Performance Comparison of CNN and ResNet50 for Skin Cancer Classification Using U-Net Segmented Images


Keywords: Skin Cancer Detection, Convolutional Neural Network (CNN), ResNet50, U-Net Segmentation, Deep Learning

Abstract

Skin cancer is a significant global health issue, with melanoma, basal cell carcinoma, and actinic keratosis being the most common types. Early and accurate detection is critical to improve survival rates and treatment outcomes. This study evaluates the performance of Convolutional Neural Networks (CNN) and ResNet50 in classifying segmented images of skin lesions. The dataset, sourced from Kaggle, was pre-processed using U-Net for lesion segmentation to enhance the quality of input data. Both models were trained and evaluated using accuracy, precision, recall, and F1-score metrics. The CNN model demonstrated a balanced performance across classes, with a weighted F1-score of 47%, but suffered from overfitting, as indicated by the divergence between training and validation losses. ResNet50 achieved better recall for basal cell carcinoma (100%) but failed to classify actinic keratosis and melanoma, resulting in a macro F1-score of 23%. The findings reveal that U-Net segmentation improved classification focus but was insufficient to address dataset imbalance and model-specific limitations. This study highlights the challenges of skin cancer classification using deep learning and underscores the importance of addressing data imbalance and overfitting. Future research should explore advanced techniques, such as ensemble methods, data augmentation, and transfer learning, to improve the generalization and clinical applicability of these models. The proposed framework serves as a foundation for further investigation into automated skin cancer detection systems.

Downloads

Download data is not yet available.

References

S. Prasher, “Resnet 50 Based Classification Model for Skin Cancer Detection Using Dermatoscopic Images,” 2023 3rd Asian Conference on Innovation in Technology, ASIANCON 2023. 2023, doi: 10.1109/ASIANCON58793.2023.10270158.

Y. Filali, “Analysis and Classification of Skin Cancer Based on Deep Learning Approach,” 2022 International Conference on Intelligent Systems and Computer Vision, ISCV 2022. 2022, doi: 10.1109/ISCV54655.2022.9806087.

A. Vatsa, “Comparing the Performance of Classification Algorithms for Melanoma Skin Cancer,” 13th IEEE Integrated STEM Education Conference, ISEC 2023. pp. 375–380, 2023, doi: 10.1109/ISEC57711.2023.10402205.

T. S. Kumar, “Classification of Skin Cancer Images using Lightweight Convolutional Neural Network,” 2023 4th International Conference for Emerging Technology, INCET 2023. 2023, doi: 10.1109/INCET57972.2023.10170637.

S. G. Ahmed, “Skin Cancer Classification Utilizing a Hybrid Model of Machine Learning Models Trained on Dermoscopic Images,” 2023 3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023. 2023, doi: 10.1109/eSmarTA59349.2023.10293619.

N. V. Y. Lankadasu, “Skin Cancer Classification Using a Convolutional Neural Network: An Exploration into Deep Learning,” 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024. pp. 1047–1052, 2024, doi: 10.1109/ICETSIS61505.2024.10459368.

S. A. Alshawi, “Skin Cancer Image Detection and Classification by CNN based Ensemble Learning,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 5, pp. 710–717, 2023, doi: 10.14569/IJACSA.2023.0140575.

I. Lihacova, “Multi-Class CNN for Classification of Multispectral and Autofluorescence Skin Lesion Clinical Images,” J. Clin. Med., vol. 11, no. 10, 2022, doi: 10.3390/jcm11102833.

A. Panthakkan, “Concatenated Xception-ResNet50 — A novel hybrid approach for accurate skin cancer prediction,” Comput. Biol. Med., vol. 150, 2022, doi: 10.1016/j.compbiomed.2022.106170.

E. Firasari, “Performance Evaluation of ResNet50 and MobileNetV2 in Skin Cancer Image Classification with Various Optimizers,” Proceeding - 2024 International Conference on Information Technology Research and Innovation, ICITRI 2024. pp. 376–380, 2024, doi: 10.1109/ICITRI62858.2024.10698943.

S. D. Thepade, “Enhancing Melanoma Skin Cancer Detection Through Feature Fusion of Pre-Trained Deep Convolutional Neural Network ResNet50 and Thepade Sorted Block Truncation Coding,” SN Comput. Sci., vol. 5, no. 4, 2024, doi: 10.1007/s42979-024-02821-5.

M. N. Hasan, “Fetal Brain Planes Classification Using Deep Ensemble Transfer Learning from U-Net Segmented Fetal Neurosonography Images,” Int. J. Image, Graph. Signal Process., vol. 16, no. 4, pp. 74–86, 2024, doi: 10.5815/ijigsp.2024.04.06.

T. T. Fousiya, “Diabetic Retinopathy Classification Based on Segmented Retinal Vasculature of Fundus Images Using Attention U-NET,” INDICON 2022 - 2022 IEEE 19th India Council International Conference. 2022, doi: 10.1109/INDICON56171.2022.10039734.

M. A. Arshed, “Multi-Class Skin Cancer Classification Using Vision Transformer Networks and Convolutional Neural Network-Based Pre-Trained Models,” Inf., vol. 14, no. 7, 2023, doi: 10.3390/info14070415.

S. Deshmukh, “Skin Cancer Classification Using CNN,” International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023. 2023, doi: 10.1109/ICAISC58445.2023.10199440.

R. Bharti, “Comparative Analysis of Potato Leaf Disease Classification Using CNN and ResNet50,” 2024 International Conference on Data Science and Its Applications, ICoDSA 2024. pp. 87–91, 2024, doi: 10.1109/ICoDSA62899.2024.10651649.

G. B. Alghanimi, “CNN and ResNet50 Model Design for Improved Ultrasound Thyroid Nodules Detection,” 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024. pp. 1000–1004, 2024, doi: 10.1109/ICETSIS61505.2024.10459588.

M. Singla, “ResNet50 Utilization for Bag Classification: A CNN Model Visualization Approach in Deep Learning,” 2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems, ICITEICS 2024. 2024, doi: 10.1109/ICITEICS61368.2024.10624847.

A. P. Wibowo, M. Taruk, T. E. Tarigan, and ..., “Improving Mental Health Diagnostics through Advanced Algorithmic Models: A Case Study of Bipolar and Depressive Disorders,” Indones. J. …, 2024, doi: 10.56705/ijodas.v5i1.122.

R. Setiawan and H. Oumarou, “Classification of Rice Grain Varieties Using Ensemble Learning and Image Analysis Techniques,” Indones. J. Data …, 2024, doi: 10.56705/ijodas.v5i1.129.

B. S. W. Poetro, E. Maria, H. Zein, and ..., “Advancements in Agricultural Automation: SVM Classifier with Hu Moments for Vegetable Identification,” Indones. J. …, 2024, doi: 10.56705/ijodas.v5i1.123.

Published
2024-12-31
How to Cite
Aris Wahyu Murdiyanto, Zulfikar, D. H., Waluyo Poetro, B. S., & Siregar, A. C. (2024). Performance Comparison of CNN and ResNet50 for Skin Cancer Classification Using U-Net Segmented Images. Indonesian Journal of Data and Science, 5(3), 198-205. https://doi.org/10.56705/ijodas.v5i3.200