AI EMPOWERED DIAGNOSIS OF PEMPHIGUS: A MACHINE LEARNING APPROACH FOR AUTOMATED SKIN LESION DETECTION
Mamun Ahmed
Bangladesh Army International University of Science and Technology, Department of Computer Science and Technology (Bangladesh)
https://orcid.org/0000-0002-3980-3981
Salma Binta Islam
Bangladesh Army International University of Science and Technology, Department of Computer Science and Technology (Bangladesh)
https://orcid.org/0009-0004-9975-4861
Aftab Uddin Alif
alifbaiust@gmail.comBangladesh Army International University of Science and Technology, Department of Computer Science and Technology (Bangladesh)
https://orcid.org/0009-0001-8461-1129
Mirajul Islam
Bangladesh Army International University of Science and Technology, Department of Computer Science and Technology (Bangladesh)
https://orcid.org/0009-0006-1215-1422
Sabrina Motin Saima
Bangladesh Army International University of Science and Technology, Department of Computer Science and Technology (Bangladesh)
https://orcid.org/0009-0005-7319-7259
Abstract
Pemphigus is a skin disease that can cause a serious damage to human skin. Pemphigus can result in other issues including painful patches and infected blisters, which can result in sepsis, weight loss, and starvation, all of which can be life-threatening, tooth decay and gum disease. Early prediction of Pemphigus may save us from fatal disease. Machine learning has the potential to offer a highly efficient approach for decision-making and precise forecasting. The healthcare sector is experiencing remarkable advancements through the utilization of machine learning techniques. Therefore, to identify Pemphigus using images, we suggested machine learning-based techniques. This proposed system uses a large dataset collected from various web sources to detect Pemphigus. Augmentation has been applied on our dataset using techniques such as zoom, flip, brightness, distortion, magnitude, height, width to enhance the breadth and variety of the dataset and improve model’s performance. Five popular machine learning algorithms has been employed to train and evaluate model, these are K-Nearest Neighbor (referred to as KNN), Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), and Convolutional Neural Network (CNN). Our outcome indicate that the CNN based model outperformed the other algorithms by achieving accuracy of 93% whereas LR, KNN, RF and DT achieved accuracies of 78%, 70%, 85% and 75% respectively.
Keywords:
pemphigus, blisters, augmentation, CNNReferences
Arduino P. G. et al.: Long-term evaluation of pemphigus vulgaris: a retrospective consideration of 98 patients treated in an oral medicine unit in north-west Italy. Journal of Oral Pathology & Medicine 48(5), 2019, 406–412 [http://doi.org/10.1111/jop.12847].
Google Scholar
Bhadula S. et al.: Machine Learning Algorithms based Skin Disease Detection. International Journal of Innovative Technology and Exploring Engineering – IJITEE 9(2), 2019, 4044-4049 [http://doi.org/10.35940/ijitee.B7686.129219].
Google Scholar
Elngar A. A.: Intelligent System for Skin Disease Prediction using Machine Learning. 3rd International Conference on Smart and Intelligent Learning for Information Optimization 1998, 2021 [http://doi.org/10.1088/1742-6596/1998/1/012037].
Google Scholar
Hashi E. K., Md. Shahid Uz Zaman: Developing a Hyperparameter Tuning Based Machine Learning Approach of Heart Disease Prediction. Journal of Applied Science & Process Engineering 7(2), 2020, 631–647 [http://doi.org/10.33736/jaspe.2639.2020].
Google Scholar
Jonnavithula S. K. et al.: Role of Machine Learning Algorithms Over Heart Diseases Prediction. 2nd International Conference on Sustainable Manufacturing, Materials and Technologies 2292(1), 2020, [http://doi.org/10.1063/5.0030743].
Google Scholar
Kameswara Rao T. et al.: Skin Disease Detection Using Machine Learning. UGC CARE Listed (Group-I) Journal 11(12), 2022, 1593–1604 [http://doi.org/10.48047/IJFANS/V11/I12/171].
