Abstract

Skin lesions, which comprise a wide range of irregularities in skin appearance, might serve as precursors of skin cancer due to the complex interaction of hereditary variables and longterm UV ex- posure. Significant advances in dermatology have been made with the use of deep learning models, notably convolutional neural net- works (CNNs). These models excel in analyzing dermatoscopic pictures, allowing for early and accurate identification of a vari- ety of skin problems. In this work, a complete evaluation of deep learning models for predicting skin lesions is conducted, with an emphasis on accuracy. Notable performers include DenseNet169 and ResNet101, both of which achieve an outstanding 91% accu- racy. Furthermore, a hybrid model obtains an accuracy of 89%, in- dicating its capacity to recognize complicated visual patterns. The study investigates model fusion strategies to capitalize on possible synergy in prediction skills, ultimately improving automated der- matological diagnosis systems. Notable models are DenseNet121, ResNet-50V2, and InceptionResNetV2, which contribute consider- ably with accuracies of 91%, 89%, and 85%, respectively, while MobileNetV2 and VGG-16 provide accuracies of 82% and 80%. These advances, taken together, enable the development of strong and accurate diagnostic technologies capable of efficiently expedit- ing skin health interventions.

References

• Neeshma, A. and Nair, C.S., 2022, August. Multiclass Skin Lesion Classification Using Densenet. In 2022 Third Interna- tional Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT) (pp. 506-510). IEEE.
• SO¨ NMEZ, A.F., C¸ AKAR, S., CEREZC˙I, F., KOTAN,
• M., DEL˙IBAS¸ OG˘ LU, ˙I. and Gu¨lu¨zar, C¸ .˙I.T., 2023. Deep Learning-Based Classification of Dermoscopic Images for Skin Lesions. Sakarya University Journal of Computer and Information Sciences, 6(2), pp.114-122.
• Jasil, S.G. and Ulagamuthalvi, V., 2021, May. Skin lesion classification using pre-trained DenseNet201 deep neural net- work. In 2021 3rd international conference on signal process- ing and communication (ICPSC) (pp. 393-396). IEEE.
• Wu, Y., Lariba, A.C., Chen, H. and Zhao, H., 2022, July. Skin Lesion Classification based on Deep Convolutional Neu- ral Network. In 2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS) (pp. 376-380). IEEE.
• Purnama, I.K.E., Hernanda, A.K., Ratna, A.A.P., Nurtanio, I., Hidayati, A.N., Purnomo, M.H., Nugroho, S.M.S. and Rach- madi, R.F., 2019, November. Disease classification based on dermoscopic skin images using convolutional neural network in teledermatology system. In 2019 international conference on computer engineering, network, and intelligent multimedia (CENIM) (pp. 1-5). IEEE.
• Salian, A.C., Vaze, S., Singh, P., Shaikh, G.N., Chapaneri, S. and Jayaswal, D., 2020, April. Skin lesion classification using deep learning architectures. In 2020 3rd International confer- ence on communication system, computing and IT applica- tions (CSCITA) (pp. 168-173). IEEE.
• Quang, N.H., 2017, November. Automatic skin lesion anal- ysis towards melanoma detection. In 2017 21st Asia Pacific symposium on intelligent and evolutionary systems (IES) (pp. 106-111). IEEE.
• Mikołajczyk, A. and Grochowski, M., 2018, May. Data aug- mentation for improving deep learning in image classification problem. In 2018 international interdisciplinary PhD work- shop (IIPhDW) (pp. 117-122). IEEE.
• “Skin Cancer MNIST: HAM10000,” www.kaggle.com. https://www.kaggle.com/datasets/kmader/skin-cancer-mnist- ham10000
