{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:21:34Z","timestamp":1783520494883,"version":"3.55.0"},"reference-count":34,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002645","name":"Sangmyung University","doi-asserted-by":"crossref","award":["2024-A000-0256"],"award-info":[{"award-number":["2024-A000-0256"]}],"id":[{"id":"10.13039\/501100002645","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The coronavirus is highly contagious, making rapid early diagnosis essential. Although deep learning-based diagnostic methods using CT or X-ray images have advanced significantly, they still face limitations in cost, processing time, and radiation exposure. In addition, for the possibility of real-time COVID-19 diagnosis, model lightweighting is required. This study proposes a lightweight deep learning model for COVID-19 diagnosis based on fluorescence images and demonstrates its applicability in embedded environments. To prevent data imbalance caused by noise and experimental variations, images were preprocessed using Gray Scale conversion, CLAHE, and Z-Score normalization to equalize brightness values. Among the tested architectures\u2014VGG, ResNet, DenseNet, and EfficientNet\u2014ResNet152 and VGG13 achieved the highest accuracies of 97.25% and 93.58%, respectively, and were selected for lightweighting. Layer-wise importance was calculated using an imprinting-based method, and less important layers were pruned. The pruned VGG13 maintained its accuracy while reducing model size by 18.9 MB and parameters by 4.2 M. ResNet152 (Prune 39) improved accuracy by 1% while reducing size by 161.5 MB and parameters by 40.22 M. The optimized model achieved 129.97 ms, corresponding to 7.69 frames per second (FPS) on an NPU(Furiosa AI Warboy), proving real-time COVID-19 diagnosis is feasible even on low-power edge devices.<\/jats:p>","DOI":"10.3390\/s26010339","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T10:53:50Z","timestamp":1767610430000},"page":"339","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Real-Time Fluorescence-Based COVID-19 Diagnosis Using a Lightweight Deep Learning System"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1284-8715","authenticated-orcid":false,"given":"Hui-Jae","family":"Bae","sequence":"first","affiliation":[{"name":"Department of Computer Science, Sangmyung University, Seoul 03016, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8916-6431","authenticated-orcid":false,"given":"Jongweon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Sangmyung University, Seoul 03016, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daesik","family":"Jeong","sequence":"additional","affiliation":[{"name":"Gyedang College of General Education, Sangmyung University, Seoul 03016, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"key":"ref_1","unstructured":"(2025, November 10). Coronavirus Disease (COVID-19). Available online: https:\/\/www.who.int\/health-topics\/coronavirus."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Angius, F., Puxeddu, S., Zaimi, S., Canton, S., Nematollahzadeh, S., Pibiri, A., Delogu, I., Alvisi, G., Moi, M.L., and Manzin, A. (2024). SARS-CoV-2 Evolution: Implications for Diagnosis, Treatment, Vaccine Effectiveness and Development. Vaccines, 13.","DOI":"10.3390\/vaccines13010017"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"10715","DOI":"10.1007\/s11033-022-07700-x","article-title":"SARS-CoV-2 Cell Entry beyond the ACE2 Receptor","volume":"49","author":"Alipoor","year":"2022","journal-title":"Mol. Biol. Rep."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jalali, M., Zaborowska, J., and Jalali, M. (2017). The Polymerase Chain Reaction. Basic Science Methods for Clinical Researchers, Elsevier.","DOI":"10.1016\/B978-0-12-803077-6.00001-1"},{"key":"ref_5","unstructured":"(2025, November 10). Real-Time RT-PCR. Available online: https:\/\/dportal.kdca.go.kr\/pot\/www\/CVID19\/INSP\/INSPMET.jsp?seq=TAB22_1."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e63","DOI":"10.1093\/nar\/28.12.e63","article-title":"Loop-Mediated Isothermal Amplification of DNA","volume":"28","author":"Notomi","year":"2000","journal-title":"Nucleic Acids Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1038\/s41551-021-00760-7","article-title":"CRISPR-Based Diagnostics","volume":"5","author":"Kaminski","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"ref_8","first-page":"100628","article-title":"A Deep Learning Framework for Accurate COVID-19 Classification in CT-Scan Images","volume":"19","author":"Kordnoori","year":"2025","journal-title":"Mach. Learn. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhao, M., She, C., Peng, H., Liu, M., and Li, B. (2025). Classification of CT Scan and X-Ray Dataset Based on Deep Learning and Particle Swarm Optimization. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0317450"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"11639","DOI":"10.1038\/s41598-024-61693-0","article-title":"COVID-19 Detection from Chest X-Ray Images Using Transfer Learning","volume":"14","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bani Baker, Q., Hammad, M., Al-Smadi, M., Al-Jarrah, H., Al-Hamouri, R., and Al-Zboon, S.A. (2024). Enhanced COVID-19 Detection from X-Ray Images with Convolutional Neural Network and Transfer Learning. J. Imaging, 10.","DOI":"10.3390\/jimaging10100250"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1847","DOI":"10.1007\/s11845-025-04046-8","article-title":"Radiation Dose Estimation and Lifetime Attributable Risk of Radiation-Induced Cancer from Chest CT in COVID-19 Patients","volume":"194","author":"Mansour","year":"2025","journal-title":"Ir. J. Med. