Enhancing Colonoscopy Image Quality with CLAHE in the GASTROLAB Dataset

This research focuses on improving image quality in the context of colonoscopy, a critical procedure for diagnosing gastrointestinal conditions such as colorectal polyps, which can lead to cancer. The study highlights the challenges posed by the large volume of frames generated during colonoscopy procedures, which necessitates the use of automated systems to detect anomalies. Despite the fact that some datasets contain low-quality images, it emphasizes the importance of various datasets in gastrointestinal disease research and machine learning. The primary goal of this work is to improve the image quality of the GASTROLAB dataset, emphasizing the significance of accurate results derived from high-quality data. The study looks into various image enhancement techniques, with a focus on Contrast Limited Adaptive Histogram Equalization (CLAHE), which produces superior results in image quality metrics like Peak Signal to Noise Ratio (PSNR) and), Structural Similarity Index (SSIM), which are 32.26 and 0.912, respectively. The findings demonstrate the utility of PSNR and SSIM as image quality assessment tools, while also emphasizing the importance of clinical validation and expert judgement in medical image evaluation. The study concludes with findings that support CLAHE as a preferred method for improving image quality, particularly when visualizing small polyps during colonoscopy.