DEEP LEARNING BASED APPROACH FOR DETECTION OF MELANOMA AND NON-MELANOMA FROM DERMASCOPIC IMAGES
Keywords:
Skin diseases, Melanoma, Non-melanoma, Deep learning, Convolutional Neural Networks.Abstract
Amid growing concerns about global skin diseases, there is an urgent need for innovative applications to mitigate their impact and improve overall skin health. Skin problems, stemming from a combination of genetic factors and environmental influences, underscore the global significance of effective diagnosis and treatment. Theproblem statement is to figure out if a skin issue is the serious kind called melanoma ornot, so we can treat it the right way. Current diagnostic approaches relying on Gaussian Naive Bayes models reveal limitations in accuracy and sensitivity, necessitating a transformative shift. The research advocates for a paradigm change towards a Deep Learning-Based Automated Classification system, specifically leveragingConvolutional Neural Networks (CNNs) for heightened precision in classifying melanoma and non-melanoma skin diseases from dermascopic images. The proposed methodology entails importing dermoscopic image data, implementing tailored preprocessing, and defining variables before applying CNNs to extract intricate patterns. Performance metrics, including accuracy and confusion matrix, gauge the model's efficacy compared to the Gaussian Naive Bayes model. By transitioning to a deep learning approach, this study aims to overcome the limitations of the current Gaussian Naive Bayes model, providing a more sophisticated and automated solution for precise skin disease classification. The primary objective is to contribute
to the reduction of skin disorders, offering an efficient tool for classifying melanoma or non-melanoma skin diseases and thereby enhancing public health outcomes.
Downloads
References
Gajera, Himanshu K., Deepak Ranjan Nayak, and Mukesh A. Zaveri. "A comprehensive
analysis of dermoscopy images for melanoma detection via deep CNN features." Biomedical
Signal Processing and Control 79 (2023): 104186.
Zhou, Yufei, Can Koyuncu, Cheng Lu, Rainer Grobholz, Ian Katz, Anant Madabhushi, and
Andrew Janowczyk. "Multi-site cross-organ calibrated deep learning (MuSClD):
Automated diagnosis of non-melanoma skin cancer." Medical image analysis 84 (2023):
Albraikan, Amani Abdulrahman, Nadhem Nemri, Mimouna Abdullah Alkhonaini, Anwer
Mustafa Hilal, Ishfaq Yaseen, and Abdelwahed Motwakel. "Automated Deep Learning Based
Melanoma Detection and Classification Using Biomedical Dermoscopic Images." Computers,
Materials & Continua 74,no. 2 (2023).
Wamane, Niharika, Aishwarya Yadav, Jidnyasa Bhoir, Deep Shelke, and Deepali Kadam.
"Comparison of Deep Learning Algorithms for Early Detectionof Melanoma Skin Cancer on
Dermoscopic and Non-dermoscopic Images." In International Conference on Multi-
disciplinary Trends in Artificial Intelligence, pp. 778-785. Cham: Springer Nature
Switzerland, 2023.
Nigar, N., A. Wajid, S. Islam, and M. K. Shahzad. "Skin cancer classification: adeep learning
approach." Pakistan Journal of Science 75, no. 02 (2023).
Sivakumar, M. Senthil, L. Megalan Leo, T. Gurumekala, V. Sindhu, and A. Saraswathi
Priyadharshini. "Deep learning in skin lesion analysis for malignant melanoma cancer
identification." Multimedia Tools and Applications (2023): 1-21.
Ali Shah, Asghar, Ayesha Sher Ali Shaker, Sohail Jabbar, Qaisar Abbas, Talal Saad Al-
Balawi, and M. Emre Celebi. "An ensemble-based deep learning model for detection of
mutation causing cutaneous melanoma." Scientific Reports 13, no. 1 (2023): 22251.
Sauter, Daniel, Georg Lodde, Felix Nensa, Dirk Schadendorf, Elisabeth Livingstone, andMarkus Kukuk. "Deep learning in computational dermatopathology of melanoma: A
technical systematic literature review." Computers in Biology and Medicine (2023):
Nambisan, Anand K., Akanksha Maurya, Norsang Lama, Thanh Phan, Gehana Patel, Keith
Miller, Binita Lama, Jason Hagerty, Ronald Stanley, and William
V. Stoecker. "Improving automatic melanoma diagnosis using deep learning- based
segmentation of irregular networks." Cancers 15, no. 4 (2023): 1259
Rahman, Md Mahbubur, Mostofa Kamal Nasir, Md Nur-A-Alam, and Md Saikat Islam
Khan. "Proposing a hybrid technique of feature fusion and convolutional neural network for
melanoma skin cancer detection." Journal of Pathology Informatics 14 (2023): 100341
Bharathi, G., M. Malleswaran, and V. Muthupriya. "Detection and diagnosis of
melanoma skin cancers in dermoscopic images using pipelined internal module architecture
(PIMA) method." Microscopy Research and Technique 86, no. 6 (2023): 701-713.
Tembhurne, Jitendra V., Nachiketa Hebbar, Hemprasad Y. Patil, and Tausif Diwan.
"Skin cancer detection using ensemble of machine learning and deep learning techniques."
Multimedia Tools and Applications (2023): 1-24.
Sukanya, S. T., and S. Jerine. "Skin lesion analysis towards melanoma detection using
optimized deep learning network." Multimedia Tools and Applications (2023): 1-23.
Gayatri, Erapaneni, and S. L. Aarthy. "Challenges and Imperatives of Deep Learning
Approaches for Detection of Melanoma: A Review." International Journal of Image and
Graphics 23, no. 03 (2023): 2240012.
Hussien, Maha Ali, and Abbas H. Hassin Alasadi. "Classification of melanoma skin
cancer using deep learning approach." TELKOMNIKA (Telecommunication Computing
Electronics and Control) 22,no. 1 (2024): 129-137
Downloads
Published
Issue
Section
License
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
