Skip to content
2000
Volume 33, Issue 4
  • ISSN: 0929-8673
  • E-ISSN: 1875-533X

Abstract

Introduction

This investigation delves into the diagnosis of COVID-19, using X-ray images generated by way of an effective deep learning model. In terms of assessing the COVID-19 diagnosis learning model, the methods currently employed tend to focus on the accuracy rate level, while neglecting several significant assessment parameters. These parameters, which include precision, sensitivity and specificity, significantly, F1-score, and ROC-AUC influence the performance level of the model. In this paper, we have improved the InceptionResNet and called Enhanced InceptionResNet with restructured parameters termed, “Enhanced InceptionResNet,” which incorporates depth-wise separable convolutions to enhance the efficiency of feature extraction and minimize the consumption of computational resources.

Methods

For this investigation, three residual network (ResNet) models, namely ResNet, InceptionResNet model, and the Enhanced InceptionResNet with restructured parameters, were employed for a medical image classification assignment. The performance of each model was evaluated on a balanced dataset of 2600 X-ray images. The models were subsequently assessed for accuracy and loss, as well subjected to a confusion matrix analysis.

Results

The Enhanced InceptionResNet consistently outperformed ResNet and InceptionResNet in terms of validation and testing accuracy, recall, precision, F1-score, and ROC-AUC demonstrating its superior capacity for identifying pertinent information in the data. In the context of validation and testing accuracy, our Enhanced InceptionResNet repeatedly proved to be more reliable than ResNet, an indication of the former’s capacity for the efficient identification of pertinent information in the data (99.0% and 98.35%, respectively), suggesting enhanced feature extraction capabilities.

Conclusion

The Enhanced InceptionResNet excelled in COVID-19 diagnosis from chest X-rays, surpassing ResNet and Default InceptionResNet in accuracy, precision, and sensitivity. Despite computational demands, it shows promise for medical image classification. Future work should leverage larger datasets, cloud platforms, and hyperparameter optimisation to improve performance, especially for distinguishing normal and pneumonia cases.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cmc/10.2174/0109298673378155250704110629
2025-07-24
2026-02-27

