Enhanced KNN-Based Model for Early Detection and Classification of Skin Cancer
DOI:
https://doi.org/10.64229/3ehes479Keywords:
Artificial Intelligence, Cancer, Classification, Machine Learning, KNN, SDG, ResNetAbstract
Skin cancer especially melanoma is one of the most aggressive and lethal type of cancer in the world allied with the fact that early detection is a major step towards survival. Nevertheless, it has been difficult to distinguish benign and malignant skin lesions because they are visually similar. The present paper identifies a modified K-Nearest Neighbors (KNN) classification model that is expected to correct skin cancer diagnosis without false negatives, as the classification model makes the determination by means of machine learning on digital pictures of skin lesions. The five principal components include the steps in the model, namely data acquisition, preprocessing, feature extraction, classification, and evaluation, and its priority is to maximize the accuracy of the diagnosis. As shown in the proposed KNN model, feature extraction techniques aka Histogram of Oriented Gradients (HOG) and Scale-Invariant Feature Transform (SIFT) are used to extract the valuable features texture, shape, and edges of the image. It was found that the KNN model is superior to both the traditional and deep learning models with overall accuracy at 92.4%, which is higher than 89.4% of dermatologists and 81.5% of ResNet models. Furthermore, due to the low CPU-intensive requirements of the KNN model, the latter solution is viable in resource-limited settings providing a non-invasive and highly dependable method of screening individuals at risk of early-stage skin cancer. The results indicate that the more robust KNN model would become a benefit to dermatologists in terms of improved diagnostics and eliminated invasive procedures opportunities. Additional studies are required to determine feasibility of adaptation to the real-life setting and clinician use.
References
[1]G. Chugh, S. Kumar, and N. Singh, “Survey on machine learning and deep learning applications in breast cancer diagnosis,” Cognitive Computation, vol. 13, no. 6, pp. 1451-1470, 2021.
[2]Kushwaha, S. (2023). A futuristic perspective on artificial intelligence. In Proceedings of the IEEE OPJU International Technology Conference on Emerging Technologies For Sustainable Development (pp. 1-6). O.P. Jindal University, Raigarh, Chhattisgarh, India.
[3]Ali, L., Rahman, A., Khan, A., Zhou, M., Javeed, A., & Khan, J. A. (2019). An automated diagnostic system for heart disease prediction based on χ² statistical model and optimally configured deep neural network. IEEE Access, 7, 34938-34945.
[4]Kushwaha, S., Chithras, T., Girija, S. P., Prasanth, K. G., Minisha, R. A., Dhanalakshmi, M., Jayanthi, A., Robin, C. R. R., & Rajaram, A. (2024). Efficient liver disease diagnosis using infrared image processing for enhanced detection and monitoring. Journal of Environmental Protection and Ecology, 25(4), 1266-1278.
[5]World Health Organization. Cardiovascular diseases. https://www.who.int/health-topics/cardiovascular-diseases (Accessed April 19, 2025)
[6]Li, H., & Boulanger, P. (2020). A survey of heart anomaly detection using ambulatory electrocardiogram (ECG). Sensors, 20(5), 1461.
[7]Duncker, D.(2021). Smart wearables for cardiac monitoring—real-world use beyond atrial fibrillation. Sensors, 21(7), 2539.
[8]Isakadze, N., & Martin, S. S. (2020). How useful is the smartwatch ECG? Trends in Cardiovascular Medicine, 30(7), 442-448.
[9]Kushwaha, S. (2023). An effective adaptive fuzzy filter for speckle noise reduction. Multimedia Tools and Applications, 2023, 1-16. Springer.
[10]Dhanalakshmi, P., Venkatesh, V., Ranjit, P. S., Hemalatha, N., Divyapriya, S., Sandhiya, R., Kushwaha, S., Marathe, A., & Huluka, M. A. (2022). Application of machine learning in multi-directional model to follow solar energy using photo sensor matrix. International Journal of Photoenergy, 2022, 1-9. Hindawi.
[11]Hemanand, D., Mishra, N., Premalatha, G., Mavaluru, D., Vajpayee, A., Kushwaha, S., & Sahile, K. (2022). Applications of intelligent model to analyze the green finance for environmental development in the context of artificial intelligence. Computational Intelligence and Neuroscience, 2022, 1-8. Hindawi.
[12]Singh, A., Khan, R. A., Kushwaha, S., & Alshenqeeti, T. (2022). Roll of Newtonian and Non-Newtonian motion in analysis of two-phase hepatic blood flow in artery during jaundice. International Journal of Mathematics and Mathematical Sciences, 2022, 1-10. Hindawi.
[13]Singh, A., Kushwaha, S., Alarfaj, M., & Singh, M. (2022). Comprehensive overview of backpropagation algorithm for digital image denoising. Electronics, 11(10), 1590. MDPI.
[14]Kushwaha, S. (2017). An efficient filtering approach for speckle reduction in ultrasound images. Biomedical and Pharmacology Journal, 10(3), 1355-1367.
[15]A, S. B., S, S., S, R. S., Nair, A. R., & Raju, M. (2022). Scalogram based heart disease classification using hybrid CNN-naive Bayes classifier. In 2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET) (pp. 345-348). IEEE.
[16]Kushwaha, S., & Singh, R. K. (2019). Optimization of the proposed hybrid denoising technique to overcome over-filtering issue. Biomedical Engineering/Biomedizinische Technik, 64(5), 601-618.
