Deep Learning Framework for Optimizing Early Detection of Measles Using Transfer Learning

Nouman Saleem; Anam Ishaq; Malaika Riaz; Tanzeela Kousar; Aqsa Jameel; Muhammad Bilal; Sobia Aslam; Qurat ul Ain; Komal Rani Narejo; Humaira Anwar; Saleem Ullah

doi:10.70749/ijbr.v2i02.308

Authors

Nouman Saleem Faculty of Information Technology, Khwaja Fareed University of Engineering and IT, Rahim Yar Khan, Punjab, Pakistan.
Anam Ishaq Faculty of Information Technology, Khwaja Fareed University of Engineering and IT, Rahim Yar Khan, Punjab, Pakistan.
Malaika Riaz Faculty of Information Technology, Khwaja Fareed University of Engineering and IT, Rahim Yar Khan, Punjab, Pakistan.
Tanzeela Kousar Institute of Computer Science & IT, The Women University, Multan, Punjab, Pakistan.
Aqsa Jameel Institute of Computer Science & IT, The Women University, Multan, Punjab, Pakistan.
Muhammad Bilal Torch Solutions, Lahore, Punjab, Pakistan.
Sobia Aslam Govt Girls High School, Mankiala Muslim GK, Rawalpindi, Punjab, Pakistan.
Qurat ul Ain Department of Information Technology, The Islamia University of Bahawalpur, Punjab, Pakistan.
Komal Rani Narejo School of Computer and Artificial Intelligence, Zhengzhou University, China.
Humaira Anwar Faculty of Information Technology, Khwaja Fareed University of Engineering and IT, Rahim Yar Khan, Punjab, Pakistan.
Saleem Ullah Faculty of Information Technology, Khwaja Fareed University of Engineering and IT, Rahim Yar Khan, Punjab, Pakistan.

DOI:

https://doi.org/10.70749/ijbr.v2i02.308

Keywords:

Deep Learning, Early Detection, Measles, Transfer Learning, Framework Optimization

Abstract

Measles is a highly infectious viral disease that can have serious health consequences. Accurate and early diagnosis is crucial. This study aims to enhance automated classification and early detection of this disease. To address the class imbalance, we augmented the dataset of normal images. Spatial features were extracted using convolutional neural networks, and traditional classifiers, including support vector machine, Random Forest, logistic regression, and k-nearest neighbors were applied to these features. Initial classification accuracy based solely on spatial features was as follows: Random Forest 63%, SVM 63%, KNN 60%, and Logistic Regression 63%. Through 10-fold cross-validation, mean accuracies were recorded as 65% for RF, 62% for SVM, 60% for KNN, and 61% for LR. Despite these initial results, the implementation of transfer learning led to significant improvements. By extracting probabilistic features from spatial features using RF and KNN models and concatenating these derived features, classification accuracy was substantially enhanced. The improved model achieved 99% accuracy for RF, SVM, and LR, with KNN reaching 98%. Cross-validation confirmed the robustness of the models, with a mean accuracy of approximately 98% and minimal standard deviations of 0.01. The findings demonstrate that combining transfer learning with traditional classifiers improves the efficiency and accuracy of lesion images. This approach shows significant potential for clinical applications.

Downloads

Download data is not yet available.

References

Kondamudi, N. P., & Waymack, J. R. (2024). Measles. PubMed; StatPearls Publishing. https://www.ncbi.nlm.nih.gov/books/NBK448068

Misin, A., Antonello, R. M., Di Bella, S., Campisciano, G., Zanotta, N., Giacobbe, D. R., Comar, M., & Luzzati, R. (2020). Measles: An Overview of a Re-Emerging Disease in Children and Immunocompromised Patients. Microorganisms, 8(2), 276. https://doi.org/10.3390/microorganisms8020276

Congera, P., Maraolo, A. E., Parente, S., Schiano Moriello, N., Bianco, V., & Tosone, G. (2020). Measles in pregnant women: A systematic review of clinical outcomes and a meta-analysis of antibodies seroprevalence. Journal of Infection, 80(2), 152-160. https://doi.org/10.1016/j.jinf.2019.12.012