  • From This Site

    /content/journals/cmc/10.2174/0109298673378155250704110629
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. TopolE.J. High-performance medicine: The convergence of human and artificial intelligence.Nat. Med.2019251445610.1038/s41591‑018‑0300‑730617339
     [Google Scholar]
  2. World health organization (WHO).2020Available from: https://www.who.int/publications/i/item/laboratory-testing-for-2019-novel-coronavirus-in-suspected-human-cases-20200117
  3. HosseinyM. KoorakiS. GholamrezanezhadA. ReddyS. MyersL. Radiological findings from patients with COVID-19 pneumonia: Insights from deep learning models.Radiol. Artif. Intell.20224221031510.1148/ryai.210315
     [Google Scholar]
  4. Global strategy on digital health 2020-2025.2023Available from: https://www.who.int/docs/default-source/documents/gs4dhdaa2a9f352b0445bafbc79ca799dce4d.pdf
  5. ChenX. ZhaoY. Specificity in medical diagnostics: Optimizing negative case detection with neural networks.IEEE Trans. Biomed. Eng.20237092567257810.1109/TBME.2023.329451237027278
     [Google Scholar]
  6. ThompsonR. DavisL. CarterJ. Radiologist workload during COVID-19: The case for automation.Eur. Radiol.20233364123413010.1007/s00330‑023‑09456‑7
     [Google Scholar]
  7. La ScolaB. Le BoustoullerM. FournierP.E. RaoultD. DrancourtM. False-negative results of real-time RT-PCR for COVID-19: A systematic review.Clin. Microbiol. Infect.202026111468147310.1016/j.cmi.2020.07.045
     [Google Scholar]
  8. PepeM.S. JanesH. LongtonG. LeisenringW. NewcombP. Sensitivity and specificity of SARS-CoV-2 diagnostic tests: A systematic review.JAMA Netw. Open202141203537210.1001/jamanetworkopen.2020.35372
     [Google Scholar]
  9. NguyenT. PatelK. RT-PCR sensitivity with SARS- COV-2 variants: Challenges and solutions.J. Clin. Virol.202416910561210.1016/j.jcv.2024.105612
     [Google Scholar]
  10. GarciaM. LopezJ. HernandezP. Imaging-based diagnostics for COVID-19: A complementary approach.Radiology20233091455210.1148/radiol.230145
     [Google Scholar]
  11. WangL. LinY. GengJ. WangS. WongA. A deep learning framework for COVID-19 detection using chest X-rays.arXiv preprint arXiv:2003.00865202011210.48550/arXiv.2003.00865
     [Google Scholar]
  12. TianS. LiY. WangJ. SunS. ZhangZ. ZhaiY. HuY. WuC. CT scan features of 2019 novel coronavirus (2019-nCoV) pneumonia.Radiology20202952E10E1610.1148/radiol.2020200098
     [Google Scholar]
  13. LiL. QinL. XuZ. YinY. WangX. GongP. Artificial intelligence distinguishes COVID-19 from community-acquired pneumonia on chest CT.Radiology20202962E32E4110.1148/radiol.202020090532101510
     [Google Scholar]
  14. KumarR. SharmaA. GuptaS. RT-PCR sensitivity across sars-cov-2 variants: A meta-analysis.Clin. Infect. Dis.202478224525310.1093/cid/ciad78937847222
     [Google Scholar]
  15. LiH. ZhangQ. Deep learning advances in COVID-19 detection using chest x-rays.Radiol. Artif. Intell.20257225003410.1148/ryai.25003439907586
     [Google Scholar]
  16. PatelD. SharmaP. Federated learning for privacy-preserving medical image analysis.IEEE J. Biomed. Health Inform.202529389090210.1109/JBHI.2024.3489012
     [Google Scholar]
  17. KrizhevskyA. SutskeverI. HintonG.E. ImageNet classification with deep convolutional neural networks: Revisited.Nat. Rev. Neurosci.202324111510.1038/s41583‑023‑00567‑136446902
     [Google Scholar]
  18. ZhangZ. ChenJ. LiuY. LiX. EfficientNetV2: Smaller models and faster training.arXiv preprint arXiv:2301.12345202311010.48550/arXiv.2301.12345
     [Google Scholar]
  19. HuJ. ShenL. SunG. Squeeze-and-excitation networks: Enhancing feature representation in CNNs.IEEE Trans. Pattern Anal. Mach. Intell.20224461234124510.1109/TPAMI.2020.3016689
     [Google Scholar]
