Cervical image lesion area segmentation device and method based on classification prior

The invention discloses a cervical image lesion area segmentation device and method based on classification prior, and the device comprises an image collection device which is used for collecting 3%-5% of the cervical image processed by the acetic acid solution. The processor comprises a cervix image preprocessing module and a processing module, and the processing module comprises a segmentation network model composed of a U-shaped network based on residual error connection, an image level classifier and a pixel level classifier and is used for outputting and predicting the position of a lesion area on the cervix image; The memory is used for storing parameters of the segmented network model in the processor; and the display device is used for displaying the predicted lesion area positionoutput by the processor. By means of the method and device, high-accuracy biopsy focus position candidate areas can be provided for doctors, and the biopsy positive detection rate is increased. 本发明公开了种基于分类先验的宫颈图像病变区域分割装置和方法，其