System and method for classifying type of a fracture on musculoskeletal x-ray image

A system (100) for classifying a type of fracture on musculoskeletal X-ray image (101), characterized in that, the system (100) comprises:

• a memory (203);
• a processor (201) coupled with the memory (203), wherein the processor (201) is configured to execute programmed instructions stored in the memory (203);
• a data collection module (205), wherein data (210) collected by the data collection module (205) corresponds to an input X-ray image (101);
• a fracture-type classification module (206) for classifying the type of fracture based on the collected data (210), using a classification model (207) and a segmentation model (208) based on an artificial intelligence, wherein the classification model (207) and the segmentation model (208) carried out by the processor (201);
• wherein the classification model (207) is configured to perform steps of:
• analysing the input X-ray image (101) to recognize a plurality of tags, wherein the plurality of tags including the types of fracture;
• calculating a classification score, corresponds to the recognition of the plurality of tags;
• and
• wherein the segmentation model (208) is configured to perform step of:
• dividing the input X-ray image (101) into a plurality of pixels to determine a probability of fracture for each pixel of the plurality of pixels;
• calculating a segmentation score for each pixel of the plurality of pixels, corresponds to a level of the probability of fracture;
• wherein the fracture-type classification module (206) is configured for:
• generating a fracture-type score (401) based on the classification score and the segmentation score;
• and
• comparing the fracture-type score (401) with a threshold value for each fracture part separately to classify the type of the fracture.