This study addresses the challenge of detecting and classifying diabetic retinopathy (DR) in retinal images, a leading cause of vision loss. The effectiveness of automated diagnosis systems is heavily dependent on segmentation techniques, which must account for variations in retinal and image parameters such as intensity levels, noise, and the presence of blood vessels and lesions. The research employs a fuzzy entropy multi-dimensional thresholding approach to segment fundus images, generating a comprehensive dataset of 42,000 images that cover a wide range of DR scenarios and severity levels. Feasibility and consistency analyses are conducted using a Monte Carlo statistical method to evaluate the accuracy and reliability of the automated diagnosis system. The study identifies specific conditions that ensure accurate DR detection, including minimum differences in intensity levels between background, blood vessels, and lesions for different severity levels of DR. These conditions are validated through comparisons with real retinal images, confirming their reliability as indicators of successful DR detection. The findings contribute to the advancement and practical applicability of automated diagnosis systems, providing healthcare professionals with a valuable tool for efficient and accurate detection and assessment of DR.This study addresses the challenge of detecting and classifying diabetic retinopathy (DR) in retinal images, a leading cause of vision loss. The effectiveness of automated diagnosis systems is heavily dependent on segmentation techniques, which must account for variations in retinal and image parameters such as intensity levels, noise, and the presence of blood vessels and lesions. The research employs a fuzzy entropy multi-dimensional thresholding approach to segment fundus images, generating a comprehensive dataset of 42,000 images that cover a wide range of DR scenarios and severity levels. Feasibility and consistency analyses are conducted using a Monte Carlo statistical method to evaluate the accuracy and reliability of the automated diagnosis system. The study identifies specific conditions that ensure accurate DR detection, including minimum differences in intensity levels between background, blood vessels, and lesions for different severity levels of DR. These conditions are validated through comparisons with real retinal images, confirming their reliability as indicators of successful DR detection. The findings contribute to the advancement and practical applicability of automated diagnosis systems, providing healthcare professionals with a valuable tool for efficient and accurate detection and assessment of DR.