DEEP NEURAL NETWORKS FOR SKIN LESIONS DIAGNOSTICS

Magdalena Michalska-Ciekańska

mmagamichalska@gmail.com
Lublin University of Technology (Poland)
http://orcid.org/0000-0002-0874-3285

Abstract

Non-invasive diagnosis of skin cancer is extremely necessary. In recent years, deep neural networks and transfer learning have been very popular in the diagnosis of skin diseases. The article contains selected basics of deep neural networks, their interesting applications created in recent years, allowing the classification of skin lesions from available dermatoscopic images.


Keywords:

deep neural networks, transfer learning, dermatoscopic images, skin lesions diagnostics

Abunadi I., Senan E. M.: Deep learning and machine learning techniques of diagnosis dermoscopy images for early detection of skin diseases. Electronics 10, 3158, 2021.
DOI: https://doi.org/10.3390/electronics10243158   Google Scholar

Al-Masni M. A., Kim D. H., Kim T. S:. Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification. Comput Methods Programs Biomed. 190, 105351, 2020.
DOI: https://doi.org/10.1016/j.cmpb.2020.105351   Google Scholar

Brinker T. J. et al: Deep learning outperformed 136 of 157 dermatologists in a head-to-head der moscopic melanoma image classification task. Eur J Cancer 113, 47–54, 2019.
  Google Scholar

Chaturvedi S. S., Gupta K., Prasad P. S.: Skin lesion analyser: An efficient seven-way multi-class skin cancer classification using MobileNet. Advances in Intelligent Systems and Computing 1141, Springer, Singapore, 2020.
DOI: https://doi.org/10.1007/978-981-15-3383-9_15   Google Scholar

Codella N. C. F. et al.: Deep learning ensembles for melanoma recognition in dermoscopy images. IBM Journal of Research and Development 61(4/5), 173, 2017.
DOI: https://doi.org/10.1147/JRD.2017.2708299   Google Scholar

DERMOFIT IMAGE LIBRARY [https://licensing.edinburghinnovations.ed.ac.uk/i/software/dermofit-imagelibrary.html?item=dermofit-image-library] (accessed 04.01.2021).
  Google Scholar

Gavrilov D., Lazarenko L., Zakirov E.: AI recognition in skin pathologies detection. Proceedings of the 2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI), 554–542, Belgrade 2019.
DOI: https://doi.org/10.1109/IC-AIAI48757.2019.00017   Google Scholar

Ge Y. et al.: Melanoma segmentation and classification in clinical images using deep learning. 10th International Conference on Machine Learning and Computing ICMLC, 2018, 252–256.
DOI: https://doi.org/10.1145/3195106.3195164   Google Scholar

Gessert N. et al.: Skin lesion classification using CNNs with patch-based attention and diagnosis-guided loss weighting. IEEE Trans. Biomed. Eng. 67, 495–503, 2020.
DOI: https://doi.org/10.1109/TBME.2019.2915839   Google Scholar

Haenssle H. A. et al: Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermato-logists working under less artificial conditions. Ann Oncol 31, 137–143, 2020.
  Google Scholar

Harangi B.: Skin lesion classification with ensembles of deep convolutional neural networks. J. Biomed. Inform. 86, 25–32, 2018.
DOI: https://doi.org/10.1016/j.jbi.2018.08.006   Google Scholar

Hasan M. M., Elahi M., Alam M. A.: DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning and augmentation. medRxiv 2021.02.02.21251038.
DOI: https://doi.org/10.1101/2021.02.02.21251038   Google Scholar

He K. et al.: Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016, 770–778.
DOI: https://doi.org/10.1109/CVPR.2016.90   Google Scholar

Hekler A. et al.: Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images, Eur J Cancer 118, 91–96, 2019.
DOI: https://doi.org/10.1016/j.ejca.2019.06.012   Google Scholar

Howard A. G. et al.: MobileNets: Efficient convolutional neural networks for mobile vision applications. Computer Science, Computer Vision and Pattern Recognition, arXiv:1704.04861v1.
  Google Scholar

Huang G. et al.: Densely Connected Convolutional Networks. Computer Vision and Pattern Recognition arXiv:1608.06993v5.
  Google Scholar

Iqbal I. et al.: Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images. Computerized Medical Imaging and Graphics 88, 101843, 2021.
DOI: https://doi.org/10.1016/j.compmedimag.2020.101843   Google Scholar

ISIC Archive [https://www.isic-archive.com/#!/topWithHeader/onlyHeaderTop/gallery] (accessed 23.03.2022).
  Google Scholar

Kareem O., Mohsin Abdulazeez A., Zeebaree D.: Skin Lesions Classification Using Deep Learning Techniques: Review. Asian Journal of Research in Computer Science 9(1), 1–22, 2021.
DOI: https://doi.org/10.9734/ajrcos/2021/v9i130210   Google Scholar

Lee S. et al.: Augmented decision-making for acrallentiginous melanoma detection using deep convolutional neural networks. J. Eur. Acad. Dermatol. Venereol. 34, 1842–1850, 2020.
DOI: https://doi.org/10.1111/jdv.16185   Google Scholar

