A Biomimetic Cement-Based Solid-State Electrolyte with Both High Strength and Ionic Conductivity for Self-Energy-Storage Buildings.

Cement-based materials are the foundation of modern buildings but suffer from intensive energy consumption. Utilizing cement-based materials for efficient energy storage is one of the most promising strategies for realizing zero-energy buildings. However, cement-based materials encounter challenges in achieving excellent electrochemical performance without compromising mechanical properties. Here, we introduce a biomimetic cement-based solid-state electrolyte (labeled as l-CPSSE) with artificially organized layered microstructures by proposing an in situ ice-templating strategy upon the cement hydration, in which the layered micropores are further filled with fast-ion-conducting hydrogels and serve as ion diffusion highways. With these merits, the obtained l-CPSSE not only presents marked specific bending and compressive strength (2.2 and 1.2 times that of traditional cement, respectively) but also exhibits excellent ionic conductivity (27.8 mS·cm-1), overwhelming most previously reported cement-based and hydrogel-based electrolytes. As a proof-of-concept demonstration, we assemble the l-CPSSE electrolytes with cement-based electrodes to achieve all-cement-based solid-state energy storage devices, delivering an outstanding full-cell specific capacity of 72.2 mF·cm-2. More importantly, a 5 × 5 cm2 sized building model is successfully fabricated and operated by connecting 4 l-CPSSE-based full cells in series, showcasing its great potential in self-energy-storage buildings. This work provides a general methodology for preparing revolutionary cement-based electrolytes and may pave the way for achieving zero-carbon buildings.

Diffusion Models To Predict 3D Late Mechanical Activation From Sparse 2D Cardiac MRIs.

Identifying regions of late mechanical activation (LMA) of the left ventricular (LV) myocardium is critical in determining the optimal pacing site for cardiac resynchronization therapy in patients with heart failure. Several deep learning-based approaches have been developed to predict 3D LMA maps of LV myocardium from a stack of sparse 2D cardiac magnetic resonance imaging (MRIs). However, these models often loosely consider the geometric shape structure of the myocardium. This makes the reconstructed activation maps suboptimal; hence leading to a reduced accuracy of predicting the late activating regions of hearts. In this paper, we propose to use shape-constrained diffusion models to better reconstruct a 3D LMA map, given a limited number of 2D cardiac MRI slices. In contrast to previous methods that primarily rely on spatial correlations of image intensities for 3D reconstruction, our model leverages object shape as priors learned from the training data to guide the reconstruction process. To achieve this, we develop a joint learning network that simultaneously learns a mean shape under deformation models. Each reconstructed image is then considered as a deformed variant of the mean shape. To validate the performance of our model, we train and test the proposed framework on a publicly available mesh dataset of 3D myocardium and compare it with state-of-the-art deep learning-based reconstruction models. Experimental results show that our model achieves superior performance in reconstructing the 3D LMA maps as compared to the state-of-the-art models.

JOINT DEEP LEARNING FOR IMPROVED MYOCARDIAL SCAR DETECTION FROM CARDIAC MRI.

Automated identification of myocardial scar from late gadolinium enhancement cardiac magnetic resonance images (LGE-CMR) is limited by image noise and artifacts such as those related to motion and partial volume effect. This paper presents a novel joint deep learning (JDL) framework that improves such tasks by utilizing simultaneously learned myocardium segmentations to eliminate negative effects from non-region-of-interest areas. In contrast to previous approaches treating scar detection and myocardium segmentation as separate or parallel tasks, our proposed method introduces a message passing module where the information of myocardium segmentation is directly passed to guide scar detectors. This newly designed network will efficiently exploit joint information from the two related tasks and use all available sources of myocardium segmentation to benefit scar identification. We demonstrate the effectiveness of JDL on LGE-CMR images for automated left ventricular (LV) scar detection, with great potential to improve risk prediction in patients with both ischemic and non-ischemic heart disease and to improve response rates to cardiac resynchronization therapy (CRT) for heart failure patients. Experimental results show that our proposed approach outperforms multiple state-of-the-art methods, including commonly used two-step segmentation-classification networks, and multitask learning schemes where subtasks are indirectly interacted.