Prognosis of Eye Cancer and Its Stages Using Image Preprocessing and Machine Learning

• Published in: 2025 International Conference on Knowledge Engineering and Communication Systems (ICKECS) pp. 1 - 6
• Main Authors: Keerthishree, B T, Shivani, B L, Amrutha, H N, Uthsavi, M B, Spoorthi, K R, Chaithra, I V
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.04.2025
• Subjects: Accuracy; Cancer; Convolutional Neural Networks; Data models; Deep learning; Eye Cancer; Feature extraction; Histopathological Images; Image preprocessing; Manuals; Medical diagnostic imaging; Medical services; Prediction; Prognostics and health management
• DOI: 10.1109/ICKECS65700.2025.11035915

Eye cancer remains a significant health challenge due to its often late diagnosis and diverse clinical presentation. Early detection is crucial for improving treatment outcomes and preventing vision loss. However, the manual interpretation of histopathological images is time-consuming and subject to interobserver variability, leading to potential inconsistencies in diagnosis. In recent years, advancements in digital pathology and image preprocessing techniques have paved the way for more efficient and automated cancer detection. This study aims to enhance the predictive accuracy of eye cancer by integrating advanced image preprocessing techniques. A comprehensive dataset of digital histopathological images is utilized, undergoing a series of preprocessing steps to improve data quality and consistency. These steps include RGB-to-grayscale conversion, thresholding, image sharpening, segmentation, noise reduction, contrast stretching, histogram modification, and feature extraction. These techniques help refine image clarity, enhance critical features, and reduce artifacts, ensuring optimal input for machine learning models. The main goal of this study is to use histopathological image processing to create an accurate and effective model for the early detection of eye cancer. To avoid serious health issues including eye impairment and metastases, early detection is crucial. This initiative is a big step toward bettering the prognosis of eye cancer, which could save lives and improve the standard of treatment for those who are impacted.