Patent attributes
The present invention relates to an automatic cervical cancer diagnosis system for performing machine learning by classifying cervical data required for automatic diagnosis of cervical cancer according to accurate criteria and automatically diagnosing cervical cancer based on the machine learning, the automatic cervical cancer diagnosis system including: a learning data generator configured to classify unclassified photographed image data for a cervix transmitted from an external device or a storage according a combination of multi-level classification criteria to generate learning data for each new classification criterion in a learning mode; a photographed image pre-processer configured to pre-process photographed cervix images; a cervical cancer diagnoser including a machine learning model for cervical cancer that learns a characteristic of the learning data generated for each classification criterion in the learning mode, wherein the machine learning model generates diagnosis information about whether cervical cancer has occurred with respect to the pre-processed photographed cervix image; a screen display controller configured to display and output a user interface screen configured to display the diagnosis information and inputting evaluation information according to a reading specialist; a retraining data generator configured to extract information required for retraining from the evaluation information input through the user interface screen and request retraining the machine learning model; and a diagnosis and evaluation information storage configured to store the diagnosis information about whether cervical cancer has occurred and the evaluation information input through the user interface screen.
