Multi-input melanoma classification using mobilenet-V3-large architecture

• Autorzy: Aksoy Serra

Identyfikatory

DOI

10.14313/jamris‐2025‐008

• Języki publikacji: EN

Abstrakty

EN

All over the globe there exists a serious problem with skin cancer, most especially melanoma; a malignancy which is known to behave aggressively and can metastasize. Detecting this early is the key to saving lives. This study introduces a new method of classifying melanoma using an advanced model known as MobileNet-V3-Large. This technique differs from others in that it considers both the images of the skin lesion and tabular data including factors consisting of the patient’s approximate age, gender and the location of the lesion on the body of the patient. Such an approach empowers the predictions of whether the skin lesion may be malignant or benign. Tested on a huge collection consisting of skin images combined with tabular data, it was established that this method outperforms others already existing. The results of this study showed that a high accuracy of 99.56% was achieved using the proposed model. This study indicates that utilizing the multi-input method will substantially enhance diagnosis for melanoma hence reducing mortal- ities in the future.

Słowa kluczowe

EN

melanoma cancer; benign; malignant; convolution neural network; CNN; deep learning; DL; pretrained model

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2025
• Tom: Vol. 19, No. 1
• Strony: 73--84
• Opis fizyczny: Bibliogr. 35 poz., rys.

Twórcy

autor

Aksoy Serra

• Ludwig Maximilian University of Munich (LMU), Munich, Geschwister-Scholl-Platz 1, 80539, Germany