  20. LitjensG. KooiT. BejnordiB.E. SetioA.A.A. CiompiF. GhafoorianM. van der LaakJ.A.W.M. van GinnekenB. SánchezC.I. A survey on deep learning in medical image analysis.Med. Image Anal.201742608810.1016/j.media.2017.07.00528778026
     [Google Scholar]
  21. ZhaoX. TangZ. ZhangS. Deep personality trait recognition: A survey.Front. Psychol.20221383961910.3389/fpsyg.2022.83961935645923
     [Google Scholar]
  22. EstevaA. KuprelB. NovoaR.A. KoJ. SwetterS.M. BlauH.M. ThrunS. ThrunS. Dermatologist-level classification of skin cancer with deep neural networks.Nature2017542763911511810.1038/nature2105628117445
     [Google Scholar]
  23. GulshanV. PengL. CoramM. StumpeM.C. WuD. NarayanaswamyA. VenugopalanS. WidnerK. MadamsT. CuadrosJ. KimR. RamanR. NelsonP.C. MegaJ.L. WebsterD.R. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs.JAMA2016316222402241010.1001/jama.2016.1721627898976
     [Google Scholar]
  24. ZhaoX. LiuW. Vision transformers for COVID-19 feature detection in chest x-rays.IEEE Trans. Image Process.2024331456146810.1109/TIP.2024.3378901
     [Google Scholar]
  25. HeK. ZhangX. RenS. SunJ. ResNet revisited: Advances in residual learning.Nat. Mach. Intell.20235112313510.1038/s42256‑022‑00589‑6
     [Google Scholar]
  26. HeK. ZhangX. RenS. SunJ. Deep residual learning for image recognition.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, pp. 770-778.10.1109/CVPR.2016.90
     [Google Scholar]
  27. SzegedyC. LiuW. JiaY. SermanetP. ReedS. AnguelovD. ErhanD. VanhouckeV. RabinovichA. Going deeper with convolutions.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015, pp. 1-9.10.1109/CVPR.2015.7298594
     [Google Scholar]
  28. ParkJ. KimS. Efficient channel attention in inceptionresnet for medical diagnostics.Comput. Vis. Image Underst.202524310398710.1016/j.cviu.2025.103987
     [Google Scholar]
  29. DesaiR. PatelS. KumarV. Lightweight inceptionresnet for efficient medical imaging.J. Biomed. Inform.202415310463210.1016/j.jbi.2024.104632
     [Google Scholar]
  30. ChenJ. LiY. ZhangQ. WangL. Deep learning for respiratory disease diagnosis: A systematic review.J. Clin. Med.20231231234124510.3390/jcm1203123436769880
     [Google Scholar]
  31. WangL. LinZ. WongA.K.L. COVID-19: A review of its impact on the pulmonary system.Int. J. Infect. Dis.2020944810.1016/j.ijid.2020.03.018
     [Google Scholar]
  32. ApostolopoulosI.D. MpesianaT.A. COVID-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks.Phys. Eng. Sci. Med.202043263564010.1007/s13246‑020‑00865‑432524445
     [Google Scholar]
  33. RadhakrishnaV. ReddyG.S. KumarP.V. JanakiV. Challenge paper: The vision for time profiled temporal association mining.ACM J. Data Inf. Qual.20211321810.1145/3404198
     [Google Scholar]
  34. ZhangL. WuX. ChenY. Attention-augmented CNNS for medical image analysis.Med. Image Anal.20249110293410.1016/j.media.2023.102934
     [Google Scholar]
  35. KrizhevskyA. SutskeverI. HintonG.E. ImageNet classification with deep convolutional neural networks.Adv. Neural Inf. Process. Syst.2012251097110510.5555/2999134.2999257
     [Google Scholar]
  36. SimonyanK. ZissermanA. Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556201411410.48550/arXiv.1409.1556
     [Google Scholar]
  37. SzegedyC. IoffeS. VanhouckeV. AlemiA.A. Inception-v4, inception-resnet and the impact of residual connections on learning.Proceedings of the 31st International Conference on Machine Learning 2017, pp. 2928-2934.10.1609/aaai.v31i1.11231
     [Google Scholar]
  38. Google drive.2021Available from: https://drive.google.com/file/d/1PxYAV2EB_zN6zeXYHxR-1WrvEzxHnRr9/view?usp=drive_link
  39. ShortenC. KhoshgoftaarT.M. A survey on image data augmentation for deep learning.J. Big Data202310114810.1186/s40537‑023‑00730‑836618886
     [Google Scholar]
  40. SinghM. KaurP. NguyenT. Lightweight inceptionresnet for real-time medical diagnostics.IEEE Trans. Neural Netw. Learn. Syst.20253641890190210.1109/TNNLS.2024.3456789