Measles: Practice essentials, background, pathophysiology. (2024, May 2). Diseases & Conditions - Medscape Reference. https://emedicine.medscape.com/article/966220-overview

Inthiyaz, S., Altahan, B. R., Ahammad, S. H., Rajesh, V., Kalangi, R. R., Smirani, L. K., Hossain, M. A., & Rashed, A. N. (2023). Skin disease detection using deep learning. Advances in Engineering Software, 175, 103361. https://doi.org/10.1016/j.advengsoft.2022.103361

Kundu, D., Rahman, M. M., Rahman, A., Das, D., Siddiqi, U. R., Alam, M. G., Dey, S. K., Muhammad, G., & Ali, Z. (2024). Federated deep learning for Monkeypox disease detection on GAN-augmented dataset. IEEE Access, 12, 32819-32829. https://doi.org/10.1109/access.2024.3370838

Ariansyah, M. H., Winarno, S., & Sani, R. R. (2023). Monkeypox and measles detection using CNN with VGG-16 transfer learning. Journal of Computing Research and Innovation, 8(1), 32-44. https://doi.org/10.24191/jcrinn.v8i1.340

Shah, K., Solanki, M., Vadi, A., Goel, P., & Ramoliya, D. (2024). Skin disease classification using pre-trained convolution neural network with transfer learning. 2024 3rd International Conference for Innovation in Technology (INOCON), 1-7. https://doi.org/10.1109/inocon60754.2024.10511794

Shareef, M. M., Sunitha, G., Prasad Sanaboina, S. V., Sireesha, M., Reddy Madhavi, K., Antharam, G., & Kumar, V. N. (2024). Measles detection using deep learning. Lecture Notes in Networks and Systems, 381-389. https://doi.org/10.1007/978-981-99-9707-7_36

Naveen, C. V., Abhiram, G., Aneesh, V., Kakulapati, V., & Kumar, K. (2023). Monkeypox detection using transfer learning, ResNet50, Alex net, ResNet18 & Custom CNN model. Asian Journal of Advanced Research and Reports, 17(5), 7-13. https://doi.org/10.9734/ajarr/2023/v17i5480

Singh, U., & Songare, L. S. (2022). Analysis and detection of Monkeypox using the GoogLeNet model. 2022 International Conference on Automation, Computing and Renewable Systems (ICACRS), 1000-1008. https://doi.org/10.1109/icacrs55517.2022.10029125

Pramanik, A., Chowdhury, F., Sultana, S., Rahman, M. M., Bijoy, M. H., & Rahman, M. S. (2023). Monkeypox detection from various types of poxes: A deep learning approach. 2023 IEEE 8th International Conference for Convergence in Technology (I2CT), 1-7. https://doi.org/10.1109/i2ct57861.2023.10126223

Gyebi, R., Okyere, G. A., Nakua, E. K., Aseidu-Bekoe, F., Nti, J. S., Ansah, E. O., & Opoku, F. A. (2023). Prediction of measles patients using machine learning classifiers: A comparative study. Bulletin of the National Research Centre, 47(1). https://doi.org/10.1186/s42269-023-01079-w

Ahsan, M. M., Uddin, M. R., Ali, M. S., Islam, M. K., Farjana, M., Sakib, A. N., Momin, K. A., & Luna, S. A. (2023). Deep transfer learning approaches for Monkeypox disease diagnosis. Expert Systems with Applications, 216, 119483. https://doi.org/10.1016/j.eswa.2022.119483

Campana, M. G., Colussi, M., Delmastro, F., Mascetti, S., & Pagani, E. (2024). A transfer learning and explainable solution to detect mpox from smartphones images. Pervasive and Mobile Computing, 98, 101874. https://doi.org/10.1016/j.pmcj.2023.101874

