IMAGE SEGMENTATION WITH A CONVOLUTIONAL NEURAL NETWORK WITHOUT POOLING LAYERS IN DERMATOLOGICAL DISEASE DIAGNOSTICS SYSTEMS
Keywords:psoriasis image, image segmentation, convolutional network, pooling layer, color space, deep learning
Context. The problem of automating of the segmentation of spectral-statistical texture images is considered. The object of research is image processing in dermatological disease diagnostic systems.
Objective. The aim of the research is to improve the segmentation performance of color images of psoriasis lesions by elaboration of a deep learning convolutional neural network without pooling layers.
Method. The convolutional neural network is proposed to process a three-channel psoriasis image with a specified size. The initial color images were scaled to the specified size and then inputed on the neural network. The architecture of the proposed neural network consists of four convolutional layers with batch normalization layers and ReLU activation function. Feature maps from the output of these layers were inputted to the 1*1 convolutional layer with the Softmax activation function. The resulting feature maps were inputted to the image pixel classification layer. When segmenting images, convolutional and pooling layers extract the features of image fragments, and fully connected layers classify the resulting feature vectors, forming a partition of the image into homogeneous segments. The segmentation features are evaluated as a result of network training using ground-truth images which segmented by an expert. Such features are robust to noise and distortion in images. The combination of segmentation results at different scales is determined by the network architecture. Pooling layers were not included in the architecture of the proposed convolutional neural network since they reduce the size of feature maps compared to the size of the original image and can decrease the segmentation performance of small psoriasis lesions and psoriasis lesions of complex shape.
Results. The proposed convolutional neural network has been implemented in software and researched for solving the problem of psoriasis images segmentation.
Conclusions. The use of the proposed convolutional neural network made it possible to enhance the segmentation performance of plaque and guttate psoriasis images, especially at the edges of the lesions. Prospects for further research are to study the performance of the proposed CNN then abrupt changes in color and illumination, blurring, as well as the complex background areas are present on dermatological images, for example, containing clothes or fragments of the interior. It is advisable to use the proposed CNN in other problems of color image processing to segment statistical or spectral-statistical texture regions on a uniform or textured background.
Kotvitska A. A., Carlo V. V. Research on the indicators of the prevalence of psoriasis in the world and Ukraine, Zaporozhye Medical Journal, 2013, № 3(78), pp. 38–42.
Jarad T. S., Dawood A. J. A quantitative technique for systematic monitoring of the treatment efficiency psoriasis lesion, London Journal of Research in Computer Science and Technology, 2019, Vol. 19, № 1, pp. 37–46.
Velasco J., Pascion C., Alberio J. W. et al. A smartphonebased skin disease classification using MobileNet CNN, International Journal of Advanced Trends in Computer Science and Engineering, 2019, Vol. 8, № 5, pp. 2632– 2637. DOI: 10.30534/ijatcse/2019/116852019
Pal A., Chaturvedi A., Garain U. et. al. Severity grading of psoriatic plaques using deep CNN based multi-task learning, Pattern Recognition: 23rd International Conference, ICPR, Cancun, Mexico, 4–8 December, 2016 : proceedings. Piscataway, NJ, IEEE, 2016, pp. 1478–1483. DOI: 10.1109/ICPR.2016.7899846
Pal A., Garain U., Chandra A., Chatterjee R., Senapati S. Psoriasis skin biopsy image segmentation using deep convolutional neural network, Computer Methods and Programs in Biomedicine, 2018, Vol. 59, № 6 (1), pp. 59– 69. DOI:10.1016/j.cmpb.2018.01.027
Jarad T. S., Dawood A. J. Accurate segmentation of psoriasis diseases images using k-means algorithm based on CIELAB (L*A*B) color space, Journal of Theoretical and Applied Information Technology, 2017, Vol. 95, № 17, pp. 4201–4210.
Pal A., Roy A., Sen K. et al. Mixture model based color clustering for psoriatic plaque segmentation, Pattern Recognition : Third IAPR Asian Conference, ACPR, Kuala Lumpur, Malaysia, 3–6 November 2015 : proceedings. Red Hook, NY, IEEE, 2015, pp. 376–380. DOI:10.1109/ACPR.2015.7486529
Volkova N. P. Detector quasi-periodic texture segmentation method for dermatologica images processing, Herald of Advanced Information Technology, 2019, Vol. 2, № 4, pp. 259–267. DOI: 10.15276/hait.04.2019.2.
