Attention Balanced Multi-Dimension Multi-Task Deep Learning for Alopecia Recognition

C Saraswathi; B Pushpa

doi:10.17485/IJST/v16i18.29

Article

Attention Balanced Multi-Dimension Multi-Task Deep Learning for Alopecia Recognition

VIEWS 525
PDF 121

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v16i18.29

Year: 2023, Volume: 16, Issue: 18, Pages: 1365-1373

Original Article

Attention Balanced Multi-Dimension Multi-Task Deep Learning for Alopecia Recognition

C Saraswathi^1*, B Pushpa²

¹Research Scholar, Department of Computer and Information Science, Faculty of Science, Annamalai University, Chidambaram, 608002, Tamil Nadu, India
²Assistant Professor/Programmer, Department of Computer and Information Science, Faculty of Science, Annamalai University, Chidambaram, 608002, Tamilnadu, India

*Corresponding Author
Email: [email protected]

Received Date:04 January 2023, Accepted Date:08 April 2023, Published Date:09 May 2023

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objective: To increase the accuracy of Alopecia Areata (AA) classification by learning local and global features across AA images and scalp hair images. Methods: An Attention-based Balanced Multi-Task Deep (AB-MTDeep) learning system is proposed. In this system, the MTDeep model incorporates both Multi- Task Learning (MTL) and Cross-Residual Learning (CRL) to simultaneously train hair and scalp images for recognizing AA conditions. In MTL, a new shared encoder is added to the MTDeep model, whereas in CRL, cross-residual layers are added to improve the model’s efficiency. According to this learning, both local and global features are learned at multiple scales, as well as, concatenated to get the cross-feature representation. Such features are then classified by the softmax classifier to recognize AA conditions. Findings: Finally, the test outcomes demonstrate that the AB-MTDeep system on hair and scalp image databases realizes an accuracy of 95.11% compared to all other classical systems. Novelty: This model has considerably increased the accuracy of classifying AA conditions. Thus, it represents a promising classifier for AA classification.

Keywords: Dermatology; Alopecia Areata; FRCNNLSTM; Multitask learning; Crossresidual learning

References

Kim S, Shin S, Kim SN, Na Y. Understanding the Characteristics of the Scalp for Developing Scalp Care Products. Journal of Cosmetics, Dermatological Sciences and Applications. 2021;11(03):204–216. Available from: https://doi.org/10.4236/jcdsa.2021.113018
Chang WJJ, Chen LBB, Chen MCB, Chiu YCC, Lin JYY. ScalpEye: A Deep Learning-Based Scalp Hair Inspection and Diagnosis System for Scalp Health. IEEE Access. 2020;8:134826–134837. Available from: https://doi.org/10.1109/access.2020.3010847
Alshahrani AA, Al-Tuwaijri R, Abuoliat ZA, Alyabsi M, Aljasser MI, Alkhodair R. Prevalence and Clinical Characteristics of Alopecia Areata at a Tertiary Care Center in Saudi Arabia. Dermatology Research and Practice. 2020;2020:1–4. Available from: https://doi.org/10.1155/2020/7194270
Fricke ACV, Miteva M. Epidemiology and burden of alopecia areata: a systematic review. Clinical, Cosmetic and Investigational Dermatology. 2015;8:397–403. Available from: https://doi.org/10.2147/ccid.s53985
Ocampo-Garza J, Tosti A. Trichoscopy of Dark Scalp. Skin Appendage Disorders. 2019;5(1):1–8. Available from: https://doi.org/10.1159/000488885
Elder A, Ring C, Heitmiller K, Gabriel Z, Saedi N. The Role of Artificial Intelligence in Cosmetic Dermatology-Current, Upcoming, and Future Trends. Journal of Cosmetic Dermatology. 2021;20(1):48–52. Available from: https://doi.org/10.1111/jocd.13797
Alarcón-Soldevilla F, Hernández-Gómez FJ, García-Carmona JA, Carreño CC, Grimalt R, Vañó-Galvan S, et al. Use of Artificial Intelligence as a Predictor of the Response to Treatment in Alopecia Areata. Iproceedings. 2021;7(1):e35433. Available from: https://www.iproc.org/2021/1/e35433/PDF
Nie Y, Sommella P, Carratu M, Ferro M, O'nils M, Lundgren J. Recent Advances in Diagnosis of Skin Lesions Using Dermoscopic Images Based on Deep Learning. IEEE Access. 2022;10:95716–95747. Available from: https://doi.org/10.1109/ACCESS.2022.3199613
Lee S, Lee JW, Choe SJ, Yang S, Koh SB, Ahn YS, et al. Clinically Applicable Deep Learning Framework for Measurement of the Extent of Hair Loss in Patients With Alopecia Areata. JAMA Dermatology. 2020;156(9):1018–1020. Available from: https://doi.org/10.1001/jamadermatol.2020.2188
Ibrahim S, Azmy ZAN, Mangshor NNA, Sabri NN, Fadzil AFA, Ahmad Z. Pre-trained classification of scalp conditions using image processing. Indonesian Journal of Electrical Engineering and Computer Science. 2020;20(1):138–144. Available from: http://doi.org/10.11591/ijeecs.v20.i1.pp138-144
Zhang L, Man Q, Cho YI. Deep-Learning-Based Hair Damage Diagnosis Method Applying Scanning Electron Microscopy Images. Diagnostics. 2021;11(10):1–12. Available from: https://doi.org/10.3390/diagnostics11101831
Chen X, Li X, Chen B, Yin Y, Zhang J, Zhou C. Female Pattern Hair Loss in Female and Male: A Quantitative Trichoscopic Analysis in Chinese Han Patients. Frontiers in Medicine. 2021;8:1–8. Available from: https://doi.org/10.3389/fmed.2021.649392
Shakeel CS, Khan SJ, Chaudhry B, Aijaz SF, Hassan U. Classification Framework for Healthy Hairs and Alopecia Areata: A Machine Learning (ML) Approach. Computational and Mathematical Methods in Medicine. 2021;2021:1–10. Available from: https://doi.org/10.1155/2021/1102083
Gao M, Wang Y, Xu H, Xu C, Yang X, Nie J, et al. Deep Learning-Based Trichoscopic Image Analysis and Quantitative Model for Predicting Basic and Specific Classification in Male Androgenic Alopecia. Acta Dermato-Venereologica. 2022;102:1–6. Available from: https://doi.org/10.2340/actadv.v101.564
Kim M, Kang S, Lee BD. Evaluation of Automated Measurement of Hair Density Using Deep Neural Networks. Sensors. 2022;22(2):1–10. Available from: https://doi.org/10.3390/s22020650
Jeong JII, Park DSS, Koo JEE, Song WSS, Pae DJJ, Choi HJJ. Artificial intelligence (AI) based system for the diagnosis and classification of scalp health: AI-ScalpGrader. Instrumentation Science & Technology. 2022;p. 1–11. Available from: https://doi.org/10.1080/10739149.2022.2129382
Roy M, Protity AT. Hair and Scalp Disease Detection Using Machine Learning and Image Processing. European Journal of Information Technologies and Computer Science. 2023;3(1):1–7. Available from: https://doi.org/10.48550/arXiv.2301.00122

Copyright

© 2023 Saraswathi & Pushpa. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)