[17]Bulbul, H. I., Usta, N., & Yildiz, M. (2017). Classification of ECG arrhythmia with machine learning techniques. In 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 546-549). IEEE.
[18]Kushwaha, S., & Singh, R. K. (2018). Robust denoising technique for ultrasound images by splicing of low rank filter and principal component analysis. Biomedical Research, 29(18), 3444-3455.
[19]Sharma, P., & Gupta, D. V. (2018). Disease classification from ECG signal using R-peak analysis with artificial intelligence. International Journal of Signal Processing, Image Processing and Pattern Recognition, 11(3), 29-40.
[20]Ullah, A., Anwar, S. M., Bilal, M., & Mehmood, R. M. (2020). Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation. Remote Sensing, 12(10), 1685.
[21]Kushwaha, S., & Singh, R. K. (2017). An efficient approach for denoising ultrasound images using anisotropic diffusion and teaching learning based optimization. Biomedical and Pharmacology Journal, 10(2), 805-816.
[22]Khan, M. U., Aziz, S., Naqvi, S. Z. H., & Rehman, A. (2020). Classification of coronary artery diseases using electrocardiogram signals. In 2020 International Conference on Emerging Trends in Smart Technologies (ICETST). IEEE.
[23]Kushwaha, S., & Singh, R. K. (2017). Performance comparison of different despeckled filters for ultrasound images. Biomedical and Pharmacology Journal, 10(2), 837-845.
[24]Abidalkareem, A., Ibrahim, A. K., Abd, M., Rehman, O., & Zhuang, H. (2024). Identification of gene expression in different stages of breast cancer with machine learning. Cancers (Basel), 16, 1864.
[25]Alshawwa, I. A., El-Mashharawi, H. Q., Salman, F. M., Al-Qumboz, M. N. A., Abunasser, B. S., & Abu-Naser, S. S. (2024). Advancements in early detection of breast cancer: Innovations and future directions. (Publisher and journal info missing-complete if available.)
[26]Bijari, S., Sayfollahi, S., Mardokh-Rouhani, S., Bijari, S., Moradian, S., Zahiri, Z. (2024). Radiomics and deep features: Robust classification of brain hemorrhages and reproducibility analysis using a 3D autoencoder neural network. Bioengineering, 11, 643.
[27]Bostanci, E., Kocak, E., Unal, M., Guzel, M. S., Acici, K., & Asuroglu, T. (2023). Machine learning analysis of RNA-seq data for diagnostic and prognostic prediction of colon cancer. Sensors, 23, 3080.
[28]Kushwaha, S. (2023). Review on artificial intelligence and human computer interaction. In Proceedings of the IEEE OPJU International Technology Conference on Emerging Technologies For Sustainable Development (pp. 1-6). O.P. Jindal University, Raigarh, Chhattisgarh, India.
[29]Chugh, G., Kumar, S., & Singh, N. (2021). Survey on machine learning and deep learning applications in breast cancer diagnosis. Cognitive Computation, 13, 1451-1470.
[30]Mahboubisarighieh, A., Shahverdi, H., Jafarpoor Nesheli, S., Alipoor Kermani, M., Niknam, M., Torkashvand, M. (2024). Assessing the efficacy of 3D Dual-CycleGAN model for multi-contrast MRI synthesis. Egyptian Journal of Radiology and Nuclear Medicine, 55, 1-12.
[31]Rezaeijo, S. M., Rezaei, M., Poursheikhani, A., Mohammadkhani, S., Goharifar, N., Shayankia, G. (2023). Integrative bioinformatics analysis of miRNA and mRNA expression profiles identified some potential biomarkers for breast cancer. Egyptian Journal of Medical Human Genetics, 24, 62.
[32]Sahu, A., Qazi, S., Raza, K., Singh, A., & Verma, S. (2022). Machine learning-based approach for early diagnosis of breast cancer using biomarkers and gene expression profiles. In Computational Intelligence in Oncology Applications: Diagnosis, Prognosis, and Therapy of Cancers (pp. 285-306). Springer.
[33]Sharma, P., & Gupta, D. V. (2018). Disease classification from ECG signal using R-peak analysis with artificial intelligence. International Journal of Signal Processing, Image Processing and Pattern Recognition, 11(3), 29-40.
[34]Ullah, A., Anwar, S. M., Bilal, M., & Mehmood, R. M. (2020). Classification of arrhythmia by using deep learning with 2-D ECG spectral image representation. Remote Sensing, 12(10), 1685.
[35]Khan, M. U., Aziz, S., Naqvi, S. Z. H., & Rehman, A. (2020). Classification of coronary artery diseases using electrocardiogram signals. In 2020 International Conference on Emerging Trends in Smart Technologies (ICETST). IEEE.
[36]Asadi, O., Yekkalam, A., & Manthouri, M. (2023). MDDC: Melanoma detection using discrete wavelet transform and convolutional neural network. Journal of Ambient Intelligence and Humanized Computing, 14(9), 12959-12966.
[37]Tembhurne, J. V., Hebbar, N., Patil, H. Y., & Diwan, T. (2023). Skin cancer detection using ensemble of machine learning and deep learning techniques. Multimedia Tools and Applications, 16, 1-24.
[38]Li, Y., Li, C., Li, X., Wang, K., Rahaman, M. M., Sun, C., Chen, H., Wu, X., Zhang, H., & Wang, Q. (2022). A comprehensive review of Markov random field and conditional random field approaches in pathology image analysis. Archives of Computational Methods in Engineering, 29(1), 609-639.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Sumit Kushwaha (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