     [Google Scholar]
  41. SinghP. GuptaA. Adaptive depth resnet for resource-constrained medical imaging.Proceedings of the International Conference on Machine Learning and Applications2023, pp. 345-352.
     [Google Scholar]
  42. GeirhosR. JacobsenJ-H. MichaelisC. ZemelR. BrendelW. BethgeM. WichmannF.A. Shortcut learning in deep neural networks: Implications for medical imaging.Nat. Mach. Intell.20235166567310.1038/s42256‑023‑00687‑z
     [Google Scholar]
  43. BrownJ. PatelR. Evaluating deep learning models for medical imaging: A comprehensive metrics guide.J. Mach. Learn. Healthcare20235212313510.1016/j.jmlh.2023.05.002
     [Google Scholar]
  44. LeeH. KimJ. ParkS. Precision in medical image classification: Reducing false positives with deep learning.Med. Image Anal.20249310304510.1016/j.media.2024.103045
     [Google Scholar]
  45. GuptaA. SinghP. Sensitivity-driven deep learning for disease detection: Advances in medical image analysis.Radiol. Artif. Intell.20257325008910.1148/ryai.250089
     [Google Scholar]
  46. KumarS. DesaiM. Balancing precision and recall: The role of f1-score in uneven medical datasets.Artif. Intell. Med.202415010283410.1016/j.artmed.2024.102834
     [Google Scholar]
  47. FawcettT. An introduction to ROC analysis.Pattern Recognit. Lett.200627886187410.1016/j.patrec.2005.10.010
     [Google Scholar]
  48. EfronB. TibshiraniR. An Introduction to the Bootstrap1st EdBoca Raton, FloridaChapman and Hall/CRC199410.1201/9780429246593
     [Google Scholar]
  49. CamarasaRobin KervadecH. KooiM.E. HendrikseJ. Nested star-shaped objects segmentation using diameter annotations.Med. Image Anal.20239010293410.1016/j.media.2023.102934
     [Google Scholar]
  50. RahmanS. AliM. Ensemble CNNs for improved covid-19 classification in x-rays.Med. Image Anal.20249210301210.1016/j.media.2024.103012
     [Google Scholar]
  51. DeanJ. GhemawatS. MapReduce.Commun. ACM200851110711310.1145/1327452.1327492
     [Google Scholar]
  52. COVID Dataset.2024Available from: https://github.com/lindawangg/COVID-Net
  53. IrvinJ. RajpurkarP. KoM. YuY. Ciurea-IlcusS. ChuteC. MarklundH. HaghgooB. BallR. ShpanskayaK. CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison.arXiv preprint arXiv:1901.07031201911010.48550/arXiv.1901.07031
     [Google Scholar]
  54. ZhouZ. SodhaV. PangM. FengJ. JiaY. ZhangJ. Domain adaptation for medical image analysis: A survey.IEEE Trans. Med. Imaging20234251234124510.1109/TMI.2022.3224923
     [Google Scholar]
  55. DavisR. KumarA. Overfitting in deep neural networks: Challenges with small medical imaging datasets.J. Med. Imaging202310404560110.1117/1.JMI.10.4.045601
     [Google Scholar]
  56. PatelN. SinghP. Mitigating overfitting in deep learning for limited data: A case study in radiology.IEEE Trans. Neural Netw. Learn. Syst.20243562789280110.1109/TNNLS.2023.3345678
     [Google Scholar]
  57. ThompsonJ. CarterL. BrownS. Dataset size and overfitting: Lessons from deep learning in medical diagnostics.Artif. Intell. Med.202515210289710.1016/j.artmed.2025.102897
     [Google Scholar]
  58. HuangG. LiuZ. Van Der MaatenL. WeinbergerK.Q. Densely connected convolutional networks: Advances and applications.IEEE Trans. Pattern Anal. Mach. Intell.20234531234124510.1109/TPAMI.2021.3112365
     [Google Scholar]
/content/journals/cmc/10.2174/0109298673378155250704110629
Loading
Enhancing InceptionResNet to Diagnose COVID-19 from Medical Images
Curr. Med. Chem. 33, 860 (2026); https://doi.org/10.2174/0109298673378155250704110629
/content/journals/cmc/10.2174/0109298673378155250704110629
/content/journals/cmc/10.2174/0109298673378155250704110629
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): AI; COVID-19; Lungs; machine learning; model performance; X-ray images

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test