Deep neural network-based pathological myopia detection system

The invention provides a pathological myopia detection system based on a deep neural network, which comprises a computer memory, a computer processor and an executable program, and is characterized in that the executable program is used for receiving an eye fundus image, transmitting the eye fundus image into a trained pathological myopia detection network model and finally outputting a result; the pathological myopia detection network model comprises a focus detector, a lesion degree classifier and a pathological myopia discriminator; the lesion degree classifier is used for judging the lesion level of the fundus image; if the lesion level of the image is abnormal, the fundus image is sent to a focus detector; the focus detector is used for detecting the type and position of a focus in the fundus image; the pathological myopia discriminator discriminates whether the fundus image suffers from pathological myopia according to output results of the lesion degree classifier and the focus detector. The system can