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.

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.