Active multitask learning with uncertainty-weighted loss for coronary calcium scoring.

PURPOSE: The coronary artery calcification (CAC) score is an independent marker for the risk of cardiovascular events. Automatic methods for quantifying CAC could reduce workload and assist radiologists in clinical decision-making. However, large annotated datasets are needed for training to achieve very good model performance, which is an expensive process and requires expert knowledge. The number of training data required can be reduced in an active learning scenario, which requires only the most informative samples to be labeled. Multitask learning techniques can improve model performance by joint learning of multiple related tasks and extraction of shared informative features. METHODS: We propose an uncertainty-weighted multitask learning model for coronary calcium scoring in electrocardiogram-gated (ECG-gated), noncontrast-enhanced cardiac calcium scoring CT. The model was trained to solve the two tasks of coronary artery region segmentation (weak labels) and coronary artery calcification segmentation (strong labels) simultaneously in an active learning scenario to improve model performance and reduce the number of samples needed for training. We compared our model with a single-task U-Net and a sequential-task model as well as other state-of-the-art methods. The model was evaluated on 1275 individual patients in three different datasets (DISCHARGE, CADMAN, orCaScore), and the relationship between model performance and various influencing factors (image noise, metal artifacts, motion artifacts, image quality) was analyzed. RESULTS: Joint learning of multiclass coronary artery region segmentation and binary coronary calcium segmentation improved calcium scoring performance. Since shared information can be learned from both tasks for complementary purposes, the model reached optimal performance with only 12% of the training data and one-third of the labeling time in an active learning scenario. We identified image noise as one of the most important factors influencing model performance along with anatomical abnormalities and metal artifacts. CONCLUSIONS: Our multitask learning approach with uncertainty-weighted loss improves calcium scoring performance by joint learning of shared features and reduces labeling costs when trained in an active learning scenario.

Spatio-Temporal Deep Learning-Based Undersampling Artefact Reduction for 2D Radial Cine MRI With Limited Training Data.

In this work we reduce undersampling artefacts in two-dimensional (2D) golden-angle radial cine cardiac MRI by applying a modified version of the U-net. The network is trained on 2D spatio-temporal slices which are previously extracted from the image sequences. We compare our approach to two 2D and a 3D deep learning-based post processing methods, three iterative reconstruction methods and two recently proposed methods for dynamic cardiac MRI based on 2D and 3D cascaded networks. Our method outperforms the 2D spatially trained U-net and the 2D spatio-temporal U-net. Compared to the 3D spatio-temporal U-net, our method delivers comparable results, but requiring shorter training times and less training data. Compared to the compressed sensing-based methods kt-FOCUSS and a total variation regularized reconstruction approach, our method improves image quality with respect to all reported metrics. Further, it achieves competitive results when compared to the iterative reconstruction method based on adaptive regularization with dictionary learning and total variation and when compared to the methods based on cascaded networks, while only requiring a small fraction of the computational and training time. A persistent homology analysis demonstrates that the data manifold of the spatio-temporal domain has a lower complexity than the one of the spatial domain and therefore, the learning of a projection-like mapping is facilitated. Even when trained on only one single subject without data-augmentation, our approach yields results which are similar to the ones obtained on a large training dataset. This makes the method particularly suitable for training a network on limited training data. Finally, in contrast to the spatial 2D U-net, our proposed method is shown to be naturally robust with respect to image rotation in image space and almost achieves rotation-equivariance where neither data-augmentation nor a particular network design are required.

Glassy correlations and microstructures in randomly cross-linked homopolymer blends.

We consider a microscopic model of a polymer blend that is prone to phase separation. Permanent cross-links are introduced between randomly chosen pairs of monomers, drawn from the Deam-Edwards distribution. Thereby, not only density but also concentration fluctuations of the melt are quenched-in in the gel state, which emerge upon sufficient cross-linking. We derive a Landau expansion in terms of the order parameters for gelation and phase separation, and analyze it on the mean-field level, including Gaussian fluctuations. The mixed gel is characterized by thermal as well as time-persistent (glassy) concentration fluctuations. Whereas the former are independent of the preparation state, the latter reflect the concentration fluctuations at the instant of cross-linking, provided the mesh size is smaller than the correlation length of phase separation. The mixed gel becomes unstable to microphase separation upon lowering the temperature in the gel phase. Whereas the length scale of microphase separation is given by the mesh size, at least close to the transition, the emergent microstructure depends on the composition and compressibility of the melt. Hexagonal structures, as well as lamellas or random structures with a unique wavelength, can be energetically favorable.