• Shetty, B., Fernandes, R., Rodrigues, A.P., Chengoden, R., Bhattacharya, S. and Lakshmanna, K., 2022. Skin lesion classification of dermoscopic images using machine learning and convolutional neural network. Scientific Reports, 12(1), p.18134.
• Mahbod, A., Schaefer, G., Wang, C., Ecker, R., Dorffner, G. and Ellinger, I., 2021, January. Investigating and exploiting image resolution for transfer learning-based skin lesion clas- sification. In 2020 25th international conference on pattern recognition (ICPR) (pp. 4047-4053). IEEE.
• Zhang, Y. and Wang, C., 2021, March. SIIM-ISIC melanoma classification with DenseNet. In 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) (pp. 14-17). IEEE.
• Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. and Chen, L.C., 2018. Mobilenetv2: Inverted residuals and linear bottle- necks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510-4520).
• Ogundokun, R.O., Li, A., Babatunde, R.S., Umezuruike, C., Sadiku, P.O., Abdulahi, A.T. and Babatunde, A.N., 2023. En- hancing skin cancer detection and classification in dermo- scopic images through concatenated MobileNetV2 and xcep- tion models. Bioengineering, 10(8), p.979.
• Arya, M.S., Prabahavathy, P. and Ahamed, S., 2022. Skin le- sion classification and Prediction by Data Augmentation in HAM10000 and ISIC 2019 dataset.
• Kondaveeti, H.K. and Edupuganti, P., 2020, December. Skin cancer classification using transfer learning. In 2020 IEEE In- ternational Conference on Advent Trends in Multidisciplinary Research and Innovation (ICATMRI) (pp. 1-4). IEEE.
• Shah, V., Autee, P. and Sonawane, P., 2020, December. Detec- tion of melanoma from skin lesion images using deep learning techniques. In 2020 International Conference on Data Science and Engineering (ICDSE) (pp. 1-8). IEEE.
• Quang, N.H., 2017, November. Automatic skin lesion anal- ysis towards melanoma detection. In 2017 21st Asia Pacific symposium on intelligent and evolutionary systems (IES) (pp. 106-111). IEEE.
• Salian, A.C., Vaze, S., Singh, P., Shaikh, G.N., Chapaneri, S. and Jayaswal, D., 2020, April. Skin lesion classification using deep learning architectures. In 2020 3rd International confer- ence on communication system, computing and IT applica- tions (CSCITA) (pp. 168-173). IEEE.
• Ahmed, S.A.A., Yanikog˘lu, B., Go¨ksu, O¨ . and Aptoula, E., 2020, October. Skin lesion classification with deep CNN en- sembles. In 2020 28th Signal Processing and Communica- tions Applications Conference (SIU) (pp. 1-4). IEEE.
• Nguyen, V.D., Bui, N.D. and Do, H.K., 2022. Skin lesion classification on imbalanced data using deep learning with soft attention. Sensors, 22(19), p.7530.
• Sachdev, J., Shekhar, S. and Indu, S., 2018, April. Melanoma screening using deep neural networks. In 2018 3rd Interna- tional Conference for Convergence in Technology (I2CT) (pp. 1-5). IEEE.
• Mahbod, A., Schaefer, G., Wang, C., Ecker, R. and Ellinge, I., 2019, May. Skin lesion classification using hybrid deep neu- ral networks. In ICASSP 2019-2019 IEEE international con- ference on acoustics, speech and signal processing (ICASSP) (pp. 1229-1233). IEEE.
• Lopez, A.R., Giro-i-Nieto, X., Burdick, J. and Marques, O., 2017, February. Skin lesion classification from dermo- scopic images using deep learning techniques. In 2017 13th IASTED international conference on biomedical engineering (BioMed) (pp. 49-54). IEEE.
• Moldovan, D., 2019, November. Transfer learning based method for two-step skin cancer images classification. In 2019 E-Health and Bioengineering Conference (EHB) (pp. 1- 4). IEEE.
• Jain, S., Singhania, U., Tripathy, B., Nasr, E.A., Aboudaif, M.K. and Kamrani, A.K., 2021. Deep learning-based trans- fer learning for classification of skin cancer. Sensors, 21(23), p.8142