Implementation of Contrast Limited Adaptive Histogram Equalisation in CNN-Based Pneumonia Detection Using Chest X-ray Images: A Systematic Literature Review

Abstract

Pneumonia remains a major global health burden, and chest X-ray (CXR) interpretation is constrained by image quality and observer variability. Contrast Limited Adaptive Histogram Equalisation (CLAHE) is widely used to enhance local contrast before convolutional neural network (CNN) classification, yet its contribution has not been synthesised systematically. This study aims to review how CLAHE is implemented in CNN-based pneumonia detection, which architectures accompany it, how it relates to diagnostic performance, and which methodological gaps remain. A systematic literature review following the PRISMA 2020 guidelines was conducted on the Scopus database for 2021–2026; of 82 records identified, 21 journal articles were included and analysed through thematic synthesis. Four themes emerged: CLAHE implementation strategies, CNN architectures and learning strategies, performance of CLAHE-based pipelines, and methodological robustness. CLAHE was rarely applied alone; it was combined with normalisation, denoising, and augmentation and was increasingly optimised or modified. Transfer learning models dominated, and the highest reported accuracies ranged from 92% to 99.78%. However, heterogeneous datasets, CLAHE parameters, validation protocols, and metrics, together with scarce ablation and external validation, prevent attributing these gains to CLAHE alone. Standardised preprocessing, ablation-based reporting, multicentre validation, and explainable AI are needed to make CLAHE-based CNN systems clinically reliable.