IJBTT

Advancing Skin Cancer Lesion Detection and Classification: A State-of-the-Art Approach Integrating Convolutional Neural Networks and Graph Neural Networks

Advancing Skin Cancer Lesion Detection and Classification: A State-of-the-Art Approach Integrating Convolutional Neural Networks and Graph Neural Networks
	© 2024 by IJETT Journal
	Volume-72 Issue-7
	Year of Publication : 2024
	Author : Dhatri Raval, Jaimin N Undavia
	DOI : 10.14445/22315381/IJETT-V72I7P116

How to Cite?

Dhatri Raval, Jaimin N Undavia, "Advancing Skin Cancer Lesion Detection and Classification: A State-of-the-Art Approach Integrating Convolutional Neural Networks and Graph Neural Networks," International Journal of Engineering Trends and Technology, vol. 72, no. 7, pp. 147-156, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I7P116

Abstract
Identifying skin cancer on time is very important for effective treatment and enhanced results in patients. In this study, an innovative approach is proposed that harnesses the power of deep learning through a hybrid model. The hybrid model of Convolutional Neural Network (CNN) architectures like Graph-Convolutional-Neural-Network (GCNN) or even ResNet for improvement in cancer detection accuracy. To address challenges related to image quality and noise, we employ preprocessing on images, such as image resizing and purifying on skin cancer images. For completing the tasks of augmented training data set and enhancing the quality of the hybrid CNN-GNN model, different augmentation methods are used. Through rigorous evaluation it is demonstrated that the hybrid CNN-GCNN approach surpasses emerging methods, emerging as the most effective solution for skin cancer detection. The proposed hybrid model achieves dramatic performance on the skin cancer dataset, and the accuracy obtained is around 99.8% with a loss of 0.1212. The accuracy of validation is 96.8%, with a loss of 0.1401. The obtained results underscore the efficacy of the hybrid CNN-GNN model in accurately identifying skin cancer lesions. By leveraging the complementary dominance of architectures of CNN and GNN, the hybrid approach showcases promising outcomes for the timely finding of skin cancer. The research plays a very important role in the advancements of clinical settings and offers a valuable tool in the diagnosis of skin cancer by clinicians. The diagnosis is prompt and effective, which improves patient care and outcomes.

Keywords
Computer-Aided Cancer Detection, Data Augmentation, Graphical Convolutional Neural Network (GCNN) and Convolutional Neural Network (CNN).

