim to bring attention to reliability and robustness, two unmet needs of cardiac image segmentation methods, which are hampering their translation into practice. To this end, we first study the performance accuracy evolution of CMR segmentation, illustrate the improvements brought by DL algorithms and highlight the symptoms of performance stagnation. Afterwards, we provide formal definitions of reliability and robustness. Based on the two definitions, we identify the factors that limit the reliability and robustness of state-of-the-art deep learning CMR segmentation techniques. Finally, we give an overview of the current set of works that focus on improving the reliability and robustness of CMR segmentation, and we categorize them into two families of methods: quality control methods and model improvement techniques. The first category corresponds to simpler strategies that only aim to flag situations where a model may be incurring poor reliability or robustness. The second one, instead, directly tackles the problem by bringing improvements into different aspects of the CMR segmentation model development process. We aim to bring the attention of more researchers towards these emerging trends regarding the development of reliable and robust CMR segmentation frameworks, which can guarantee the safe use of DL in clinical routines and studies.

The role of artificial intelligence in paediatric cardiovascular magnetic resonance imaging

Artificial intelligence (AI) offers the potential to change many aspects of paediatric cardiac imaging. At present, there are only a few clinically validated examples of AI applications in this field. This review focuses on the use of AI in paediatric cardiovascular MRI, using examples from paediatric cardiovascular MRI, adult cardiovascular MRI and other radiologic experience.

Congenital heart disease-associated liver disease: a narrative review

Congenital heart diseases (CHD) can be associated with liver dysfunction. The cause for liver impairment can result out of a wide spectrum of different causes, including liver congestion, hypoxemia or low cardiac output. Fortunately, most CHD show a good long-term outcome from a cardiac perspective, but great attention should be paid on non-cardiac health problems that develop frequently in patients suffering from CHD. The treatment of liver dysfunction in CHD requires a close multidisciplinary management in a vulnerable patient collective. Unfortunately, structured recommendations on the management of liver dysfunction in patients with CHD are scarce. The objective of this review is to provide insights on the pathophysiology and etiologies of liver dysfunction as one of the most relevant non-cardiac problems related to CHD. Furthermore, we advise here on the management of liver disease in CHD with special attention on assessment of liver dysfunction, management of portal hypertension as well as on surveillance and management of hepatocellular carcinoma (HCC). A multidisciplinary perspective may help to optimize morbidity and mortality in the long-term course in these patients. However, as evidence is low in many aspects, we encourage the scientific community to perform prospective studies to gain more insights in the treatment of liver dysfunction in patients with CHD.

A collection input based support tensor machine for lesion malignancy classification in digital breast tomosynthesis

Digital breast tomosynthesis (DBT) with improved lesion conspicuity and characterization has been adopted in screening practice. DBT-based diagnosis strongly depends on physicians' experience, so an automatic lesion malignancy classification model using DBT could improve the consistency of diagnosis among different physicians. Tensor-based approaches that use the original imaging data as input have shown promising results for many classification tasks. However, DBT data are pseudo-3D volumetric imaging as the slice spacing of DBT is much coarser than that of the in-plane resolution. Thus, directly constructing DBT as the third-order tensor in a conventional tensor-based classifier with introducing additional information to the original DBT data along the slice-spacing dimension will lead to inconsistency across all three dimensions. To avoid such inconsistency, we introduce a collection input based support tensor machine (CISTM)-based classifier that uses the tensor collection as input for classifying lesion malignancy in DBT. In CISTM, instead of introducing the third dimension directly into the geometry construction, the third-dimension structural relationship is related by weight parameters in the decision function, which is dynamically and automatically constructed during the classifier training process and is more consistent with the pseudo-3D nature of DBT. We tested our method on a DBT dataset of 926 images among which 262 were malignant and 664 were benign. We compared our method with the latest tensor-based method, KSTM (kernelled support tensor machine), which does not consider the unique non-uniform resolution property of DBT. Experimental results illustrate that the CISTM-based classifier is effective for classifying breast lesion malignancy in DBT and that it outperforms the KSTM-based classifier.

A pilot study using kernelled support tensor machine for distant failure prediction in lung SBRT

We developed a kernelled support tensor machine (KSTM)-based model with tumor tensors derived from pre-treatment PET and CT imaging as input to predict distant failure in early stage non-small cell lung cancer (NSCLC) treated with stereotactic body radiation therapy (SBRT). The patient cohort included 110 early stage NSCLC patients treated with SBRT, 25 of whom experienced failure at distant sites. Three-dimensional tumor tensors were constructed and used as input for the KSTM-based classifier. A KSTM iterative algorithm with a convergent proof was developed to train the weight vectors for every mode of the tensor for the classifier. In contrast to conventional radiomics approaches that rely on handcrafted imaging features, the KSTM-based classifier uses 3D imaging as input, taking full advantage of the imaging information. The KSTM-based classifier preserves the intrinsic 3D geometry structure of the medical images and the correlation in the original images and trains the classification hyper-plane in an adaptive feature tensor space. The KSTM-based predictive algorithm was compared with three conventional machine learning models and three radiomics approaches. For PET and CT, the KSTM-based predictive method achieved the highest prediction results among the seven methods investigated in this study based on 10-fold cross validation and independent testing.

