article · Multimedia Tools and Applications
Chest computed tomography scans offer a viable route for the early identification of COVID-19 infections. By combining transfer learning with deep convolutional neural networks, computational architectures can classify medical imagery effectively. Using a curated sample of 13,413 scans from the COVIDx dataset, covering both confirmed COVID-19 patients and healthy individuals, multiple pre-trained models were evaluated to distinguish between diseased and normal lungs. Models including ResNet-50, VGG-19, VGG-16, and Inception V3 were trained using binary cross-entropy alongside optimisers designed to prevent overfitting. When evaluated with the Adam optimiser on validation data, these architectures achieved high classification accuracies, with ResNet-50 attaining the strongest result at 99.07 percent. These outcomes confirm that established neural network architectures can enhance automated image classification, providing a foundation for developing rapid, dependable diagnostic tools for respiratory disease identification.
Early and accurate detection of COVID-19 is critical for improving patient outcomes and managing healthcare resources during outbreaks. Chest CT scans provide detailed internal views, and automating their interpretation with reliable machine learning models can assist medical professionals by speeding up diagnosis, reducing diagnostic workloads, and lowering the risk of human error during clinical triage.
The research demonstrates an applied methodology tested on an established retrospective dataset, representing an early to intermediate stage of development. The approach could enable health-tech developers to create automated diagnostic support software for radiologists and clinical hospital staff. Moving towards real-world deployment would require prospective clinical trials and integration into existing hospital picture archiving and communication systems.
AI-generated from the published abstract. Always read the original work before citing.
Abstract This paper explores the use of chest CT scans for early detection of COVID-19 and improved patient outcomes. The proposed method employs advanced techniques, including binary cross-entropy, transfer learning, and deep convolutional neural networks, to achieve accurate results. The COVIDx dataset, which contains 104,009 chest CT images from 1,489 patients, is used for a comprehensive analysis of the virus. A sample of 13,413 images from this dataset is categorised into two groups: 7,395 CT scans of individuals with confirmed COVID-19 and 6,018 images of normal cases. The study presents pre-trained transfer learning models such as ResNet (50), VGG (19), VGG (16), and Inception V3 to enhance the DCNN for classifying the input CT images. The binary cross-entropy metric is used to compare COVID-19 cases with normal cases based on predicted probabilities for each class. Stochastic Gradient Descent and Adam optimizers are employed to address overfitting issues. The study shows that the proposed pre-trained transfer learning models achieve accuracies of 99.07%, 98.70%, 98.55%, and 96.23%, respectively, in the validation set using the Adam optimizer. Therefore, the proposed work demonstrates the effectiveness of pre-trained transfer learning models in enhancing the accuracy of DCNNs for image classification. Furthermore, this paper provides valuable insights for the development of more accurate and efficient diagnostic tools for COVID-19.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s11042-023-17990-3
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
