LiMS-Net: A Lightweight Multi-Scale CNN for COVID-19 Detection from Chest CT Scans

Recent years have witnessed a rise in employing deep learning methods, especially convolutional neural networks (CNNs) for detection of COVID-19 cases using chest CT scans. Most of the state-of-the-art models demand a huge amount of parameters which often suffer from overfitting in the presence of limited training samples such as chest CT data and thereby, reducing the detection performance. To handle these issues, in this paper, a lightweight multi-scale CNN called LiMS-Net is proposed. The LiMS-Net contains two feature learning blocks where, in each block, filters of different sizes are applied in parallel to derive multi-scale features from the suspicious regions and an additional filter is subsequently employed to capture discriminant features. The model has only 2.53M parameters and therefore, requires low computational cost and memory space when compared to pretrained CNN architectures. Comprehensive experiments are carried out using a publicly available COVID-19 CT dataset and the results demonstrate that the proposed model achieves higher performance than many pretrained CNN models and state-of-the-art methods even in the presence of limited CT data. Our model achieves an accuracy of 92.11% and an F1-score of 92.59% for detection of COVID-19 from CT scans. Further, the results on a relatively larger CT dataset indicate the effectiveness of the proposed model. © 2023 Association for Computing Machinery.

Encephalitis or Stroke? A Case Report of Thalamic Stroke in COVID Era

Introduction: Since 2019, COVID-19 pneumonia caused by SARS-CoV-2 virus has led to a worldwide pandemic. Since then, various neurological manifestations of COVID-19 pneumonia have been reported. Neurological manifestations include headache, anosmia, seizures, and altered mental status. In some cases, it presents as stroke, encephalitis, and neuropathy. Artery of Percheron (AOP) is a variant in the posterior circulation. Here, a single artery arises from the posterior cerebral artery p1 segment. It supplies bilateral thalamus with or without midbrain. Thrombosis in this artery leads to clinical symptoms like reduced level of consciousness, altered mental status, and memory impairment. Case Report: Here, we present a case who presented with fever and altered sensorium without any focal neurological deficits and without known risk factors for stroke. His COVID-19 PCR was positive. He was initially diagnosed as COVID-19 pneumonia with encephalitis and was started on treatment for the same. His initial CT brain and lumbar puncture were normal. The next day, when MRI brain with and without contrast was done, the thalamic stroke due to AOP infarction was diagnosed and appropriate treatment for stroke was initiated. Discussion(s): Many patients miss the window for thrombolysis because of variable presentation in clinical symptoms with negative imaging. It is also difficult to assess the time of onset of stroke in this varied presentation. Our patient had fever and cough for 2 days and had altered mental status since the morning of admission. During hospital stay, he developed bilateral third nerve palsy. This case also highlights the importance of detailed evaluation in COVID-19 patients with neurological complaints. This helps to avoid delays in treatment and to improve clinical outcomes. As our knowledge of COVID-19 and its varied neurological manifestations evolve, we need to be prepared for more atypical presentation to facilitate timely interventions.Copyright © 2022 The Author(s). Published by S. Karger AG, Basel.

GDenseMNet: Global Dense Multiscale Feature Learning Network for Efficient COVID-19 Detection in CT Images

Accurate and rapid diagnosis of COVID-19 is crucial for curbing its fast spread across the globe, with constant mutations leading to newer variants. Recent studies have exhibited that chest CT scans manifest clear radiological findings for the COVID-19 infected patients. Convolutional neural networks (CNN) have been used considerably for COVID-19 diagnosis;however, most CNN architectures demand a huge amount of parameters, resulting in overfitting on limited training data and a slower inference. Further, residual and densely connected neural networks such as ResNet and DenseNet have been proven to strengthen feature extraction and feature propagation but fail to fully discover both local and global representations. Moreover, few linearly stacked networks fall short in capturing and preserving multiscaled features from various receptive fields. This paper proposes a new CNN architecture called global dense multiscale feature learning network (GDenseMNet) for COVID-19 detection from CT images that effectively incorporates global dense connections while capturing multiscaled features. The GDenseMNet model comprises multiscale local feature extraction (MLF) blocks that capture local features of various size receptive fields using multiple filters and residual skip connections. The global dense connections between these blocks further enable global feature learning capability. The proposed architecture is lightweight, end-to-end learnable, and validated using the SARS-CoV-2 CT-Scan dataset. Experimental results demonstrate that the GDenseMNet model achieves promising detection performance compared to state-of-the-art CNN approaches and hence, it can be utilized as an effective tool real-time COVID-19 diagnosis. © 2022 IEEE.

