Skin Cancer Classification Using Fine-Tuned Transfer Learning of DENSENET-121

被引:10
作者
Bello, Abayomi [1 ]
Ng, Sin-Chun [1 ]
Leung, Man-Fai [1 ]
机构
[1] Anglia Ruskin Univ, Fac Sci & Engn, Sch Comp & Informat Sci, Cambridge CB1 1PT, England
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 17期
关键词
deep learning; transfer learning; skin lesions; VGG16; Resnet; Densenet; Inceptionnet; CNN;
D O I
10.3390/app14177707
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Skin cancer diagnosis greatly benefits from advanced machine learning techniques, particularly fine-tuned deep learning models. In our research, we explored the impact of traditional machine learning and fine-tuned deep learning approaches on prediction accuracy. Our findings reveal significant improvements in predictability and accuracy with fine-tuning, particularly evident in deep learning models. The CNN, SVM, and Random Forest Classifier achieved high accuracy. However, fine-tuned deep learning models such as EfficientNetB0, ResNet34, VGG16, Inception _v3, and DenseNet121 demonstrated superior performance. To ensure comparability, we fine-tuned these models by incorporating additional layers, including one flatten layer and three densely interconnected layers. These layers play a crucial role in enhancing model efficiency and performance. The flatten layer preprocesses multidimensional feature maps, facilitating efficient information flow, while subsequent dense layers refine feature representations, capturing intricate patterns and relationships within the data. Leveraging LeakyReLU activation functions in the dense layers mitigates the vanishing gradient problem and promotes stable training. Finally, the output dense layer with a sigmoid activation function simplifies decision making for healthcare professionals by providing binary classification output. Our study underscores the significance of incorporating additional layers in fine-tuned neural network models for skin cancer classification, offering improved accuracy and reliability in diagnosis.
引用
收藏
页数:25
相关论文
共 37 条
[1]  
Agrahari P., 2022, Futuristic communication and network technologies: Select proceedings of VICFCNT 2020, P179, DOI DOI 10.1007/978-981-16-4625-618
[2]  
[Anonymous], Radiation: Ultraviolet (UV) radiation and skin cancer, 2021
[3]   Transcription of human papillomaviruses in nonmelanoma skin cancers of the immunosuppressed [J].
Arroyo Muhr, Laila Sara ;
Hultin, Emilie ;
Dillner, Joakim .
INTERNATIONAL JOURNAL OF CANCER, 2021, 149 (06) :1341-1347
[4]  
Milton MAA, 2019, Arxiv, DOI [arXiv:1901.10802, 10.48550/arXiv.1901.10802]
[5]   A BERT Framework to Sentiment Analysis of Tweets [J].
Bello, Abayomi ;
Ng, Sin-Chun ;
Leung, Man-Fai .
SENSORS, 2023, 23 (01)
[6]  
Borges A.L., 2017, Dermatology in Public Health Environments, P1157, DOI [10.1007/978-3-319-33919-1_56, DOI 10.1007/978-3-319-33919-156]
[7]   Deep neural networks are superior to dermatologists in melanoma image classification [J].
Brinker, Titus J. ;
Hekler, Achim ;
Enk, Alexander H. ;
Berking, Carola ;
Haferkamp, Sebastian ;
Hauschild, Axel ;
Weichenthal, Michael ;
Klode, Joachim ;
Schadendorf, Dirk ;
Holland-Letz, Tim ;
von Kalle, Christof ;
Froehling, Stefan ;
Schilling, Bastian ;
Utikal, Jochen S. .
EUROPEAN JOURNAL OF CANCER, 2019, 119 :11-17
[8]   Extraction of features from cross correlation in space and frequency domains for classification of skin lesions [J].
Chatterjee, Saptarshi ;
Dey, Debangshu ;
Munshi, Sugata ;
Gorai, Surajit .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2019, 53
[9]   Tensor Factorization With Sparse and Graph Regularization for Fake News Detection on Social Networks [J].
Che, Hangjun ;
Pan, Baicheng ;
Leung, Man-Fai ;
Cao, Yuting ;
Yan, Zheng .
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2024, 11 (04) :4888-4898
[10]  
Codella Noel, 2015, Machine Learning in Medical Imaging. 6th International Workshop, MLMI 2015, held in conjunction with MICCAI 2015. Proceedings: LNCS 9352, P118, DOI 10.1007/978-3-319-24888-2_15