article · Heliyon
Automated disease assessment schemes using deep learning can alleviate diagnostic burdens by detecting COVID-19 in lung CT scans. A lightweight disease assessment scheme has been developed using pre-trained deep learning methods to analyse CT slices with reduced complexity. The system processes images using Shannon's thresholding, extracts deep features with lightweight models, and refines these features using the Brownian Butterfly Algorithm. Classification is conducted through three-fold cross-validation across individual, fused, and ensemble feature sets. Testing on a lung CT database shows that the scheme achieves 93.80 percent accuracy using individual features, improving to 96.00 percent with fused features. Combining ensemble features yields the highest accuracy at 99.10 percent, demonstrating that the lightweight feature optimisation process can deliver reliable COVID-19 detection on the evaluated dataset.
Automated analysis of lung CT scans helps lessen the diagnostic workload placed on healthcare systems during medical emergencies. By pairing lightweight deep learning architectures with nature-inspired feature optimisation, high detection rates can be achieved without the resource burden typically required by complex artificial intelligence models.
The method could eventually assist radiologists and diagnostic software providers by automating COVID-19 detection from lung CT slices. Its lightweight architecture suggests potential suitability for clinical environments with constrained computing hardware. However, because the abstract reports validation only on a selected CT database using three-fold cross-validation, the technology remains early-stage research requiring extensive clinical testing before commercial use.
AI-generated from the published abstract. Always read the original work before citing.
Several deep-learning assisted disease assessment schemes (DAS) have been proposed to enhance accurate detection of COVID-19, a critical medical emergency, through the analysis of clinical data. Lung imaging, particularly from CT scans, plays a pivotal role in identifying and assessing the severity of COVID-19 infections. Existing automated methods leveraging deep learning contribute significantly to reducing the diagnostic burden associated with this process. This research aims in developing a simple DAS for COVID-19 detection using the pre-trained lightweight deep learning methods (LDMs) applied to lung CT slices. The use of LDMs contributes to a less complex yet highly accurate detection system. The key stages of the developed DAS include image collection and initial processing using Shannon's thresholding, deep-feature mining supported by LDMs, feature optimization utilizing the Brownian Butterfly Algorithm (BBA), and binary classification through three-fold cross-validation. The performance evaluation of the proposed scheme involves assessing individual, fused, and ensemble features. The investigation reveals that the developed DAS achieves a detection accuracy of 93.80% with individual features, 96% accuracy with fused features, and an impressive 99.10% accuracy with ensemble features. These outcomes affirm the effectiveness of the proposed scheme in significantly enhancing COVID-19 detection accuracy in the chosen lung CT database.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1016/j.heliyon.2024.e27509
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.