Uysal, F. (2023). Detection of Monkeypox disease from human skin images with a hybrid deep learning model. Diagnostics, 13(10), 1772. https://doi.org/10.3390/diagnostics13101772

Monkeypox skin images dataset (MSID). (n.d.). Kaggle: Your Machine Learning and Data Science Community. https://www.kaggle.com/datasets/sujaykapadnis/monkeypox-skin-images-dataset-msid

Thorat, R., & Gupta, A. (2024). Transfer learning-enabled skin disease classification: The case of monkeypox detection. Multimedia Tools and Applications, 83(35), 82925-82943. https://doi.org/10.1007/s11042-024-18750-7

Meena, G., Mohbey, K. K., Kumar, S., & Lokesh, K. (2023). A hybrid deep learning approach for detecting sentiment polarities and knowledge graph representation on monkeypox tweets. Decision Analytics Journal, 7, 100243. https://doi.org/10.1016/j.dajour.2023.100243

Olasunkanmi, M. (2018). The Effectiveness of Disease Prediction in Enhancing Patient Satisfaction at the Community Level. Journal of Coastal Life Medicine, 6, 01-05. https://jclmm.com/index.php/journal/article/view/1

Jain, D. K., Gupta, K., Bajaj, V., & Hussain, A. (2024). Multi-model deep learning system for screening human Monkeypox using skin images. https://doi.org/10.22541/au.171015937.76129301/v1

Alcalá-Rmz, V., Villagrana-Bañuelos, K. E., Celaya-Padilla, J. M., Galván-Tejada, J. I., Gamboa-Rosales, H., & Galván-Tejada, C. E. (2022). Convolutional neural network for Monkeypox detection. Lecture Notes in Networks and Systems, 89-100. https://doi.org/10.1007/978-3-031-21333-5_9

García Espinosa, E.; Ruiz Castilla, J.; García Lamont, F. Comparison of artificial vision algorithms in the classification of skin diseases using neural networks. Abstraction and Application. In press.

Chen, C., Zhu, J., & Zeng, Z. (2022). Use of ultrasound to observe mycosis Fungoides: A case report and Reviewof literature. Current Medical Imaging Formerly Current Medical Imaging Reviews, 18(7), 771-775. https://doi.org/10.2174/1573405617666211208121419

Li, R., Peng, L., Zhang, J., Zeng, H., Li, Z., & Wang, C. (2024). Clinical features, diagnosis, treatment, and prognosis of heparin-induced Bullous hemorrhagic dermatosis. Dermatologic Therapy, 2024, 1-6. https://doi.org/10.1155/2024/1372188

Abbas, M. A., Munir, K., Raza, A., Samee, N. A., Jamjoom, M. M., & Ullah, Z. (2024). Novel transformer based contextualized embedding and probabilistic features for depression detection from social media. IEEE Access, 12, 54087-54100. https://doi.org/10.1109/access.2024.3387695

Chen, C., Zhu, J., & Zeng, Z. (2022). Use of ultrasound to observe mycosis Fungoides: A case report and Reviewof literature. Current Medical Imaging Formerly Current Medical Imaging Reviews, 18(7), 771-775. https://doi.org/10.2174/1573405617666211208121419

Weiss, K., Khoshgoftaar, T. M., & Wang, D. (2016). A survey of transfer learning. Journal of Big Data, 3(1). https://doi.org/10.1186/s40537-016-0043-6

Iqbal, S., Qureshi, A. N., Alhussein, M., Aurangzeb, K., Choudhry, I. A., & Anwar, M. S. (2024). Hybrid deep spatial and statistical feature fusion for accurate MRI brain tumor classification. Frontiers in Computational Neuroscience, 18. https://doi.org/10.3389/fncom.2024.1423051

Naseer, A., Amjad, M., Raza, A., Munir, K., Samee, N. A., & Alohali, M. A. (2024). A novel transfer learning approach for detection of pomegranates growth stages. IEEE Access, 12, 27073-27087. https://doi.org/10.1109/access.2024.3365356