Evaluation of EfficientNet deep network settings on dermoscopic datasets
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1337Keywords:
Artificial Intelligence, Medical Informatics, Skin NeoplasmsAbstract
Objective: To investigate pioneer settings of the EfficientNet-B2 deep network to classify small dermoscopic databases. Method: An approach for (1) image pre-processing, (2) classification with eight settings to fine-tune a pretrained EfficientNet-B2, and (3) classifier evaluation with stratified cross-validation in three dermoscopic databases. Results: All the models outperformed a baseline. Some statistical differences among them were found. The best network reached an average Accuracy of 98.33% in the PH2 public dataset. Conclusion: Some pioneer configurations of the deep network were found to be competitive against recent references in dermoscopy classification.
References
Malik FS, Yousaf MH, Sial HA, Viriri S. Exploring dermoscopic structures for melanoma lesions’ classification. Front Big Data. 2024;7:1366312. DOI: https://doi.org/10.3389/fdata.2024.1366312
Spolaôr N, Lee HD, Mendes AI, Nogueira CV, Parmezan ARS, Takaki WSR, et al. Fine-tuning pre-trained neural networks for medical image classification in small clinical datasets. Multimed Tools Appl. 2024;83(9):27305-29. DOI: https://doi.org/10.1007/s11042-023-16529-w
Balaha HM, Hassan AES. Skin cancer diagnosis based on deep transfer learning and sparrow search algorithm. Neural Comput Appl. 2023;35(1):815-53. DOI: https://doi.org/10.1007/s00521-022-07762-9
Instituto Nacional de Câncer (BR). Estimativa 2023: incidência de câncer no Brasil [Internet]. Rio de Janeiro: Instituto Nacional de Câncer; 2023 [citado 2024 Mai 22]. Disponível em: https://www.inca.gov.br/publicacoes/livros/estimativa-2023-incidencia-de-cancer-no-brasil.
Venugopal V, Raj NI, Nath MK, Stephen N. A deep neural network using modified EfficientNet for skin cancer detection in dermoscopic images. Decision Analytics Journal. 2023;8:100278. DOI: https://doi.org/10.1016/j.dajour.2023.100278
Bansal P, Garg R, Soni P. Detection of melanoma in dermoscopic images by integrating features extracted using handcrafted and deep learning models. Comput Ind Eng. 2022;168:108060. DOI: https://doi.org/10.1016/j.cie.2022.108060
Hasan Rafi T, Shubair RM. A scaled-2D CNN for skin cancer diagnosis. In: Hallinan J, Chetty M, Heredia GR, et al., editors. Proceedings of the 18th IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology; 2021; Melbourne, Australia. [New York]: Curran Associates; 2021. p. 1-6. DOI: https://doi.org/10.1109/CIBCB49929.2021.9562888
Chollet F, Kalinowski T, Allaire JJ. Deep learning in R. 2nd ed. Shelter Island: Manning publications; 2022.
Liu XJ, Li Kl, Luan Hy, Wang Wh, Chen Zy. Few-shot learning for skin lesion image classification. Multimed Tools Appl. 2022;81(4):4979-90. DOI: https://doi.org/10.1007/s11042-021-11472-0
Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. In: Chaudhuri K, Salakhutdinov R, editors. Proceedings of the 36th International Conference on Machine Learning; 2019; Long Beach, United States. [Brookline]: [Microtome Publishing]; 2019. p. 6105-14.
Jaisakthi SM, Mirunalini P, Aravindan C, Appavu R. Classification of skin cancer from dermoscopic images using deep neural network architectures. Multimed Tools Appl. 2023;82(10):15763-78. DOI: https://doi.org/10.1007/s11042-022-13847-3
Tajerian A, Kazemian M, Tajerian M, Akhavan Malayeri A. Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images. PLoS One. 2023;18(4):1-17. DOI: https://doi.org/10.1371/journal.pone.0284437
Papiththira S, Kokul T. Melanoma skin cancer detection using EfficientNet and channel attention module. In: Wijayakulasooriya J, editor. Proceedings of the 16th IEEE International Conference on Industrial and Information Systems; 2021; Kandy, Sri Lanka. [New York]: Curran Associates; 2021. p. 227-32. DOI: https://doi.org/10.1109/ICIIS53135.2021.9660759
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: Large-scale machine learning on heterogeneous systems. Version 2.14 [software]. 2023 [cited 2024 May 22]. Available from: http://tensorflow.org.
Lee HD, Mendes AI, Spolaôr N, Oliva JT, Sabino Parmezan AR, Chung WF, et al. Dermoscopic assisted diagnosis in melanoma: Reviewing results, optimizing methodologies and quantifying empirical guidelines. Knowl Based Syst. 2018;158:9-24. DOI: https://doi.org/10.1016/j.knosys.2018.05.016
Machado M, Pereira J, Fonseca-Pinto R. Classification of reticular pattern and streaks in dermoscopic images based on texture analysis. J Med Imaging. 2015;2(4):044503. DOI: https://doi.org/10.1117/1.JMI.2.4.044503
Argenziano G, Zalaudek I. Dermoscopy: a new perspective. Dermatol Pract Concept. 2011;1(1):57-8. DOI: https://doi.org/10.5826/dpc.0101a12
Boer A, Nischal K. A growing online resource for learning dermatology and dermatopathology. Indian J Dermatol Venereol Leprol. 2007;73(2):138-40. DOI: https://doi.org/10.4103/0378-6323.31909
Mendonça TF, Ferreira PM, Marçal ARS, Barata C, Marques JS, Rocha J, et al. PH2: A public database for the analysis of dermoscopic images. In: Celebi ME, Mendonça TF, Marques JS, editors. Dermoscopy Image Analysis. Boca Ratón: CRC Press; 2016. p. 419-40.
Codella N, Rotemberg V, Tschandl P, Celebi ME, Dusza S, Gutman D, et al. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (ISIC). arXiv: 1902.03368 [Preprint]. 2019 [cited 2024 May 22]: [12 p.]. Available from: https://arxiv.org/abs/1902.03368.
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. MobileNetV2: Inverted residuals and linear bottlenecks. In: Brown MS, Morse B, Peleg S, editors. Proceedings of the 31st IEEE Conference on Computer Vision and Pattern Recognition; 2018; Salt Lake City, United States. [Washington]: IEEE Computer Society; 2018. p. 4510-20. DOI: https://doi.org/10.1109/CVPR.2018.00474
Witten IH, Frank E, Hall MA, Pal CJ. Data mining: Practical machine learning tools and techniques. 4th ed. Burlington: Morgan Kaufmann; 2016.
Velden BHM, Kuijf HJ, Gilhuijs KGA, Viergever MA. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Med Image Anal. 2022;79:102470. DOI: https://doi.org/10.1016/j.media.2022.102470
Chougrad H, Zouaki H, Alheyane O. Deep convolutional neural networks for breast cancer screening. Comput Methods Programs Biomed. 2018;157:19-30. DOI: https://doi.org/10.1016/j.cmpb.2018.01.011
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
