ENHANCING DEEP LEARNING BASED LUNG CANCER HISTOPATHOLOGICAL IMAGE CLASSIFICATION THROUGH GRAY-WORLD COLOR NORMALIZATION

Read full text Summarise with VIRAT
Authors: SUBRATA SINHA, Suvomoy Datta, ANKUR MUKHERJEE, SAURAV MALI
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study examines the effectiveness of Gray-World color normalization in reducing staininginduced color variability in histopathological images to enhance deep learning performance.A VGG16-based transfer learning model was trained using both original and normalized datasets consisting of 11,580 image patches across LUAD, LSCC, and Non-Malignant classes.The normalized dataset resulted in notable improvements in precision, recall, and F1-score metrics.ROC curve analysis further confirmed higher AUC values compared to the unnormalized data.Overall, Gray-World normalization improved the robustness of CNN-based lung cancer classification models.

Fields of Study & Subjects

AI in cancer detection Digital Imaging for Blood Diseases Radiomics and Machine Learning in Medical Imaging

Publication details

Journal / source
Science and Culture
Volume
92
Publication date
17 March 2026
Language
EN