İkili Görüntü Sınıflandırma için Evrişimsel Sinir Ağı Mimarilerinin Karşılaştırmalı Analizi: Cilt Kanseri Tespitinde Bir Vaka Çalışması

Yıl 2024, , 2008 - 2022, 15.12.2024

Şerife Gül Korkut , Hatice Kocabaş , Rifat Kurban

https://doi.org/10.31466/kfbd.1515451

Öz

Bu çalışmada, ikili görüntü sınıflandırması için Evrişimsel Sinir Ağı (CNN) mimarilerinin kapsamlı bir karşılaştırmalı analizi sunulmuş ve transfer öğreniminin faydalarına vurgu yapılmıştır. MobileNetV3, VGG19, ResNet50 ve EfficientNetB0 gibi önde gelen CNN modellerinin ikili görüntülerden cilt kanseri sınıflandırmadaki performans ve doğruluğu değerlendirilmiştir. Önceden eğitilmiş bir yaklaşım kullanılarak, transfer öğreniminin bu mimarilerin etkinliği üzerindeki etkisi araştırılmış ve ikili görüntü sınıflandırması bağlamında güçlü ve zayıf yönleri belirlenmiştir. Bu makale, optimal CNN mimarisinin seçimi ve transfer öğreniminden yararlanarak ikili görüntü sınıflandırma uygulamalarında, özellikle tıbbi görüntü analiziyle ilgili olanlarda, üstün performans elde etme konusunda değerli içgörüler sağlamayı amaçlamaktadır.

Anahtar Kelimeler

Evrişimsel Sinir Ağları (CNN, Transfer Öğrenimi, İkili Görüntü Sınıflandırma, CNN Mimari Karşılaştırması, Cilt Kanseri Tespiti

A Comparative Analysis of Convolutional Neural Network Architectures for Binary Image Classification: A Case Study in Skin Cancer Detection

Öz

In this study, a comprehensive comparative analysis of Convolutional Neural Network (CNN) architectures for binary image classification is presented with a particular focus on the benefits of transfer learning. The performance and accuracy of prominent CNN models, including MobileNetV3, VGG19, ResNet50, and EfficientNetB0, in classifying skin cancer from binary images are evaluated. Using a pre-trained approach, the impact of transfer learning on the effectiveness of these architectures and identify their strengths and weaknesses within the context of binary image classification are investigated. This paper aims to provide valuable insights for selecting the optimal CNN architecture and leveraging transfer learning to achieve superior performance in binary image classification applications, particularly those related to medical image analysis.

Anahtar Kelimeler

Convolutional Neural Networks (CNNs), Transfer Learning, Binary Image Classification, CNN Architecture Comparison, Skin Cancer Detection