Bibliografia

• [1] R. L. Siegel, K. D. Miller, H. E. Fuchs, and A. Jemal, “Cancer statistics, 2022,” CA A Cancer J Clinicians, vol. 72, no. 1, pp. 7-33, Jan. 2022, doi: 10.3322/caac.21708.
• [2] R. L. Siegel, K. D. Miller, N. S. Wagle, and A. Jemal, “Cancer statistics, 2023,” CA A Cancer J Clinicians, vol. 73, no. 1, pp. 17-48, Jan. 2023, doi: 10.3322/caac.21763.
• [3] S. Aksoy, P. Demircioglu, and I. Bogrekci, “Enhancing Melanoma Diagnosis with Advanced Deep Learning Models Focusing on Vision Transformer, Swin Transformer, and ConvNeXt,” Dermatopathology, vol. 11, no. 3, pp. 239-252, Aug. 2024, doi: 10.3390/dermatopathology 11030026.
• [4] A. K. Nambisan et al., “Improving Automatic Melanoma Diagnosis Using Deep Learning-Based Segmentation of Irregular Networks,” Cancers, vol. 15, no. 4, p. 1259, Feb. 2023, doi: 10.3390/cancers15041259.
• [5] R. Ashraf et al., “Region-of-Interest Based Transfer Learning Assisted Framework for Skin Cancer Detection,” IEEE Access, vol. 8, pp. 147858-147871, 2020, doi: 10.1109/ACCESS.2020.3014701.
• [6] M. Elgamal, “Automatic Skin Cancer Images Classification,” IJACSA, vol. 4, no. 3, 2013, doi: 10.14569/IJACSA.2013.040342.
• [7] F. Xiang, R. Lucas, S. Hales, and R. Neale, “Incidence of Nonmelanoma Skin Cancer in Relation to Ambient UV Radiation in White Populations, 1978-2012: Empirical Relationships,” JAMA Dermatol, vol. 150, no. 10, p. 1063, Oct. 2014, doi: 10.1001/jamadermatol.2014.762.
• [8] A. Stratigos et al., “Diagnosis and treatment of invasive squamous cell carcinoma of the skin: European consensus-based interdisciplinary guideline,” European Journal of Cancer, vol. 51, no. 14, pp. 1989-2007, Sep. 2015, doi: 10.1016/j.ejca.2015.06.110.
• [9] D. Koh, H. Wang, J. Lee, K. S. Chia, H. P. Lee, and C. L. Goh, “Basal cell carcinoma, squamous cel carcinoma and melanoma of the skin: analysis of the Singapore Cancer Registry data 1968-97,” Br J Dermatol, vol. 148, no. 6, pp. 1161-1166, Jun.2003, doi: 10.1046/j.1365-2133.2003.05223.x.
• [10] L. Fania et al., “Basal Cell Carcinoma: From Pathophysiology to Novel Therapeutic Approaches,” Biomedicines, vol. 8, no. 11, p. 449, Oct. 2020, doi: 10.3390/biomedicines8110449.
• [11] L. Fania et al., “Cutaneous Squamous Cell Carcinoma: From Pathophysiology to Novel Therapeutic Approaches,” Biomedicines, vol. 9, no. 2, p. 171, Feb. 2021, doi: 10.3390/biomedicines9020171.
• [12] S. K. T. Que, F. O. Zwald, and C. D. Schmults, “Cutaneous squamous cell carcinoma,”Journal of the American Academy of Dermatology, vol. 78, no. 2, pp. 237-247, Feb. 2018, doi: 10.1016/j.jaad.2017.08.059.
• [13] M. Rubatto et al., “Classic and new strategies for the treatment of advanced melanoma and non-melanoma skin cancer,” Front. Med., vol. 9, p. 959289, Feb. 2023, doi: 10.3389/fmed.2022.959289.
• [14] S. R. Waheed, N. M. Suaib, M. S. Mohd Rahim, M. Mundher Adnan, and A. A. Salim, “Deep Learning Algorithms-based Object Detection and Localization Revisited,” J. Phys.: Conf. Ser., vol. 1892, no. 1, p. 012001, Apr. 2021, doi: 10.1088/1742-6596/1892/1/012001.
• [15] S. R. Waheed et al., “Melanoma Skin Cancer Classification based on CNN Deep Learning Algorithms,” Mal. J. Fund. Appl. Sci., vol. 19, no. 3, pp. 299-305, May 2023, doi: 10.11113/mjfas.v19n3.2900.
• [16] F. Pereira Dos Santos and M. Antonelli Ponti, “Robust Feature Spaces from Pre-Trained Deep Network Layers for Skin Lesion Classification,” in 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Parana: IEEE, Oct. 2018, pp. 189-196. doi: 10.1109/SIBGRAPI.2018.00031.
• [17] P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multisource dermatoscopic images of common pigmented skin lesions,” Sci Data, vol. 5, no. 1, p. 180161, Aug. 2018, doi: 10.1038/sdata.2018.161.
• [18] D. Gutman et al., “Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC),” 2016, doi: 10.48550/ARXIV.1605.01397.
• [19] N. Codella et al., “Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC),” 2019, doi: 10.48550/ARXIV.1902.03368.
• [20] B. Cassidy, C. Kendrick, A. Brodzicki, J. Jaworek-Korjakowska, and M. H. Yap, “Analysis of the ISIC image datasets: Usage, benchmarks and recommendations,” Medical Image Analysis, vol. 75, p. 102305, Jan. 2022, doi: 10.1016/j.media.2021.102305.
• [21] M. Combalia et al., “BCN20000: Dermoscopic Lesions in the Wild,” 2019, doi: 10.48550/ARXIV.1908.02288.
• [22] K. Ali, Z. A. Shaikh, A. A. Khan, and A. A. Laghari, “Multiclass skin cancer classification using EfficientNets - a first step towards preventing skin cancer,” Neuroscience Informatics, vol. 2, no. 4, p. 100034, Dec. 2022, doi: 10.1016/j.neuri.2021.100034.
• [23] K. H. Cheong et al., “An automated skin melanoma detection system with melanoma-index based on entropy features,” Biocybernetics and Biomedical Engineering, vol. 41, no. 3, pp. 997-1012, Jul. 2021, doi: 10.1016/j.bbe.2021.05.010.
• [24] N. Alfed and F. Khelifi, “Bagged textural and color features for melanoma skin cancer detection in dermoscopic and standard images,” Expert Systems with Applications, vol. 90, pp. 101-110, Dec. 2017, doi: 10.1016/j.eswa.2017.08.010.
• [25] Q. Ul Ain, Bing Xue, H. Al-Sahaf, and M. Zhang, “Genetic programming for skin cancer detectionin dermoscopic images,” in 2017 IEEE Congress on Evolutionary Computation (CEC), Donostia, San Sebastián, Spain: IEEE, Jun. 2017, pp. 2420-2427. doi: 10.1109/CEC.2017.7969598.
• [26] R. Garg, S. Maheshwari, and A. Shukla, “Decision Support System for Detection and Classification of Skin Cancer using CNN,” 2019, doi: 10.48550/ARXIV.1912.03798.
• [27] T. H. H. Aldhyani, A. Verma, M. H. Al-Adhaileh, and D. Koundal, “Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network,” Diagnostics, vol. 12, no. 9, p. 2048, Aug. 2022, doi: 10.3390/diagnostics12092048.
• [28] S. K. Datta, M. A. Shaikh, S. N. Srihari, and M. Gao, “Soft-Attention Improves Skin Cancer Classification Performance,” 2021, doi: 10.48550/ARXIV.2105.03358.
• [29] M. Abd Elaziz, A. Dahou, A. Mabrouk, S. El-Sappagh, and A. O. Aseeri, “An Efficient Artificial Rabbits Optimization Based on Mutation Strategy For Skin Cancer Prediction,” Computers in Biology and Medicine, vol. 163, p. 107154, Sep. 2023, doi: 10.1016/j.compbiomed.2023.107154.
• [30] C. Xin et al., “An improved transformer network for skin cancer classification,” Computers in Biology and Medicine, vol. 149, p. 105939, Oct. 2022, doi: 10.1016/j.compbiomed.2022.105939.
• [31] S. Gupta, N. Sharma, R. Tyagi, P. Singh, A. Aggarwal, and S. Chawla, “Cognitive Inspired & Computationally-Intelligent Early Melanoma Detection Using Feature Analysis Techniques,” JAIT, Oct. 2023, doi: 10.37965/jait.2023.0334.
• [32] K. Kachare, N. Bhagat, and P. Raundale, “Advancements in Melanoma Skin Cancer Detection Using Deep Learning: A Comprehensive Review,” in 2023 7th International Conference On Computing, Communication, Control And Automation (ICCUBEA), Pune, India: IEEE, Aug. 2023, pp. 1-6. doi: 10.1109/ICCUBEA58933.2023.10392174.
• [33] K. Tomar, U. Panwar, and R. Gupta, “A melanoma skin cancer detection and analysis using dermoscopy image processing,” presented at the MACHINE LEARNING AND INFORMATION PROCESSING: PROCEEDINGS OF ICMLIP 2023, Ranchi, India, 2023, p. 080007. doi: 10.1063/5.0168906.
• [34] R. Mittal, F. Jeribi, R. J. Martin, V. Malik, S. J. Menachery, and J. Singh, “DermCDSM: Clinical Decision Support Model for Dermatosis Using Systematic Approaches of Machine Learning and Deep Learning,” IEEE Access, vol. 12, pp. 47319-47337, 2024, doi: 10.1109/ACCESS.2024.3373539.
• [35] S. Aksoy, P. Demircioglu, and I. Bogrekci, “Advanced Artificial Intelligence Techniques for Comprehensive Dermatological Image Analysis and Diagnosis,” Dermato 2024, vol. 4, no. 4, pp. 173-186, doi: 10.3390/dermato4040015.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).