DETECTION OF HAIR FALL AND SCALP DISORDERS THROUGH ML AND IMAGE PROCESSING

Nagesh; Dr.Priscilla  Joy; Dr. Immanuel Johnraja Jebadurai; Dr. Jebakumar  Immanuel

doi:10.30572/2018/KJE/160406

Authors

Nagesh Division of CSE, Karunya Institute of Technology and Sciences, Coimbatore – 641114, India
Dr.Priscilla Joy Assistant Professor, Division of CSE, Karunya Institute of Technology and Sciences, Coimbatore – 641114, India
Dr. Immanuel Johnraja Jebadurai Professor, Division of CSE, Karunya Institute of Technology and Sciences, Coimbatore – 641114, India
Dr. Jebakumar Immanuel Associate Professor, Karpagam Institute of Technology, Coimbatore – 641105, India

DOI:

https://doi.org/10.30572/2018/KJE/160406

Keywords:

Pad net algorithm, DenseNet, AlexNet, Confusion matrix, Machine Learning, Scalp Diseases

Abstract

Hair loss impacts approximately 80 million people in the United States and arises from factors such as aging, genetic predisposition, stress, and medication. In many cases, early signs of scalp and hair disorders remain unnoticed, delaying timely diagnosis and treatment. Neural networks, particularly in image-based diagnostics, have shown great promise across medical domains, including oncology and dermatology. This research investigates the application of deep learning for identifying three major scalp conditions: alopecia, psoriasis, and folliculitis. Major challenges included limited literature, a small dataset, and non-uniform image quality from online sources. To address these, the study compiled 150 scalp images and employed preprocessing techniques such as denoising, histogram equalization, augmentation, and class balancing. A two-dimensional Convolutional Neural Network (CNN) was trained on this dataset, achieving a training accuracy of 96.2% and a validation accuracy of 91.1%, with consistently high precision and recall across all classes. Additionally, a new scalp scan dataset was introduced to support future research, contributing to the development of AI-driven diagnostic tools for hair and scalp health assessment

Downloads

Download data is not yet available.

References

Alshahrani, A. A., Al-Tuwaijri, R., Abuoliat, Z. A., Alyabsi, M., AlJasser, M. I., and Alkhodair, R., 2020. Prevalence and clinical characteristics of alopecia areata at a tertiary care center in Saudi Arabia. Dermatology Research and Practice, 2020, Article ID 7194270, 4 pages.

Bernardis, E. and Castelo-Soccio, L., 2018. Quantifying alopecia areata via texture analysis to automate the salt score computation. Journal of Investigative Dermatology Symposium Proceedings, 19(1), pp. S34-S40.

Dubey, K., Srivastava, V., and Mehta, D. S., 2018. Automated in vivo identification of fungal infection on human scalp using optical coherence tomography and machine learning. Laser Physics, 28(4), Article 045602.

Esfandiari, A., Kalantari, K. R., and Babaei, A., 2012. Hair loss diagnosis using artificial neural networks. International Journal of Computer Science Issues (IJCSI), 9(5).

Hoffmann, R., 2003. TrichoScan: a novel tool for the analysis of hair growth in vivo. Journal of Investigative Dermatology Symposium Proceedings, 8(1), pp. 109-115.

Ibrahim, S., Noor Azmy, Z. A., Abu Mangshor, N. N., Sabri, N., Ahmad Fadzil, A. F., and Ahmad, Z., 2020. Pre-trained classification of scalp conditions using image processing. Indonesian Journal of Electrical Engineering and Computer Science, 20(1), pp. 138-144.

Kapoor, A. and Mishra, A., 2018. Automated classification method for early diagnosis of alopecia using machine learning. Procedia Computer Science, 132, pp. 437-443.

Lee, S.-H. and Yang, C.-S., 2018. An intelligent hair and scalp analysis system using camera sensors and Norwood-Hamilton model. International Journal of Innovative Computing Information and Control, 14(2), pp. 503-518.

Mathiyalagan, P. and Devaraj, D., 2021. A machine learning classification approach based glioma brain tumor detection. International Journal of Imaging Systems and Technology, 31, pp. 1424-1436.

Meah, N., Wall, D., York, K. et al., 2021. The alopecia areata consensus of experts (ACE) study part II: results of an international expert opinion on diagnosis and laboratory evaluation for alopecia areata. Journal of the American Academy of Dermatology, 84(6), pp. 1594-1601.

Pangti, R., Mathur, J., Chouhan, V. et al., 2021. A machine learning-based, decision support, mobile phone application for diagnosis of common dermatological diseases. Journal of the European Academy of Dermatology and Venereology, 35(2), pp. 536-545.

Pratt, C. H., King, L. E., Messenger, A. G., Christiano, A. M., and Sundberg, J. P., 2017. Alopecia areata. Nature Reviews Disease Primers, 3(1), pp. 1-17.

Rimi, T. A., Sultana, N., and Foysal, M. F. A., 2020. Derm-NN: skin diseases detection using convolutional neural network. In: 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS), pp. 1205-1209. Madurai, India.

Saber, M., Sakr, M., Abo-Seida, O. M., Keshk, A., and Chen, H., 2021. A novel deep-learning model for automatic detection and classification of breast cancer using the transfer-learning technique. IEEE Access, 9, pp. 71194-71209.

Sadick, N. S., 2018. New-generation therapies for the treatment of hair loss in men. Dermatologic Clinics, 36(1), pp. 63-67.

Sahli, H., 2020. An introduction to machine learning. In: TORUS 1–Toward an Open Resource Using Services: Cloud Computing for Environmental Data, pp. 61-74. Wiley Online Library.

Seo, S. and Park, J., 2020. Trichoscopy of alopecia areata: hair loss feature extraction and computation using grid line selection and eigenvalue. Computational and Mathematical Methods in Medicine, 2020, Article ID 6908018, 9 pages.

Shih, H., 2015. A precise automatic system for the hair assessment in hair-care diagnosis applications. Skin Research and Txechnology, 21(4), pp. 500-507.

Simakou, T., Butcher, J. P., Reid, S., and Henriquez, F. L., 2019. Alopecia areata: a multifactorial autoimmune condition. Journal of Autoimmunity, 98, pp. 74-85.

Sterkens, A., Lambert, J., and Bervoets, A., 2021. Alopecia areata: a review on diagnosis, immunological etiopathogenesis and treatment options. Clinical and Experimental Medicine, 21(2), pp. 215-230.

Svanera, M., Muhammad, U. R., Leonardi, R., and Benini, S., 2016. Figaro, hair detection and segmentation in the wild. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 933-937. Phoenix, AZ, USA.

Wang, W.-C., Chen, L.-B., and Chang, W.-J., 2018. Development and experimental evaluation of machine-learning techniques for an intelligent hairy scalp detection system. Applied Sciences, 8(6).

Wu, P., Ye, H., Cai, X. et al., 2021. An effective machine learning approach for identifying non-severe and severe coronavirus disease 2019 patients in a rural Chinese population: the Wenzhou retrospective study. IEEE Access, 9, pp. 45486-45503.

Yue, Z., Sun, C., Chen, F. et al., 2021. Machine learning-based LIBS spectrum analysis of human blood plasma allows ovarian cancer diagnosis. Biomedical Optics Express, 12(5), pp. 2559-2574.

Zhao, S., Wang, P., Heidari, A. A. et al., 2021. Multilevel threshold image segmentation with diffusion association slime mould algorithm and Renyi's entropy for chronic obstructive pulmonary disease. Computers in Biology and Medicine, 134, Article 104427.