Lopez A. R. et al.: Skin lesion classification from dermatoscopic images using deep learning techniques. 13th International Conference on Biomedical Engineering (BioMed) IASTED, 2017, 49–54.
  Google Scholar

Maglogiannis I., Doukas C. N.: Overview of advanced computer vision systems for skin lesions characterization, IEEE transactions on information technology in biomedicine 13(5), 721–733, 2009.
DOI: https://doi.org/10.1109/TITB.2009.2017529   Google Scholar

Mahbod A. et al.: Fusing finetuned deep features for skin lesion classification, Comput. Med. Imaging Graph. 71, 19–29, 2019.
DOI: https://doi.org/10.1016/j.compmedimag.2018.10.007   Google Scholar

Mahdianpari M. et al.: Very deep convolutional neural networks for complex land cover mapping using multispectral remote sensing imagery. Remote Sens. 10(7), 2018.
DOI: https://doi.org/10.3390/rs10071119   Google Scholar

Marchetti M. A. et al.: Computer algorithms show potential for improving dermatologists’ accuracy to diagnose cutaneous melanoma: results of the international skin imaging collaboration 2017. J Am Acad Dermatol 82, 622–627, 2020.
DOI: https://doi.org/10.1016/j.jaad.2019.07.016   Google Scholar

Maron R. C. et al.: Systematic outperformance of 112 dermato-logists in multiclass skin cancer image classification by convo-lutional neural networks, Eur J Cancer 119, 57–65, 2019.
  Google Scholar

MED-NODE Dataset [http://www.cs.rug.nl/~imaging/databases/melanoma_naevi/] (accessed 23.03.2022).
DOI: https://doi.org/10.48189/nl.2022.v03i2.004   Google Scholar

Nida N. et al.: Melanoma lesion detection and segmentation using deep region based convolutional neural network and fuzzy C-means clustering, International Journal of Medical Informatics 124, 37–48, 2019.
DOI: https://doi.org/10.1016/j.ijmedinf.2019.01.005   Google Scholar

PAD-UFES-20 Dataset [https://data.mendeley.com/datasets/zr7vgbcyr2/1] (accessed: 23.03.2022).
  Google Scholar

PH2 Dataset [https://www.fc.up.pt/addi/ph2%20database.html] (accessed 23.03.2022).
  Google Scholar

Qin Z. et al.: A GAN-based image synthesis method for skin lesion classification. Computer Methods and Programs in Biomedicine, 105568, 2020.
DOI: https://doi.org/10.1016/j.cmpb.2020.105568   Google Scholar

Raza R. et al.: Melanoma Classification from dermoscopy images using ensemble of convolutional neural networks. Mathematics 10, 26, 2022.
DOI: https://doi.org/10.3390/math10010026   Google Scholar

Sandler M. et al.: MobileNetV2: Inverted Residuals and Linear Bottlenecks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, 4510–4520.
DOI: https://doi.org/10.1109/CVPR.2018.00474   Google Scholar

Simonyan K., Zisserman A.: Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations ICLR, 2015.
  Google Scholar

Szegedy C. et al.: Inception-v4, Inception-ResNet and the impact of residual connections on learning. AAAI, 4278–4284, 2017.
DOI: https://doi.org/10.1609/aaai.v31i1.11231   Google Scholar

Tschandl P. et al.: Comparison of the accuracy of human readers versus machine-learning algorithms for pigmented skin lesion classification: an open, webbased, international, diagnostic study. Lancet Oncol 2019b(20), 938–947, 2019.
DOI: https://doi.org/10.1016/S1470-2045(19)30333-X   Google Scholar

Villa-Pulgarin J. et al.: Optimized convolutional neural network models for skin lesion classification, Computers, Materials & Continua Tech Science Press, CMC 70(2), 2022
DOI: https://doi.org/10.32604/cmc.2022.019529   Google Scholar

Yu C. et al.: Acral melanoma detection using a convolutional neural network for dermoscopy images. PLoS ONE 2018, 13, e0193321, 2018.
DOI: https://doi.org/10.1371/journal.pone.0193321   Google Scholar

Zakład Epidemiologii i Prewencji Nowotworów Centrum Onkologii – Instytut w Warszawie. Krajowy Rejestr Nowotworów (KRN) [http://onkologia.org.pl/] (accessed 02.08.2019).
  Google Scholar

Download


Published
2022-09-30

Cited by

Michalska-Ciekańska, M. (2022). DEEP NEURAL NETWORKS FOR SKIN LESIONS DIAGNOSTICS . Informatyka, Automatyka, Pomiary W Gospodarce I Ochronie Środowiska, 12(3), 50–53. https://doi.org/10.35784/iapgos.3042

Authors

Magdalena Michalska-Ciekańska 
mmagamichalska@gmail.com
Lublin University of Technology Poland
http://orcid.org/0000-0002-0874-3285

Statistics

Abstract views: 214
PDF downloads: 294