Building a Model and Evaluating the Performance for Colon Cancer Screening Using Histopathological Images
Journal of Science Ladkrabang · 2025
DOI: 10.55003/scikmitl.2025.261425 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Science Ladkrabang, 2025. Verfasst von Lersak Phothong und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Colon cancer remains a major global health concern. Early detection is critical for improving treatment outcomes. Although conventional diagnostic methods are generally reliable, they can be time-consuming and heavily dependent on the expertise of medical professionals. This study aims to evaluate the effectiveness of machine learning models in classifying colon cancer using 10,000 histopathological images obtained from www.kaggle.com. The data were analyzed following standard data mining procedures using four image classification techniques: Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Neural Network (NN), and Decision Tree (DT). The results showed that the k-NN technique achieved the highest accuracy at 91.86%, along with the highest sensitivity and specificity values at 92.24% and 91.48%, respectively. These findings indicate that the k-NN technique is highly suitable for developing classification models for colon cancer, contributing to the creation of essential tools for early detection and supporting more effective treatment planning.
Zitieren
APA
Phothong, L., Phanprasat, C., Thongyu, P., & Sukprasert, A. (2025). Building a Model and Evaluating the Performance for Colon Cancer Screening Using Histopathological Images. Journal of Science Ladkrabang. https://doi.org/10.55003/scikmitl.2025.261425
Vancouver
Phothong L, Phanprasat C, Thongyu P, Sukprasert A. Building a Model and Evaluating the Performance for Colon Cancer Screening Using Histopathological Images. Journal of Science Ladkrabang. 2025. doi:10.55003/scikmitl.2025.261425
BibTeX
@article{Phothong2025,
author = {Phothong, Lersak and Phanprasat, Charanya and Thongyu, Patiparn and Sukprasert, Anupong},
title = {Building a Model and Evaluating the Performance for Colon Cancer Screening Using Histopathological Images},
journal = {Journal of Science Ladkrabang},
year = {2025},
doi = {10.55003/scikmitl.2025.261425}
}
EUVIMED