Dental image enhancement network for early diagnosis of oral dental disease.

Intelligent robotics and expert system applications in dentistry suffer from identification and detection problems due to the non-uniform brightness and low contrast in the captured images. Moreover, during the diagnostic process, exposure of sensitive facial parts to ionizing radiations (e.g., X-Rays) has several disadvantages and provides a limited angle for the view of vision. Capturing high-quality medical images with advanced digital devices is challenging, and processing these images distorts the contrast and visual quality. It curtails the performance of potential intelligent and expert systems and disincentives the early diagnosis of oral and dental diseases. The traditional enhancement methods are designed for specific conditions, and network-based methods rely on large-scale datasets with limited adaptability towards varying conditions. This paper proposed a novel and adaptive dental image enhancement strategy based on a small dataset and proposed a paired branch Denticle-Edification network (Ded-Net). The input dental images are decomposed into reflection and illumination in a multilayer Denticle network (De-Net). The subsequent enhancement operations are performed to remove the hidden degradation of reflection and illumination. The adaptive illumination consistency is maintained through the Edification network (Ed-Net). The network is regularized following the decomposition congruity of the input data and provides user-specific freedom of adaptability towards desired contrast levels. The experimental results demonstrate that the proposed method improves visibility and contrast and preserves the edges and boundaries of the low-contrast input images. It proves that the proposed method is suitable for intelligent and expert system applications for future dental imaging.

A transfer learning approach for multiclass classification of Alzheimer's disease using MRI images.

Alzheimer's is an acute degenerative disease affecting the elderly population all over the world. The detection of disease at an early stage in the absence of a large-scale annotated dataset is crucial to the clinical treatment for the prevention and early detection of Alzheimer's disease (AD). In this study, we propose a transfer learning base approach to classify various stages of AD. The proposed model can distinguish between normal control (NC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and AD. In this regard, we apply tissue segmentation to extract the gray matter from the MRI scans obtained from the Alzheimer's Disease National Initiative (ADNI) database. We utilize this gray matter to tune the pre-trained VGG architecture while freezing the features of the ImageNet database. It is achieved through the addition of a layer with step-wise freezing of the existing blocks in the network. It not only assists transfer learning but also contributes to learning new features efficiently. Extensive experiments are conducted and results demonstrate the superiority of the proposed approach.

Chest radiographs may assist in predicting the outcome in the early phase of Covid-19. UK district general hospital experience of Covid-19 first wave.

Objectives: Severe Acute Respiratory Syndrome coronavirus-2 (SARS-CoV-2) has caused enormous strain on health-care systems worldwide. Early recognition of prognostic markers and appropriate management of patients with coronavirus disease 2019 (Covid-19) remains a major global health concern, particularly when resources are limited. We undertook a study to see if basic tests can inform frontline clinicians of disease trajectory in individual patients with COVID-19.Methods: We retrospectively assessed characteristics of the first 50 consecutive patients admitted to district general hospital in the United Kingdom with positive SARS-Cov-2 RNA swabs.Results: Our patient cohort shared broad similarities with previously published data on comorbidities and presenting features. We have found that chest radiographic assessment differed between survivors and non-survivors. Air space shadowing in middle zones were more prevalent in non-survivors (73.3% vs. 35.5% [p = 0.027]). Chest radiograph severity score was also found to be higher in non-survivors compared to survivors (3 vs. 1.5 [p = 0.007]).Conclusions: In this small retrospective study, our results suggest features of chest radiographs at presentation may provide a helpful tool for prognostication. In environments with constrained computed tomography (CT) imaging with serial chest radiographs could be a cost-effective tool in the assessment of Covid-19 patients.