The developed system is capable of segmenting (precisely marking) hip fractures, indicating the type of fracture, from X-rays using artificial intelligence. The software has two modes of operation. In the first, the radiographic image is a file on the hard disk, which is read, interpreted, and the system generates a mask, that is, an image of the same size as the original image where the fracture and its type are indicated. In the second mode of operation, the system reads the user’s computer screen and overlays the contour of the detected fracture on it, indicating its type and a number between zero and one indicating the method’s certainty in the fracture segmentation. Extensions of the software to integrate it into the hospital PACS system are foreseeable but not implemented. The types of fractures the system can detect are i) non-displaced femoral neck fracture ii) displaced femoral neck fracture iii) non-displaced pertrochanteric fracture iv) displaced pertrochanteric fracture and v) subtrochanteric fractures.

Expected Results or Competitive Advantages: System capable of i) segmenting the fracture and ii) providing a better classification of the fracture than current systems