The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.

Skin cancer is one of the leading causes of death globally. Early diagnosis of skin lesion significantly increases the prevalence of recovery. Automatic classification of the skin lesion is a challenging task to provide clinicians with the ability to differentiate between different kind of lesion categories and recommend the suitable treatment. Recently, Deep Convolutional Neural Networks have achieved tremendous success in many machine learning applications and have shown an outstanding performance in various computer-assisted diagnosis applications. Our goal is to develop an automated framework that efficiently performs a reliable automatic lesion classification to seven skin lesion types. In this work, we propose a deep neural network-based framework that follows an ensemble approach by combining ResNet-50 and Inception V3 architectures to classify the seven different skin lesion types. Experimental validation results have achieved accurate classification with an assuring validation accuracy up to 0.899.

Alzheimer’s disease (AD) is considered the 6 ^th leading cause of death worldwide. Early diagnosis of AD is not an easy task, and no preventive cures have been discovered yet. Having an accurate computer-aided system for the early detection of AD is important to help patients with AD. This study proposes a new approach for classifying disease stages. First, we worked on the MRI images and split them into an appropriate format to avoid data leakage. Subsequently, a simple and fast registration-free preprocessing pipeline was applied to the dataset. Numerous experiments were conducted to analyze the performances of different 3D classification architectures. Finally, an ensemble learning approach is applied to the top-performing models. The outstanding performance of the proposed method was demonstrated using augmentation of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. Our proposed ensemble approach outperforms studies in literature for distinguishing between people with AD and mild cognitive impairment (MCI), and MCI and cognitive normal (CN) with an AUC score of 91.28% and 88.42%, respectively. We also targeted the multiclass task, which was marginalized in previous work, by differentiating between the three stages of the disease.

Transcatheter aortic valve implantation is currently a well-established minimal invasive treatment option for patients with severe aortic valve stenosis. CT Angiography is used for the pre-operative planning and sizing of the prosthesis. To reduce the inconsistency in sizing due to interobserver variability, we introduce and evaluate an automatic aortic root landmarks detection method to determine the sizing parameters. The proposed algorithm detects the sinotubular junction, two coronary ostia, and three valvular hinge points on a segmented aortic root surface. Using these aortic root landmarks, the automated method determines annulus radius, annulus orientation, and distance from annulus plane to right and left coronary ostia. Validation is performed by the comparison with manual measurements of two observers for 40 CTA image datasets. Detection of landmarks showed high accuracy where the mean distance between the automatically detected and reference landmarks was 2.81 ± 2.08 mm, comparable to the interobserver variation of 2.67 ± 2.52 mm. The mean annulus to coronary ostium distance was 16.9 ± 3.3 and 17.1 ± 3.3 mm for the automated and the reference manual measurements, respectively, with a mean paired difference of 1.89 ± 1.71 mm and interobserver mean paired difference of 1.38 ± 1.52 mm. Automated detection of aortic root landmarks enables automated sizing with good agreement with manual measurements, which suggests applicability of the presented method in current clinical practice.