Skin disorder diagnosis with ambiguity reduction assisted by lesion color adaptation

Nikos Petrellis; Nikos Petrellis

doi:10.3934/ElectrEng.2019.3.290

AIMS Electronics and Electrical Engineering

2019, Volume 3, Issue 3: 290-308. doi: 10.3934/ElectrEng.2019.3.290

Previous Article Next Article

Research article Topical Sections

Skin disorder diagnosis with ambiguity reduction assisted by lesion color adaptation

Nikos Petrellis ^,

Department of Computer Science and Engineering, University of Thessaly(ex TEI of Thessaly), Geopolis, Larissa, 41110, Greece

Received: 18 June 2019 Accepted: 14 August 2019 Published: 17 September 2019

A smart phone application based on a low complexity image processing technique and a novel fuzzy-like classification method are presented for skin disorder diagnosis. The proposed classification method takes into consideration the size and color features of skin lesions rather than their shape and texture. The classification rules are determined after processing statistically a small number of representative training photographs. Consequently, they can be defined by an end user that is not necessarily skilled in computer science. The application presented in this paper can serve as a complementary tool for a dermatologist to continuously monitor remotely his patients. The accuracy of the diagnosis that is based only on the image processing outcomes, ranges between 85.3% and 97.7% using 5 only representative photographs as a "training set" (corresponding from 9% to 24% of the test set per disease). The achieved accuracy can be improved (up to 17%), if the photographs are processed using a specific color adaptation technique. The small fraction of training photographs can be scaled up if the size of the test set is increased but it is expected that a limited number of training photographs will be sufficient in order to achieve an acceptable accuracy for a test set of any size. This accuracy can be further improved if other factors are taken into consideration (progression of the symptoms, information provided by the user, etc).
- skin infections,
- skin disorders,
- image processing,
- color adaptation,
- mobile apps,
- lesions,
- histograms
Citation: Nikos Petrellis. Skin disorder diagnosis with ambiguity reduction assisted by lesion color adaptation[J]. AIMS Electronics and Electrical Engineering, 2019, 3(3): 290-308. doi: 10.3934/ElectrEng.2019.3.290

Related Papers:

Abstract

A smart phone application based on a low complexity image processing technique and a novel fuzzy-like classification method are presented for skin disorder diagnosis. The proposed classification method takes into consideration the size and color features of skin lesions rather than their shape and texture. The classification rules are determined after processing statistically a small number of representative training photographs. Consequently, they can be defined by an end user that is not necessarily skilled in computer science. The application presented in this paper can serve as a complementary tool for a dermatologist to continuously monitor remotely his patients. The accuracy of the diagnosis that is based only on the image processing outcomes, ranges between 85.3% and 97.7% using 5 only representative photographs as a "training set" (corresponding from 9% to 24% of the test set per disease). The achieved accuracy can be improved (up to 17%), if the photographs are processed using a specific color adaptation technique. The small fraction of training photographs can be scaled up if the size of the test set is increased but it is expected that a limited number of training photographs will be sufficient in order to achieve an acceptable accuracy for a test set of any size. This accuracy can be further improved if other factors are taken into consideration (progression of the symptoms, information provided by the user, etc).