Kaynakça

• Al-Mekhlafi, Z.G., Senan, E.M., Rassem, T.H., Mohammed, B.A., Makbol, N.M. et al. (2022). Deep learning and machine learning for early detection of stroke and haemorrhage. Computers, Materials & Continua, 72(1), 775-796. https://doi.org/10.32604/cmc.2022.024492
• Al-saedi, D. K. A., & Savaş, S. (2022). Classification of Skin Cancer with Deep Transfer Learning Method. IDAP-2022 : International Artificial Intelligence and Data Processing Symposium, 202-210. https://doi.org/10.53070/bbd.1172782
• Bai, X., Shang, X., Zhong, S., Hu, P., & Chang, C. (2019, May). Iterative constrained energy minimization convolutional neural network for hyperspectral image classification. Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXV. https://doi.org/10.1117/12.2519046
• Bu, Y., Jiang, X., Tian, J., Hu, X., Han, L., Huang, D., … & Luo, H. (2022). Rapid argnondestructive detecting of sorghum varieties based on hyperspectral imaging and convolutional neural network. Journal of the Science of Food and Agriculture, 103(8), 3970-3983. https://doi.org/10.1002/jsfa.12344
• Craythorne, E., & Al-Niami, F. (2017). Skin tumours: Skin cancer. Medicine, 45(7), 431-434. https://doi.org/10.1016/j.mpmed.2017.04.003
• Deng, T. and Wu, Y. (2022). Simultaneous vehicle and lane detection via mobilenetv3 in car following scene. Plos One, 17(3), e0264551. https://doi.org/10.1371/journal.pone.0264551
• Dildar, M., Akram, S., Irfan, M., Khan, H. U., Ramzan, M., Mahmood, A. R., … & Mahnashi, M. H. (2021). Skin cancer detection: a review using deep learning techniques. International Journal of Environmental Research and Public Health, 18(10), 5479. https://doi.org/10.3390/ijerph18105479
• Du, X., Si, L., Li, P., & Yun, Z. (2023). A method for detecting the quality of cotton seeds based on an improved resnet50 model. Plos One, 18(2), e0273057. https://doi.org/10.1371/journal.pone.0273057
• Garg, S., Mohanty, D. P., Thota, S. P., & Moharana, S. (2021). A simple approach to image tilt correction with self-attention mobilenet for smartphones. In Proceedings of the British Machine Vision Conference 2021 (pp. 1-12). https://doi.org/10.48550/arxiv.2111.00398
• Geng, Y., Huang, J., Yang, J., & Zhang, S. (2022). Spectrum sensing for cognitive radio based on feature extraction and deep learning. Journal of Physics Conference Series, 2261(1), 012016. https://doi.org/10.1088/1742-6596/2261/1/012016
• Guo-zhan, W., Feng, A., Gu, C., & Liu, X. (2023). Yolo-dfd: a lightweight method for dog feces detection based on improved yolov4. Journal of Sensors, 2023, 1-11. https://doi.org/10.1155/2023/5602595
• Hasan, M.K., & Aleef, T.A. (2019). Automatic Mass Detection in Breast Using Deep Convolutional Neural Network and SVM Classifier. https://doi.org/10.48550/arxiv.1907.04424
• Hu, J., Qi, Y., & Wang, J. (2022). Skin disease classification using mobilenet-rsesk network. Journal of Physics: Conference Series, 2405(1), 012017. https://doi.org/10.1088/1742-6596/2405/1/012017
• Huang, Y., Vadloori, S., Chu, H., Kang, E., Wu, W., & Fukushima, Y. (2020). Deep learning models for automated diagnosis of retinopathy of prematurity in preterm infants. Electronics, 9(9), 1444. https://doi.org/10.3390/electronics9091444
• Islam, M. S., & Panta, S. (2024). Skin cancer images classification using transfer learning techniques. arXiv.
• Jia, X., & Li, D. (2022). TFCN: Temporal-Frequential Convolutional Network for Single-Channel Speech Enhancement. https://doi.org/10.48550/arxiv.2201.00480
• Kamiri, J., Wambugu, G. M., & Oirere, A. M. (2022). A comparative study of deep learning and transfer learning in detection of diabetic retinopathy. International Journal of Computer Applications Technology and Research, 11(07), 247-254. https://doi.org/10.7753/ijcatr1107.1001
• Kashani, H. B., Jodeiri, A., Goodarzi, M. M., & Rezaei, I. S. (2019). Speech enhancement via deep spectrum image translation network. In Proceedings of the 2019 26th National and 4th International Iranian Conference on Biomedical Engineering (ICBME) (pp. 1-7). IEEE. https://doi.org/10.1109/ICBME49163.2019.9030421
• Laschowski, B., McNally, W., Wong, A., & McPhee, J. (2021). Computer vision and deep learning for environment-adaptive control of robotic lower-limb exoskeletons. In Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 4631-4635). IEEE. https://doi.org/10.1109/EMBC46164.2021.9630064
• Li, Y., Zheng, H., Huang, X., Chang, J., Hou, D., & Lu, H. (2022). Research on lung nodule recognition algorithm based on deep feature fusion and mkl-svm-ipso. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-22442-3
• Liu, Y., Tang, K., Cai, W., Chen, A., Zhou, G., Li, L., … & Liu, R. (2022). MPC-STANet: Alzheimer’s disease recognition method based on multiple phantom convolution and spatial transformation attention mechanism. Frontiers in Aging Neuroscience, 14. https://doi.org/10.3389/fnagi.2022.918462
• Mvoulana, A., Kachouri, R., & Akil, M. (2021). Fine-tuning convolutional neural networks: A comprehensive guide and benchmark analysis for glaucoma screening. In Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 4677-4684). IEEE. https://doi.org/10.1109/icpr48806.2021.9412199
• Prima, B. and Bouhorma, M. (2020). Using transfer learning for malware classification. The International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences, XLIV-4/W3-2020, 343-349. https://doi.org/10.5194/isprs-archives-xliv-4-w3-2020-343-2020
• Rashid, J., Ishfaq, M., Ali, G., Saeed, M. R., Hussain, M., Alkhalifah, T., Alturise, F., & Samand, N. (2022). Skin cancer disease detection using transfer learning technique. Applied Sciences, 12(11), 5714. https://doi.org/10.3390/app12115714
• Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., … & Li, F. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211-252. https://doi.org/10.1007/s11263-015-0816-y
• Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. (2018). Mobilenetv2: inverted residuals and linear bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/cvpr.2018.00474
• Singh, B. and Sharma, D. K. (2021). Predicting image credibility in fake news over social media using multi-modal approach. Neural Computing and Applications, 34(24), 21503-21517. https://doi.org/10.1007/s00521-021-06086-4
• Sobczak, S., & Kapela, R. (2022). Hybrid restricted Boltzmann machine–convolutional neural network model for image recognition. IEEE Access, 10, 24985-24994. https://doi.org/10.1109/access.2022.3155873
• Suciu, O., Coull, S. E., & Johns, J. (2019). Exploring adversarial examples in malware detection. 2019 IEEE Security and Privacy Workshops (SPW), 8-14. https://doi.org/10.1109/spw.2019.00015
• Tan, M. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. International Conference on Machine Learning (ICML). https://doi.org/10.48550/arxiv.1905.11946
• Tinnathi, S., & Sudhavani, G. (2022). Copy-move forgery detection using superpixel clustering algorithm and enhanced GWO-based AlexNet model. Cybernetics and Information Technologies, 22(4), 91-110. https://doi.org/10.2478/cait-2022-0041
• Tufail, A., Ma, Y., Kaabar, M., Rehman, A., Khan, R., & Cheikhrouhou, O. (2021). Classification of initial stages of Alzheimer’s disease through PET neuroimaging modality and deep learning: Quantifying the impact of image filtering approaches. Mathematics, 9(23), 3101. https://doi.org/10.3390/math9233101
• Ullah, I., & Mahmoud, Q. (2021). Design and development of a deep learning-based model for anomaly detection in IoT networks. IEEE Access, 9, 103906-103926. https://doi.org/10.1109/ACCESS.2021.3094024
• Wang, Y., Chun, X., Zhu, B., Wang, M., Wang, T., Ni, P., …, & Hu, J. (2022). A new non-invasive tagging method for leopard coral grouper (Plectropomus leopardus) using deep convolutional neural networks with PDE-based image decomposition. Frontiers in Marine Science, 9, 1093623. https://doi.org/10.3389/fmars.2022.1093623
• Xu, Y., Zhao, B., Zhai, Y., Chen, Q., & Zhou, Y. (2021). Maize diseases identification method based on multi-scale convolutional global pooling neural network. IEEE Access, 9, 27959–27970. https://doi.org/10.1109/access.2021.3058267