Nondestructive Imaging of Manufacturing Defects in Microarchitected Materials.

Defects in microarchitected materials exhibit a dual nature, capable of both unlocking innovative functionalities and degrading their performance. Specifically, while intentional defects are strategically introduced to customize and enhance mechanical responses, inadvertent defects stemming from manufacturing errors can disrupt the symmetries and intricate interactions within these materials. In this study, we demonstrate a nondestructive optical imaging technique that can precisely locate defects inside microscale metamaterials, as well as provide detailed insights on the specific type of defect.

Three-Dimensional Optical Imaging of Internal Deformations in Polymeric Microscale Mechanical Metamaterials.

Recent advances in two-photon polymerization fabrication processes are paving the way to creating macroscopic metamaterials with microscale architectures, which exhibit mechanical properties superior to their bulk material counterparts. These metamaterials typically feature lightweight, complex patterns such as lattice or minimal surface structures. Conventional tools for investigating these microscale structures, such as scanning electron microscopy, cannot easily probe the internal features of these structures, which are critical for a comprehensive assessment of their mechanical behavior. In turn, we demonstrate an optical confocal microscopy-based approach that allows for high-resolution optical imaging of internal deformations and fracture processes in microscale metamaterials under mechanical load. We validate this technique by investigating an exemplary metamaterial lattice structure of 80 × 80 × 80 µm3 in size. This technique can be extended to other metamaterial systems and holds significant promise to enhance our understanding of their real-world performance under loading conditions.

Mortality Prediction of Patients with Subarachnoid Hemorrhage Using a Deep Learning Model Based on an Initial Brain CT Scan.

BACKGROUND: Subarachnoid hemorrhage (SAH) entails high morbidity and mortality rates. Convolutional neural networks (CNN) are capable of generating highly accurate predictions from imaging data. Our objective was to predict mortality in SAH patients by processing initial CT scans using a CNN-based algorithm. METHODS: We conducted a retrospective multicentric study of a consecutive cohort of patients with SAH. Demographic, clinical and radiological variables were analyzed. Preprocessed baseline CT scan images were used as the input for training using the AUCMEDI framework. Our model's architecture leveraged a DenseNet121 structure, employing transfer learning principles. The output variable was mortality in the first three months. RESULTS: Images from 219 patients were processed; 175 for training and validation and 44 for the model's evaluation. Of the patients, 52% (115/219) were female and the median age was 58 (SD = 13.06) years. In total, 18.5% (39/219) had idiopathic SAH. The mortality rate was 28.5% (63/219). The model showed good accuracy at predicting mortality in SAH patients when exclusively using the images of the initial CT scan (accuracy = 74%, F1 = 75% and AUC = 82%). CONCLUSION: Modern image processing techniques based on AI and CNN make it possible to predict mortality in SAH patients with high accuracy using CT scan images as the only input. These models might be optimized by including more data and patients, resulting in better training, development and performance on tasks that are beyond the skills of conventional clinical knowledge.