References
[1] Skin Cancer Statistics, World Cancer Research Fund International, 2021. [Online]. Available: https://www.wcrf.org/cancer-trends/skin-cancer-statistics/
[2] Mesut Toğaçar, Zafer Cömert, and Burhan Ergen, “Intelligent Skin Cancer Detection Applying Autoencoder, MobileNetV2 and Spiking Neural Networks,” Chaos, Solitons & Fractals, vol. 144, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Zhengshun Fei et al., “A GNN Architecture with Local and Global-Attention Feature for Image Classification,” IEEE Access, vol. 11, pp. 110221-110233, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Melanoma Awareness Month 2022, International Agency for Research on Cancer, World Health Organization, 2022. [Online]. Available: https://www.iarc.who.int/news-events/melanoma-awareness-month-2022/
[5] Dariusz Brzezinski et al., “Visual-based Analysis of Classification Measures and their Properties for Class Imbalanced Problems,” Information Sciences, vol. 462, pp. 242-261, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Nazeer Hussain Khan et al., “Skin Cancer Biology and Barriers to Treatment: Recent Applications of Polymeric Micro/Nanostructures,” Journal of Advanced Research, vol. 36, pp. 223-247, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Sonal Tina Lal et al., “Changing Trends of Skin Cancer: A Tertiary Care Hospital Study in Malwa Region of Punjab,” Journal of Clinical and Diagnostic Research, vol. 10, no. 6, pp. 12-15, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[8] “Basal and Squamous Cell Skin Cancer Risk Factors | Skin Cancer Risks.” Cancer.org, 2019. [Online]. Available: www.cancer.org/cancer/types/basal-and-squamous-cell-skin-cancer/causes-risks-prevention/risk-factors.html.
[9] Zachary R. Garrison et al., “Advances in Early Detection of Melanoma and the Future of At-Home Testing,” Life, vol. 13, no. 4, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Sara Medhat et al., “Skin Cancer Diagnosis using Convolutional Neural Networks for Smartphone Images: A Comparative Study,” Journal of Radiation Research and Applied Sciences, vol. 15, no. 1, pp. 262-267, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Yunendah Nur Fu'adah et al., “Convolutional Neural Network (CNN) for Automatic Skin Cancer Classification System,” IOP Conference Series: Materials Science and Engineering, vol. 982, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Amruta Mankawade et al., “Skin Cancer Detection and Intensity Calculator using Deep Learning,” 2023 International Conference for Advancement in Technology (ICONAT), Goa, India, pp. 1-4, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Agung W. Setiawan, “Effect of Color Enhancement on Early Detection of Skin Cancer Using Convolutional Neural Network,” 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT), Doha, Qatar, pp. 100-103, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ayesha Atta et al., “Classification of Skin Cancer Empowered with Convolutional Neural Network,” 2022 International Conference on Cyber Resilience (ICCR), Dubai, United Arab Emirates, pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ravi Manne, Snigdha Kantheti, and Sneha Kantheti, “Classification of Skin Cancer Using Deep Learning, ConvolutionalNeural Networks -Opportunities and vulnerabilities - A Systematic Review,” International Journal for Modern Trends in Science and Technology, vol. 6, no. 11, pp. 101-108, 2020.
[CrossRef] [Publisher Link]
[16] Jinen Daghrir et al., “Melanoma Skin Cancer Detection using Deep Learning and Classical Machine Learning Techniques: A Hybrid Approach,” 2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), Sousse, Tunisia, pp. 1-5, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Amy F. Bruce, Laurie Theeke, and Jennifer Mallow, “A State of the Science On Influential Factors Related to Sun Protective Behaviors to Prevent Skin Cancer in Adults,” International Journal of Nursing Sciences, vol. 4, no. 3, pp. 225-235, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Tehseen Mazhar et al., “The Role of Machine Learning and Deep Learning Approaches for the Detection of Skin Cancer,” Healthcare, vol. 11, no. 3, pp. 1-22, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] M. Krishna Monika et al., “Skin Cancer Detection and Classification Using Machine Learning,” Materials Today: Proceedings, vol. 33, no. 7, pp. 4266-4270, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] A. Dascalu, and E.O. David, “Skin Cancer Detection by Deep Learning and Sound Analysis Algorithms: A Prospective Clinical Study of an Elementary Dermoscope,” EBiomedicine, vol. 43, pp. 107-113, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Lisheng Wei, Kun Ding, and Huosheng Hu, “Automatic Skin Cancer Detection in Dermoscopy Images Based on Ensemble Lightweight Deep Learning Network,” IEEE Access, vol. 8, pp. 99633-99647, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Geetika Sharma, and Raman Chadha, “Skin Cancer and Oral Cancer Detection Using Deep Learning Technique,” 2022 IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, Ballari, India, pp. 1-5, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Harsh Bhatt et al., “State-of-the-Art Machine Learning Techniques for Melanoma Skin Cancer Detection and Classification: A Comprehensive Review,” Intelligent Medicine, vol. 3, no. 3, pp. 180-190, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Mohammad Ali Kadampur, and Sulaiman Al Riyaee, “Skin Cancer Detection: Applying a Deep Learning Based Model Driven Architecture in the Cloud for Classifying Dermal Cell Images,” Informatics in Medicine Unlocked, vol. 18, pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Phillip Ly, Doina Bein, and Abhishek Verma, “New Compact Deep Learning Model for Skin Cancer Recognition,” 2018 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference, New York, NY, USA, pp. 255-261, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Meghana Karri, Chandra Sekhara Rao Annavarapu, and U. Rajendra Acharya, “Skin Lesion Segmentation using Two-Phase Cross-Domain Transfer Learning Framework,” Computer Methods Programs in Biomedicine, vol. 231, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Sanya Sinha, and Nilay Gupta, “A Comparative Analysis of Transfer Learning-Based Techniques for the Classification of Melanocytic Nevi,” Proceedings of Advances and Applications of Artificial Intelligence & Machine Learning, pp. 637–649, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Aditya Khamparia et al., “An Internet of Health Things‐Driven Deep Learning Framework for Detection and Classification of Skin Cancer Using Transfer Learning,” Transactions on Emerging Telecommunications Technologies, vol. 32, no. 7, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Aishwariya Dutta, Kamrul Hasan, and Mohiuddin Ahmad, “Skin Lesion Classification Using Convolutional Neural Network For Melanoma Recognition,” Proceedings of International Joint Conference on Advances in Computational Intelligence, pp. 55-66, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Noel C.F. Codella et al., “Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC),” arXiv, pp. 1-5, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[31] H. C. d. B. BCN_20000 Dataset: (c) Department of Dermatology. [Online]. Available: https://paperswithcode.com/dataset/bcn-20000 [32] Philipp Tschandl, Cliff Rosendahl, and Harald Kittler, “The HAM10000 Dataset, A Large Collection of Multi-Source Dermatoscopic Images of Common Pigmented Skin Lesions,” Scientific Data, vol. 5, no. 1, pp. 1-9, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Andre G.C. Pacheco et al., “PAD-UFES-20: A Skin Lesion Dataset Composed of Patient Data and Clinical Images Collected from Smartphones,” Data in Brief, vol. pp. 1-10, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Azadeh Noori Hoshyar, Adel Al-Jumaily, and Afsaneh Noori Hoshyar, “The Beneficial Techniques in Preprocessing Step of Skin Cancer Detection System Comparing,” Procedia Computer Science, vol. 42, pp. 25-31, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[35] G. Subhashini, and A. Chandrasekar, “Hybrid Deep Learning Technique for Optimal Segmentation and Classification of Multi-Class Skin Cancer,” The Imaging Science Journal, pp. 1-22, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Miguel Ángel González-Moles, Manuel Aguilar-Ruiz, and Pablo Ramos-García, “Challenges in the Early Diagnosis of Oral Cancer, Evidence Gaps and Strategies for Improvement: A Scoping Review of Systematic Reviews,” Cancers, vol. 14, no. 19, pp. 1-30, 2022.
[CrossRef] [Google Scholar] [Publisher Link]