Google Scholar
Kumar A., Shetty P., Balipa M., Rao B., Puneeth B., Shravya: An efficient technique to detect skin Disease Using Image Processing. International Conference on Artificial Intelligence and Data Engineering – AIDE, Karkala 2022, 35–40 [http://doi.org/10.1109/AIDE57180.2022.10060001].
Google Scholar
Kumar V. B., Kumar S. S., Saboo V.: Dermatological disease detection using image processing and machine learning. Third International Conference on Artificial Intelligence and Pattern Recognition – AIPR, Lodz, 2016, 1–6 [http://doi.org/10.1109/ICAIPR.2016.7585217].
Google Scholar
Mahesh B.: Machine Learning Algorithms – A Review. International Journal of Science and Research – IJSR 9(1), 2020, 381–386.
Google Scholar
Połap D. et al.: An Intelligent System for Monitoring Skin diseases. Special Issue From Sensors to Ambient Intelligence for Health and Social, 2018 [http://doi.org/10.3390/s18082552].
Google Scholar
Rathod J. et al.: Diagnosis of skin diseases using Convolutional Neural Networks. Second International Conference on Electronics, Communication and Aerospace Technology – ICECA, Coimbatore, 2018, 1048–1051 [http://doi.org/10.1109/ICECA.2018.8474593].
Google Scholar
Rimi T. A. et al.: Derm-NN: Skin Diseases Detection Using Convolutional Neural Network. 4th International Conference on Intelligent Computing and Control Systems – ICICCS. Madurai, 2020, 1205–1209 [http://doi.org/10.1109/ICICCS48265.2020.9120925].
Google Scholar
Sumithra R., Suhilb M., Guruc D. S.: Segmentation and classification of skin lesions for disease diagnosis. Procedia Computer Science 45, 2015, 76–85 [http://doi.org/10.1016/j.procs.2015.03.090].
Google Scholar
American Academy of Dermatology. https://www.aad.org/public/diseases/a-z/pemphigus-symptoms (accessed: 21.01.2023).
Google Scholar
Cleveland Clinic. https://my.clevelandclinic.org/health/diseases/21130-pemphigus (accessed: 20.04.2023)
Google Scholar
DermNet. https://dermnetnz.org/images/pemphigus-vulgaris-images (accessed: 10.01.2023).
Google Scholar
DermNet. https://dermnetnz.org/topics/pemphigus-foliaceus (accessed: 07.02.2023).
Google Scholar
National library of medicine. https://www.ncbi.nlm.nih.gov/books/NBK560860/ (accessed: 29.04.2023)
Google Scholar
NHS. https://www.nhs.uk/conditions/pemphigus-vulgaris/ (accessed: 03.01.2023).
Google Scholar
WebPathology. https://www.webpathology.com/image.asp?n=2&Case=697 (accessed: 20.02.2023).
Google Scholar
Authors
Mamun AhmedBangladesh Army International University of Science and Technology, Department of Computer Science and Technology Bangladesh
https://orcid.org/0000-0002-3980-3981
Authors
Salma Binta IslamBangladesh Army International University of Science and Technology, Department of Computer Science and Technology Bangladesh
https://orcid.org/0009-0004-9975-4861
Authors
Aftab Uddin Alifalifbaiust@gmail.com
Bangladesh Army International University of Science and Technology, Department of Computer Science and Technology Bangladesh
https://orcid.org/0009-0001-8461-1129
Authors
Mirajul IslamBangladesh Army International University of Science and Technology, Department of Computer Science and Technology Bangladesh
https://orcid.org/0009-0006-1215-1422
Authors
Sabrina Motin SaimaBangladesh Army International University of Science and Technology, Department of Computer Science and Technology Bangladesh
https://orcid.org/0009-0005-7319-7259
Statistics
Abstract views: 280PDF downloads: 199
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Most read articles by the same author(s)
- Mamun Ahmed, Sayma Alam Suha, Fahamida Hossain Mahi, Forhad Uddin Ahmed, EVALUATING THE PERFORMANCE OF BITCOIN PRICE FORECASTING USING MACHINE LEARNING TECHNIQUES ON HISTORICAL DATA , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 14 No. 2 (2024)