Dash M., Londhe N. D., Ghosh S., Semwal A., Sonawane R. S. PsLSNet: automated psoriasis skin lesion segmentation using modified U-Net-based fully convolutional network, Biomedical Signal Processing and Control, 2019, Vol. 52, pp. 226–237. DOI: 10.1016/j.bspc.2019.04.002
Lin G.-S., Lai K.-T., Syu J.-M. et al. Instance segmentation based on deep convolutional neural networks and transfer learning for unconstrained psoriasis skin images, Applied Scienses, 2021, Vol. 11, 3155. DOI: 10.3390/app11073155
Subbotin S. A. The fractal dimension based quality metrics of data samples and dependence models, Radio Electronics, Computer Science, Control, 2017, № 2, pp. 70–81. DOI: 10.15588/1607-3274-2017-2-8
Leoshchenko S. D., Oliynyk A. O., Subbotin S. O., Hoffman E. O., Kornienko O. V. Method of structural adjustment of neural network models to ensure interpretability, Radio electronics, computer science, management, 2021, № 3, pp. 86–96.
Roslan R., Razly I. N. M., Sabri N., Ibrahim Z. Evaluation of psoriasis skin disease classification using convolutional neural network, International Journal of Artificial Intelligence, 2020, Vol. 9, № 2, pp. 349–355. DOI: 10.11591/ijai.v9.i2
Raza M. A., Liaqat M. S., Shoaib M. A fuzzy expert system design for diagnosis of skin diseases, Advancements in Computational Sciences: Second International Conference, ICACS, Lahore, Pakistan, 18–20 February, 2019 : proceedings, IEEE, 2019. pp. 1–7. DOI: 10.23919/ICACS.2019.8689140
George Y. M., Aldeen M., Garnavi R. Automatic scale severity assessment method in psoriasis skin images using local descriptors, Journal of Biomedical and Health Informatics, 2020, Vol. 24, № 2, pp. 577–585. DOI: 10.1109/JBHI.2019.2910883.
Mullangi P., Yarravarapu S. R., Kotipalli P., Urooj S. (ed.). Texture and clustering-based skin disease classification, Sensors and Image Processing. Singapore, Springer, 2018, pp. 103–110. DOI: 10.1007/978-981-10-6614-6_11
Munia T. T., Haque I. R., Aymond A. et. al. Automatic clustering-based segmentation and plaque localization in psoriasis digital images, Healthcare Innovations and Pointof-Care Technologies, Special Topics Conference, IEEENIH, Bethesda Campus, MD, USA, 6–8 November, 2017 : proceedings, IEEE, 2017, pp. 113–116. DOI: 10.1109/HIC.2017.8227597
Roy K., Chaudhuri S. S., Ghosh S. et al. Skin disease detection based on different segmentation techniques, OptoElectronics and Applied Optics: International Conference, Optronix, Kolkata. India, 18–20 March, 2019, proceedings, IEEE, 2019, pp. 70–74. DOI: 10.1109/OPTRONIX.2019.8862403
Liu X., Krylov V., Jun S. et al. Segmentation and identification of spectral and statistical textures for computer medical diagnostics in dermatology, Mathematical Biosciences and Engineering, 2022, Vol. 19, № 7, pp. 6923– 6939. DOI: 10.1109/JBHI.2019.2910883.
Krylov V. N., Volkova N. P. Vector-difference texture segmentation method in technical and medical express diagnostic systems, Herald of Advanced Information Technology, 2020, Vol. 3, № 4, pp. 226–239. DOI: 10.15276/hait.04.2020.2
George Y. M., Aldeen M., Garnavi R. Automatic psoriasis lesion segmentation in two-dimensional skin images using multiscale superpixel clustering, Journal of Medical Imaging, 2017, Vol. 4, № 4, pp. 59–69. DOI: 10.1117/1.JMI.4.4.044004
Psoriasis: Symptoms, Treatment, Images and More – DermNet [Electronic resource]. Access mode: http:// dermnetnz.org/
Polyakova M., Ishchenko A., Volkova N., Pavlov O. The combining segmentation method of the scanned documents images with sequential division of the photo, graphics, and the text areas, Eastern- European Journal of Enterprise Technologies, 2018, Vol. 5, № 2, pp. 6–16. DOI: 10.15587/1729-4061.2018.142735
Polyakova M. V., Nesteryuk A. G. Improvement of the color text image binarization method using the minimum-distance classifier, Applied Aspects of Information Technology, 2021. Vol. 4, № 1, pp. 57–70. DOI: 10.15276/aait.01.2021.5
Akinlar C., Topal C. ColorED: color edge and segment detection by edge drawing, Journal of Visual Communication and Image Representation, 2017, Vol. 44, pp. 82–94. DOI: 10.1016/j.jvcir.2017.01.024
Gonzalez R. C., Woods R. E. Digital Image Processing (4rd Edition). NY, Pearson, 2017, 1192 p.
Ronneberger O., Fischer P., Brox T. U-Net: convolutional networks for biomedical image segmentation, Medical Image Computing and Computer-Assisted Intervention, 2015, Vol. 9351, pp. 234–241. DOI: 10.48550/arXiv.1505.04597
How to Cite
Copyright (c) 2023 M. V. Polyakova
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.