Iris diagonis is an important diagnostic method in evaluating the condition of our internal organ by looking at the image of iris. Evaluating the iris is done by detecting the presence of some broken tissues in iris. However, due to its qualitative, subjective and experience-based nature, conventional iris dianosis has a verry limited application in clinical medicine. Moreover, conventional iris diagnosis is always concerned with the indentification of syndromes father than with the conection between abnormal iris tissue appearances and diseases. in this paper, we present a novel computerized iris inspection method aiming to addres these problems for diagnosis of prancreas organ. First, quantitative fatures, textural measures are extracted from iris images by using popular digital image procesing techniques. Then, Neighborood based Modified Backpropagation using Adaptive Learning Parameters (ANMBP) method is employed to model the relationship between quantitative features and severity of pancreas organ symptoms. The effectivenees of the method is tested on 35 patients affected by Diabetes Mellitus as weel as other 30 healthy volunteers, and the diagnostic results predicted by the previosly trained ANMBP classfiers are compared with the insulin normality test. The achived recognition rate using ANMBP in detecting the presence of broken tisues raised from 87% for N16-12-6-2 up to 90% for N16-18-9-2 and N16-24-12-2, and comparsion using insulin normality test which given result totally correct uo to 100% from 5 patients. Keywords-Computerized iris diagnosis; GLCM; ANMBP; neighborhood