Shell feature: a new radiomics descriptor for predicting distant failure after radiotherapy in non-small cell lung cancer and cervix cancer

Distant failure is the main cause of human cancer-related mortalities. To develop a model for predicting distant failure in non-small cell lung cancer (NSCLC) and cervix cancer (CC) patients, a shell feature, consisting of outer voxels around the tumor boundary, was constructed using pre-treatment positron emission tomography (PET) images from 48 NSCLC patients received stereotactic body radiation therapy and 52 CC patients underwent external beam radiation therapy and concurrent chemotherapy followed with high-dose-rate intracavitary brachytherapy. The hypothesis behind this feature is that non-invasive and invasive tumors may have different morphologic patterns in the tumor periphery, in turn reflecting the differences in radiological presentations in the PET images. The utility of the shell was evaluated by the support vector machine classifier in comparison with intensity, geometry, gray level co-occurrence matrix-based texture, neighborhood gray tone difference matrix-based texture, and a combination of these four features. The results were assessed in terms of accuracy, sensitivity, specificity, and AUC. Collectively, the shell feature showed better predictive performance than all the other features for distant failure prediction in both NSCLC and CC cohorts.

Statistical Shape Modeling for Cavopulmonary Assist Device Development: Variability of Vascular Graft Geometry and Implications for Hemodynamics

Patients born with a single functional ventricle typically undergo three-staged surgical palliation in the first years of life, with the last stage realizing a cross-like total cavopulmonary connection (TCPC) of superior and inferior vena cavas (SVC and IVC) with both left and right pulmonary arteries, allowing all deoxygenated blood to flow passively back to the lungs (Fontan circulation). Even though within the past decades more patients survive into adulthood, the connection comes at the prize of deficiencies such as chronic systemic venous hypertension and low cardiac output, which ultimately may lead to Fontan failure. Many studies have suggested that the TCPC's inherent insufficiencies might be addressed by adding a cavopulmonary assist device (CPAD) to provide the necessary pressure boost. While many device concepts are being explored, few take into account the complex cardiac anatomy typically associated with TCPCs. In this study, we focus on the extra cardiac conduit vascular graft connecting IVC and pulmonary arteries as one possible landing zone for a CPAD and describe its geometric variability in a cohort of 18 patients that had their TCPC realized with a 20mm vascular graft. We report traditional morphometric parameters and apply statistical shape modeling to determine the main contributors of graft shape variability. Such information may prove useful when designing CPADs that are adapted to the challenging anatomical boundaries in Fontan patients. We further compute the anatomical mean 3D graft shape (template graft) as a representative of key shape features of our cohort and prove this template graft to be a significantly better approximation of population and individual patient's hemodynamics than a commonly used simplified tube geometry. We therefore conclude that statistical shape modeling results can provide better models of geometric and hemodynamic boundary conditions associated with complex cardiac anatomy, which in turn may impact on improved cardiac device development.

Detecting Clinically Meaningful Shape Clusters in Medical Image Data: Metrics Analysis for Hierarchical Clustering Applied to Healthy and Pathological Aortic Arches

OBJECTIVE

Today's growing medical image databases call for novel processing tools to structure the bulk of data and extract clinically relevant information. Unsupervised hierarchical clustering may reveal clusters within anatomical shape data of patient populations as required for modern precision medicine strategies. Few studies have applied hierarchical clustering techniques to three-dimensional patient shape data and results depend heavily on the chosen clustering distance metrics and linkage functions. In this study, we sought to assess clustering classification performance of various distance/linkage combinations and of different types of input data to obtain clinically meaningful shape clusters.

METHODS

We present a processing pipeline combining automatic segmentation, statistical shape modeling, and agglomerative hierarchical clustering to automatically subdivide a set of 60 aortic arch anatomical models into healthy controls, two groups affected by congenital heart disease, and their respective subgroups as defined by clinical diagnosis. Results were compared with traditional morphometrics and principal component analysis of shape features.

RESULTS

Our pipeline achieved automatic division of input shape data according to primary clinical diagnosis with high F-score (0.902 ± 0.042) and Matthews correlation coefficient (0.851 ± 0.064) using the correlation/weighted distance/linkage combination. Meaningful subgroups within the three patient groups were obtained and benchmark scores for automatic segmentation and classification performance are reported.

CONCLUSION

Clustering results vary depending on the distance/linkage combination used to divide the data. Yet, clinically relevant shape clusters and subgroups could be found with high specificity and low misclassification rates.

SIGNIFICANCE

Detecting disease-specific clusters within medical image data could improve image-based risk assessment, treatment planning, and medical device development in complex disease.