References

[1]	Becevic M, Anderson B, Han JG, et al. (2013) TeleMDID: Mobile Technology Applications for Interactive Diagnoses in Teledermatology Clinics. Proceedings of the IEEE 15th International Conference on e-Health Networking, Applications and Services (Healthcom), 429-433.
[2]	Mannaro K, Baralla G, Ibba S, et al. (2017) Towards a smart region: The case study of a teledermatology platform in sardinian region (Italy). Proceedings of the IEEE Wireless and Mobile Computing, Networking and Communications (WiMob), 370-377.
[3]	Al Abbadi NK, Dahir NS, Al-Dhalimi MA, et al. (2010) Psoriasis Detection Using Skin Color and Texture Features. Journal of Computer Science 6: 648-652. doi: 10.3844/jcssp.2010.648.652
[4]	Kabari LG, Bakpo FS (2009) Diagnosing skin diseases using an artificial neural network. Proceedings of the IEEE International Conference of Adaptive Science & Technology, 187-191.
[5]	Alamdari N, Tavakolian K, Alhashim M, et al. (2016) Detection and Classification of Acne Lesions in Acne Patients: A Mobile Application. Proceedings of the 2016 IEEE International Conference on Electro Information Technology (EIT), 739-734.
[6]	Baig R, Bibi M, Hamid A, et al. (2019) Deep Learning Approaches Towards Skin Lesion Segmentation and Classification from Dermoscopic Images - A Review. Curr Med Imaging Rev 15: 1-20.
[7]	Bhardwaj A, Bhatia JS (2014) An Image Segmentation Method for Early Detection and Analysis of Melanoma. IOSR Journal of Dental and Medical Sciences 13: 18-22.
[8]	Wadhawan T, Situ N, Lancaster K, et al. (2011) SkinScan ©: A Portable Library for Melanoma Detection on Handheld Devices. Proceedings of the IEEE International Symposium On Biomedical Imaging 2011: 133-136.
[9]	Joseph S, Panicker JR (2016) Skin Lesion Analysis System for Melanoma Detection with an Effective Hair Segmentation Method. Proceedings of the International Conference on Information Science (ICIS), 91-96.
[10]	Santy A, Joseph R (2015) Segmentation Methods for Computer Aided Melanoma Detection. Proceedings of the Global Conference on Communication Technologies (GCCT), 490-493.
[11]	Mirzaalian H, Lee TK, Hamarneh G (2014) Spatial Normalization of Human Back Images for Dermatological Studies. IEEE Journal of Biomedical and Health Informatics 18: 1494-1501. doi: 10.1109/JBHI.2013.2288775
[12]	Ghervase L, Carstea EM, Borisova E, et al (2015) Bringing Light into the Diagnosis of Skin Disorders - Short Review on Laser Induced Fluorescence Spectroscopy and Optical Coherence Tomography in Dermatology. Curr Med Imaging Rev 10: 297-303. doi: 10.2174/157340561004150121141449
[13]	Arifin MS, Kibria MG, Firoze A, et al. (2012) Dermatological Disease Diagnosis Using Colour-skin Images. International Conference on Machine Learning and Cybernetics 5: 1675-1680.
[14]	Islam MN, Gallardo-Alvarado J, Abu M, et al. (2017) Skin disease recognition using texture analysis. Proceedings of the IEEE International Conference on Control and System Graduate Research Colloquium (ICSGRC), 144-148.
[15]	Kumar VB, Kumar SS, Saboo V (2016) Dermatological Disease Detection Using Image Processing and Machine Learning. Proceedings of the International Conference on Artificial Intelligence and Pattern Recognition (AIPR), 1-6.
[16]	Yasir R, Rahman A, Ahmed N (2014) Dermatological Disease Detection using Image Processing and Artificial Neural Network. Proceedings of the 8th International Conference on Electrical and Computer Engineering; 687-690.
[17]	Ambad PS, Shirsat AS (2016) An Image analysis System to Detect Skin Diseases. IOSR Journal of VLSI and Signal Processing 6: 17-25. doi: 10.9790/4200-0605011725
[18]	Kabari LG, Bakpo FS (2009) Diagnosing skin diseases using an artificial neural network. International Conference on Adaptive Science & Technology, 187-191.
[19]	Abdul-Rahman S, Norhan AK, Yusoff M, et al. (2012) Dermatology Diagnosis with Feature Selection Methods and Artificial Neural Network. IEEE EMBS Confence on Biomedical Engineering and Sciences, 371-376.
[20]	Petrellis N (2018) Using Color Signatures for the Classification of Skin Disorders. Proceedings of the IEEE International Conference on Modern Circuits and Systems Technology (MOCAST), 1-4.
[21]	Petrellis N (2018) The Effect of the Training Set Size in a Skin Disorder Classification Application. 2018 41st International Conference on Telecommunications and Signal Processing, 1-5.
[22]	Petrellis N (2017) A Smart Phone Image Processing Application for Plant Disease Diagnosis. International Conference on Modern Circuits and Systems Technology (MOCAST), 1-4.
[23]	Frank E, Hall M and Witten I (2016) The WEKA workbench. Online Appendix for Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann, Fourth Edition, 2016.
[24]	Petrellis N (2018) A Review of Image Processing Techniques Common in Human and Plant Disease Diagnosis. Symmetry 10: 270.

Reader Comments

Your name:*

Email:*
© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)