AI-Driven COVID-19 Detection and Diagnosis Using Multimodal Medical Imaging and Deep Learning Models

DOI

10.2991/978-94-6239-678-4_14How to use a DOI?

Keywords

AI-driven diagnosis; COVID-19 detection; Deep learning; CNN; Grad-CAM visualization; and Healthcare AI

Abstract

The paper proposes an AI-based scheme of early COVID-19 diagnosis and detection based on multimodal medical imaging, featuring chest X-rays (CXR) and computed tomography (CT). The proposed deep learning architecture (Convolutional neural networks + feature encoders that are transformers) is the one that performs an accurate representation of space and context using convolutional neural networks and transformers that encode the features. The multimodal fusion unit matches dissimilar image attributes to enhance the diagnostic quality and strength. The data includes 12,000 CXR and 8,000 CT images, which have been processed by using adaptive normalization and augmentation. The experimental findings show that the proposed hybrid model has 98.7% accuracy, 97.9% sensitivity, and 98.5% specificity that are higher than existing approach. The GRAD-CAM analysis indicates better localization and readability of the lesion. The strategy is effective in reducing inter-modality deviations and reducing the reliability of automated COVID-19 signs, which contributes to effective triage in medical processes.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Priyanka Sharma
AU  - Varsha Sharma
PY  - 2026
DA  - 2026/05/28
TI  - AI-Driven COVID-19 Detection and Diagnosis Using Multimodal Medical Imaging and Deep Learning Models
BT  - Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)
PB  - Atlantis Press
SP  - 162
EP  - 174
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-678-4_14
DO  - 10.2991/978-94-6239-678-4_14
ID  - Sharma2026
ER  -