Deep learning algorithms were able to discover many complex features in large data sets, as manually extracting features may lower the accuracy of the information in addition to wasting time, especially in huge databases, so researchers have tended to use convolutional networks to detect and classify objects in images instead of methods Former traditional. Detection of DNA damage is one of the very important topics of our time because it is responsible for diagnosing many diseases at an early date, as well as knowing the stages of disease development by determining the degree of damage to the DNA. This study is suggest a hybrid Mamdani fuzzy logic (Type-2) for detecting edges of each object of the image in (FIS-CNN) model based on preprocessing image enhancement using adaptive histogram equalization and segmenting processing in morphology operations for each object in images, then patterns of comets are detected in CNN network and classify into five scores grade automatically. The experimental results conducted on the database have achieved a high performance precision 94.34% accuracy, the propose approach compared to similar modern methods. In addition, the proposed approach is capable of detecting comets that are difficult to see with the human eye.