Work

A Cnn-based Framework for Lung Carcinoma Classification With Z-score Color Normalization

Year: 2026

Type: article

Abstract: Accurate and automated lung carcinoma diagnosis is essential because of the high mortality rate worldwide.The conventional diagnosis process is prone to errors, particularly with the growing number of cases.In this paper, a CNN-based system with Z-score color normalization for the classification of histopathological images into Lung Adenocarcinoma, Lung Squamous Cell Carcinoma, and Non-Malignant regions is proposed.A total of 11,580 image patches of size 512 × 512 pixels were employed.Z-score normalization minimized the effect of staining and intensity differences.The system attained an accuracy of 96.02% with a batch size of 64 for 60 epochs.

Source: Science and Culture

DOI: 10.36094/sc.v92.2026.a_cnn_based_framework_for_lung_carcinoma.sinha.293

Authors: SUBRATA SINHA, ANKUR MUKHERJEE, SUVOMOY DATTA, SAURAV MALI

Language: English

Topic: AI in cancer detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: diamond

Funder: Indian Council of Medical Research

Award: G4345081054