Search

Recent studies have documented ocular changes in dementia patients, especially Alzheimer Disease (AD). In this study, we explored the change of eye size and eye shape in dementia, including AD patients. The eyeball volume and diameters were estimated via T1-weighted brain magnetic resonance (MR) images in the OASIS-3 database which included 83 AD, 247 non-AD dementiaand 336 normal-aging participants qualified for this study. After adjustment of age, sex, race, apolipoprotein E genotypes, anisotropic ratio and intracranial volume, we observed the eyeball volume of the AD group was significantly larger than both the normal control (6871mm3 vs 6415mm3, p < 0.001) and the non-AD dementia group (6871mm3 vs 6391 mm3, p < 0.001), but there was no difference between the non-AD dementia group and the normal control (6391 mm3 vs 6415mm3, p = 0.795). Similar results were observed for the axial, transverse and vertical length. No group differences were observed in the anisotropic ratio, indicating an isotropic volume increaseconsistent with previous changes induced by the ocular hypertension (OH), which suggested possible elevation of the intraocular pressure (IOP) in AD. In consideration of the recent findings in ocular changes of dementia, our findings emphasize routine eye examinations and eye cares for AD patients in the clinic.

The timely identification of mental disorders in adolescents is a global public health challenge.Single factor is difficult to detect the abnormality due to its complex and subtle nature. Additionally, the generalized multimodal Computer-Aided Screening (CAS) systems with interactive robots for adolescent mental disorders are not available. Here, we design an android application with mini-games and chat recording deployed in a portable robot to screen 3,783 middle school students and construct the multimodal screening dataset, including facial images, physiological signs, voice recordings, and textual transcripts.We develop a model called GAME (Generalized Model with Attention and Multimodal EmbraceNet) with novel attention mechanism that integrates cross-modal features into the model. GAME evaluates adolescent mental conditions with high accuracy (73.34%-92.77%) and F1-Score (71.32%-91.06%).We find each modality contributes dynamically to the mental disorders screening and comorbidities among various mental disorders, indicating the feasibility of explainable model. This study provides a system capable of acquiring multimodal information and constructs a generalized multimodal integration algorithm with novel attention mechanisms for the early screening of adolescent mental disorders.

Deep learning techniques have shown great potential in medical image processing, particularly through accurate and reliable image segmentation on magnetic resonance imaging (MRI) scans or computed tomography (CT) scans, which allow the localization and diagnosis of lesions. However, training these segmentation models requires a large number of manually annotated pixel-level labels, which are time-consuming and labor-intensive, in contrast to image-level labels that are easier to obtain. It is imperative to resolve this problem through weakly-supervised semantic segmentation models using image-level labels as supervision since it can significantly reduce human annotation efforts. Most of the advanced solutions exploit class activation mapping (CAM). However, the original CAMs rarely capture the precise boundaries of lesions. In this study, we propose the strategy of multi-scale inference to refine CAMs by reducing the detail loss in single-scale reasoning. For segmentation, we develop a novel model named Mixed-UNet, which has two parallel branches in the decoding phase. The results can be obtained after fusing the extracted features from two branches. We evaluate the designed Mixed-UNet against several prevalent deep learning-based segmentation approaches on our dataset collected from the local hospital and public datasets. The validation results demonstrate that our model surpasses available methods under the same supervision level in the segmentation of various lesions from brain imaging., Comment: 12 pages, 7 figures