The mental health of the health care professionals in India during the COVID-19 pandemic: a cross-sectional study

The COVID-19 pandemic has resulted in dramatic challenges to healthcare systems worldwide. There has been an increased awareness to protect frontline workers from COVID-19 exposure and its consequences. To assess the prevalence of healthcare professionals in India during the COVID-19, a cross-sectional web-based survey was conducted with healthcare professionals from medical colleges and hospitals from different states across the country. The study comprised 772 healthcare professionals aged >= 18 years. The main outcome measures studied were anxiety, depression, and stress. Among the healthcare professionals, 37.17%, 33.68%, and 23.7% were reported to have anxiety, depression, and stress respectively. The physicians, female, aged population, and professionals sleeping less than 7 hours are more prone to psychological problems. The results of this study predict the high levels of anxiety, depression, and stress among healthcare professionals in different states of India. Increased COVID-19 cases, high pressure, workload, and lack of training are the main reasons for the psychological problems in healthcare professionals. Proper strategies must be followed in healthcare settings to reduce the burden of stress.

A Prospective Survey to Understand the Preferences and Perspectives of Patients with Hematological Malignancies in a Tertiary Cancer Care Setting in India (CANCOV SURVEY)

Introduction: From its emergence in China on 31 st December 2019, the COVID-19 infection has spread to affect more than 185 million people across the world with approximately 4 million deaths. A systematic review and meta-analysis which included various studies across the world showed that the risk of mortality in cancer patients with COVID-19 infection is 21.1% and the risk of severe disease and mortality due to COVID-19 appears to be higher in patients with hematological malignancies likely due to immunosuppression induced by both the underlying disease and intensive treatment. The experts suggest individualization of treatment based on the prevalence of COVID-19 infection, available infrastructure and social support. Guidelines are driven by opinion from a clinician's perspective. There is a need to evaluate a patient's preference in the present situation when they are faced with the dual problem of cancer and a potentially life-threatening infection. Purpose of study: To document the patients preferences and perspectives using a structured questionnaire when they are on cancer-directed chemo/immune or targeted therapy or treatment naive in our hospital during the current COVID-19 pandemic. Objectives: The primary objective was to determine the proportion of patients who opt to continue on full intensity therapy. The secondary objectives were - to study the factors that lead to treatment discontinuation or dose reduction, to study the level of perceived risk at which patients opt for treatment discontinuation or dose reduction, to study the preferences for treatment continuation in different scenarios (COVID-19 adverse event and different relapse risk) (table 2 and 3) and to understand the difference in preferences for therapy between patients and oncologists/hematologists. Material and methods: This prospective survey was conducted between July 10, 2020 and October 16, 2020. A preconceived standard questionnaire was administered to each patient along with their caregivers (Figure 1). Along with this, we subjected the survey questionnaire separately to the set of medical oncologists/hematologists who were not a part of the patient's treating team and the responses were recorded and studied. Sample Size Assuming that 50% of the patients will continue the full intensity therapy, a sample of 203 will produce a two-sided 90% confidence interval with a precision of 12%. Considering a non-response proportion of 5%, a sample size of 213 was required to achieve primary objective. Results: A total of 200 patients were enrolled in this study with male to female ratio of 1.9:1 and a median age of 42 years (15- 78). Most common hematological malignancy in our study is acute leukemia (29%) followed by CML (23%), NHL (22%), multiple myeloma (16%). Baseline details are represented in Table 1. In this study, 47% patients were willing to receive full intensity chemotherapy (95% CI: 40.4 -54.7). Nature of disease (slow growing vs fast growing) and the intent of treatment (cure vs control of disease) were shown to significantly affect preferences of patients. There was no impact of various socio-economic or logistic factors in their preference for therapy. As high as 50% of the patients were willing to accept only 5% risk of covid 19 related complications to receive full intensity therapy. The acceptable risk of relapse over and above the baseline to receive lesser intensity chemotherapy was 5% for almost 1/3 rd of the patients. If covid related complications are mild, 40% of patients are ready to accept only 1 % risk of relapse to receive lesser intensity chemotherapy. As the risk of covid related complications increases from mild to severe, almost 50% of the patients are ready to accept ≥ 20% risk of relapse to receive lesser intensity chemotherapy (table 4). There was a statistically significant disagreement between physician and patient responses at 5%, 20%, 30% and 40% risk of covid related complications to receive full intensity therapy. When we consider the risk of relapse if lesser intensity therapy is opted, patient and physician responses are in good agreement at 1, 5, 10 and 20% risk levels. Conclusion: Almost 50% of patients are willing to opt for reduced intensity therapy because of fear of covid related complications and there is significant disagreement between patient and physician perspectives in certain clinical contexts. [Formula presented] Disclosures: No relevant conflicts of interest to declare.