METHOD AND SOFTWARE COMPONENT MODEL FOR SKIN DISEASE DIAGNOSIS
DOI:
https://doi.org/10.15588/1607-3274-2023-1-4Keywords:
dermatoscopy, medical diagnosis, convolutional neural network, skin disease, ResNet50 model, software component modelAbstract
Context. The problem of skin disease diagnosis was investigated in the paper. Its actuality is caused by the necessity of automation of at least advisory medical decision making. Such decisions are made in telemedicine, for instance, when skin disease diagnostics is performed under specific conditions. These conditions are specified by situations when data for analysis are collected but a qualified doctor has no possibility to process the data and to make a diagnosis decision based on it. The object of the study is a process of skin disease diagnosis.
Objective. The objective of the study is to develop a skin disease diagnosis method to automate making of advisory medical diagnosis decisions and to increase efficiency of such decisions.
Method. The skin disease diagnosis method was proposed in the work. This method applies the modified ResNet50 model. It was proposed to add layers to the ResNet50 model and to train it using transfer learning and fine-tuning techniques. The method also defines image processing in particular through the change of its resolution and uses oversampling technique to prepare a dataset for model training.
Results. Experimental investigation of the proposed method was performed using the HAM10000 dataset which contains images of skin diseases. The images were collected using dermatoscopy method. The dataset contains observations for 7 different skin diseases. The proposed method is characterized by the accuracy of 96.31% on this dataset. It is improved accuracy in comparison with the existing neural network models. Software component model was created to give a possibility to integrate the proposed method into a medical diagnosis system.
Conclusions. The obtained results of the investigation suggest application of the proposed skin disease method in medical diagnostic system to make advisory decisions by the system and to support making final decisions by a doctor.
References
Sung H. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries, Statistics, 2021, Volume 71, pp. 209–249. DOI: 10.3322/caac.21660.
Rak v Ukraine 2020. Informaciya k razmyshleniyu – analiz dannyx kancer-reestra [Electronic resource]. 2021. Access mode: https://chemoteka.com.ua/blog/article/ rak-v-ukraine2020-informaciya-k-razmyshleniyu-analiz-dannyh-kancerreestra-197. [In Russian]
Rak shkiry (pukhlyny shkiry) [Electronic resource]. Access mode: https://spizhenko.clinic/uk/zabolevaniya/opuholikozhi-uk. [In Ukrainian]
Balogh E. P., Miller B. T., Ball J. R. Improving Diagnosis in Health Care, Washington, DC, National Academies Press, 2015, 472 p. DOI: 10.17226/21794.
Dermatoskopiya [Electronic resource]. Access mode: https://guideh.clinic/dermatologiya/dermatoskopiya/. [In Russian]
Convolutional neural networks in dermatology [Electronic resource]. 2018. Access mode: https://dermnetnz.org/ topics/convolutional-neural-networks-in-dermatology.
Minagawa A., Koga H., Sano T. Dermoscopic diagnostic performance of Japanese dermatologists for skin tumors differs by patient origin: A deep learning convolutional neural network closes the gap, The Journal of Dermatology, 2020, Volume 48, pp. 232–236. DOI: 10.1111/1346-8138.15640.
Pham T. C., Tran G. S., Nghiem T. P., Doucet A., Luong C. M., Dung H. V. A Comparative Study for Classification of Skin Cancer, 2019 International Conference on System Science and Engineering (ICSSE), Jul 2019, Dong Hoi, Vietnam, pp. 267–272. DOI:10.1109/ICSSE.2019.8823124.
Pratt M. K. Artificial intelligence in primary care, Medical Economics Journal, 2018, Volume 95, Issue 15, pp. 19–30.
Artificial Intelligence in Medical Diagnosis [Electronic resource]. 2021. Access mode: https://sma.org/ai-in-medicaldiagnosis/.
Yadav S. S., Jadhav S. M. Deep convolutional neural network based medical image classification for disease diagnosis, Journal of Big Data, 2019, Volume 6, pp. 113–131. DOI: 10.1186/s40537-019-0276-2.
Garg R., Maheshwari S., Shukla A. Decision Support System for Detection and Classification of Skin Cancer Using CNN, Innovations in Computational Intelligence and Computer Vision, 2021, Volume 1, pp. 578–586. DOI: 10.48550/arXiv.1912.03798.
Rab Ratul M. A., Mozaffari M. H., Lee W.-S., Parimbelli E. Skin Lesions Classification Using Deep Learning Based on Dilated Convolution [Electronic resource], bioRxiv, 2019, pp. 1–11. Access mode: https:// www.biorxiv.org/content/10.1101/860700v3.full.pdf. DOI : 10.1101/860700.
Dilated Convolution [Electronic resource]. 2022. Access mode: https://www.geeksforgeeks.org/dilated-convolution/.
Lucius M., De All J., De All J. A., Belvisi M., Radizza L., Lanfranconi M., Lorenzatti V., Galmarini C. M. Deep Neural Frameworks Improve the Accuracy of General Practitioners in the Classification of Pigmented Skin Lesions, Diagnostics, 2020, Volume 10, pp. 1–15. DOI: 10.3390/diagnostics10110969.
Nelson J. You Might Be Resizing Your Images Incorrectly [Electronic resource]. 2020. Access mode: https://blog.roboflow.com/you-might-be-resizing-yourimages-incorrectly/.
Feng V. An Overview of ResNet and its Variants [Electronic resource]. 2017. Access mode: https://towardsdatascience.com/an-overview-of-resnet-andits-variants-5281e2f56035.
Donges N. What Is Transfer Learning? Exploring the Popular Deep Learning Approach [Electronic resource]. Access mode: https://builtin.com/data-science/transfer-learning.
Fine-tuning Convolutional Neural Network on own data using Keras Tensorflow [Electronic resource]. Access mode: https://cv-tricks.com/keras/fine-tuning-tensorflow/.
Tschandl Ph. The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions [Electronic resource]. 2018. Access mode: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi :10.7910/DVN/DBW86T. DOI: 10.7910/DVN/DBW86T.
Ali S., Miah S., Haque J. An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models, Machine Learning with Applications, 2021, Volume 5, pp. 1–8. DOI: 10.1016/j.mlwa.2021.100036.
Chaturvedi S., Tembhurne J., Diwan T. A multi-class skin Cancer classification using deep convolutional neural networks, Computer Science, 2020, Volume 79, Issue 39/40, pp. 28477–28498. DOI:10.1007/s11042-020-09388-2.
Brownlee J. Gentle Introduction to the Adam Optimization Algorithm for Deep Learning [Electronic resource]. 2021. Access mode: https://machinelearningmastery.com/adamoptimization-algorithm-for-deep-learning/.
Lovkin V., Oliinyk A., Lukashenko Y. Air Pollution Prediction as a Source for Decision Making Framework in Medical Diagnosis [Electronic resource]. IntelITSIS’2021: 2nd International Workshop on Intelligent Information Technologies and Systems of Information Security, 2021, Khmelnytskyi, Ukraine, 2021, pp. 295–302.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 В. М. Льовкін, С. О. Субботін, А. О. Олійник, Н. В. Мироненко
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
