Redefining Lobe-Wise Ground-Glass Opacity in COVID-19 Through Deep Learning and its Correlation With Biochemical Parameters.

During COVID-19 pandemic qRT-PCR, CT scans and biochemical parameters were studied to understand the patients' physiological changes and disease progression. There is a lack of clear understanding of the correlation of lung inflammation with biochemical parameters available. Among the 1136 patients studied, C-reactive-protein (CRP) is the most critical parameter for classifying symptomatic and asymptomatic groups. Elevated CRP is corroborated with increased D-dimer, Gamma-glutamyl-transferase (GGT), and urea levels in COVID-19 patients. To overcome the limitations of manual chest CT scoring system, we segmented the lungs and detected ground-glass-opacity (GGO) in specific lobes from 2D CT images by 2D U-Net-based deep learning (DL) approach. Our method shows accuracy, compared to the manual method (  âˆ¼ 80%), which is subjected to the radiologist's experience. We determined a positive correlation of GGO in the right upper-middle (0.34) and lower (0.26) lobe with D-dimer. However, a modest correlation was observed with CRP, ferritin and other studied parameters. The final Dice Coefficient (or the F1 score) and Intersection-Over-Union for testing accuracy are 95.44% and 91.95%, respectively. This study can help reduce the burden and manual bias besides increasing the accuracy of GGO scoring. Further study on geographically diverse large populations may help to understand the association of the biochemical parameters and pattern of GGO in lung lobes with different SARS-CoV-2 Variants of Concern's disease pathogenesis in these populations.

Biceph-Net: A Robust and Lightweight Framework for the Diagnosis of Alzheimer's Disease Using 2D-MRI Scans and Deep Similarity Learning.

Alzheimer's Disease (AD) is a neurodegenerative disease that is one of the significant causes of death in the elderly population. Many deep learning techniques have been proposed to diagnose AD using Magnetic Resonance Imaging (MRI) scans. Predicting AD using 2D slices extracted from 3D MRI scans is challenging as the inter-slice information gets lost. To this end, we propose a novel and lightweight framework termed 'Biceph-net' for AD diagnosis using 2D MRI scans that models both the intra-slice and inter-slice information. 'Biceph-net' has been experimentally shown to perform similar to other Spatio-temporal neural networks while being computationally more efficient. Biceph-net is also superior in performance compared to vanilla 2D convolutional neural networks (CNN) for AD diagnosis using 2D MRI slices. Biceph-net also has an inbuilt neighbourhood-based model interpretation feature that can be exploited to understand the classification decision taken by the network. Biceph-net experimentally achieves a test accuracy of 100% in the classification of Cognitively Normal (CN) vs AD, 98.16% for Mild Cognitive Impairment (MCI) vs AD, and 97.80% for CN vs MCI vs AD.

Reducing rip current drowning: An improved residual based lightweight deep architecture for rip detection.

Rip Currents are contributing around 25 fatal drownings each year in Australia. Previous research has indicated that most of beachgoers cannot correctly identify a rip current, leaving them at risk of experiencing a drowning incident. Automated detection of rip currents could help to reduce drownings and assist lifeguards in supervision planning; however, varying beach conditions have made this challenging. This work presents the effectiveness of an improved lightweight framework for detecting rip currents: RipDet+1, aided with residual mapping to boost the generalization performance. We have used Yolo-V3 architecture to build RipDet+ framework and utilize pretrained weight by fully exploiting the detection training set from some base classes which in result quickly adapt the detection prediction to the available rip data. Extensive experiments are reported which show the effectiveness of RipDet+ architecture in achieving a detection accuracy of 98.55%, which is significantly greater compared to other state-of-the-art methods for Rip currents detection.