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Paulis, L.E., Schnerr, R.S., Halton, J., Qin, Z.Z., and Chua, A. (2025). Assessment of Scattered and Leakage Radiation from Ultra-Portable X-Ray Systems in Chest Imaging: An Independent Study. PLoS Glob. Public Health, 5.","DOI":"10.1371\/journal.pgph.0003986"},{"key":"ref_14","unstructured":"Singh, S. (2024). CoVScreen: Pitfalls and Recommendations for Screening COVID-19 Using Chest X-Rays. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, R., Jiang, H., Wang, W., and Liu, J. (2025). Optimization Methods, Challenges, and Opportunities for Edge Inference: A Comprehensive Survey. Electronics, 14.","DOI":"10.3390\/electronics14071345"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2411849","DOI":"10.1002\/advs.202411849","article-title":"Plasmon-Driven Gold Nanopillar Multiarrayed Gene Amplification Methodology for the High-Throughput Discrimination of Pathogens","volume":"12","author":"Seo","year":"2025","journal-title":"Adv. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, L., Lei, Z., Xiao, C., Du, Z., Jiang, C., Yuan, X., Hu, Q., Zhai, S., Xu, L., and Liu, C. (2022). AI-Boosted CRISPR-Cas13a and Total Internal Reflection Fluorescence Microscopy System for SARS-CoV-2 Detection. Front. Sens., 3.","DOI":"10.3389\/fsens.2022.1015223"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1021\/acsnano.2c10159","article-title":"Virus Detection and Identification in Minutes Using Single-Particle Imaging and Deep Learning","volume":"17","author":"Shiaelis","year":"2023","journal-title":"ACS Nano"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Elkerdawy, S., Elhoushi, M., Singh, A., Zhang, H., and Ray, N. (2020). To Filter Prune, or to Layer Prune, That Is the Question. arXiv.","DOI":"10.1007\/978-3-030-69535-4_45"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Guerrouj, F.Z. (2025). Quantized Object Detection for Real-Time Inference on Embedded GPU Architectures. Int. J. Adv. Comput. Sci. Appl., 16.","DOI":"10.14569\/IJACSA.2025.0160503"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Chen, J., Gong, C., Wang, T.D., and Seibel, E.J. (2022). Deep-Learning-Based Real-Time and Automatic Target-to-Background Ratio Calculation in Fluorescence Endoscopy for Cancer Detection and Localization. Diagnostics, 12.","DOI":"10.3390\/diagnostics12092031"},{"key":"ref_22","unstructured":"Pizer, S.M., Johnston, R.E., Ericksen, J.P., Yankaskas, B.C., and Muller, K.E. (1990, January 22\u201325). Contrast-Limited Adaptive Histogram Equalization: Speed and Effectiveness. Proceedings of the First Conference on Visualization in Biomedical Computing, Atlanta, GA, USA."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1177\/02537176211046525","article-title":"Z Scores, Standard Scores, and Composite Test Scores Explained","volume":"43","author":"Andrade","year":"2021","journal-title":"Indian J. Psychol. Med."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Maur\u00edcio, J., Domingues, I., and Bernardino, J. (2023). Comparing Vision Transformers and Convolutional Neural Networks for Image Classification: A Literature Review. Appl. Sci., 13.","DOI":"10.3390\/app13095521"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Mela, C.A., and Liu, Y. (2021). Application of Convolutional Neural Networks towards Nuclei Segmentation in Localization-Based Super-Resolution Fluorescence Microscopy Images. BMC Bioinform., 22.","DOI":"10.1186\/s12859-021-04245-x"},{"key":"ref_26","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2018). Densely Connected Convolutional Networks. arXiv.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_29","unstructured":"Tan, M., and Le, Q.V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_30","unstructured":"(2025, November 10). NVIDIA Jetson Nano. Available online: https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-nano\/product-development\/."},{"key":"ref_31","unstructured":"(2025, November 10). Warboy. Available online: https:\/\/furiosa.ai\/warboy."},{"key":"ref_32","unstructured":"(2025, November 11). FuriosaAI NPU and Software Documentation, Version 0.6.3. Available online: https:\/\/developer.furiosa.ai\/docs\/v0.6.3\/ko\/npu\/intro.html?utm_source=chatgpt.com."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Dehmer, M., and Basak, S.C. (2012). Statistical and Machine Learning Approaches for Network Analysis, Wiley. [1st ed.].","DOI":"10.1002\/9781118346990"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"022022","DOI":"10.1088\/1742-6596\/1168\/2\/022022","article-title":"An Overview of Overfitting and Its Solutions","volume":"1168","author":"Ying","year":"2019","journal-title":"J. Phys. Conf. Ser."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/339\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T05:16:55Z","timestamp":1767763015000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/339"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010339"],"URL":"https:\/\/doi.org\/10.3390\/s26010339","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]}}}