The MTDDH dataset for quality evaluation of pelvic X-ray and diagnosis of developmental dysplasia of the hip

Developmental Dysplasia of the Hip (DDH) ranks among the foremost hip disorders encountered in pediatric orthopedics. Automated diagnostic tools, powered by artificial intelligence techniques, can assist clinicians in diagnosing DDH. We have constructed a dataset called MTDDH, which consists of two sub-datasets. Dataset1 consists of 1,250 pelvic X-ray images, annotated with four distinct regions for the quality evaluation of pelvic X-ray, in conjunction with eight key points for DDH diagnostic support. Dataset2 comprises 906 pelvic X-ray images, annotated exclusively with the 8 key points pertinent to DDH diagnostic assistance. MTDDH is the first dataset designed for the quality evaluation of pelvic X-rays that also provides the most extensive set of 8 key points (typically 6 key points) for aiding in DDH diagnosis, thereby meeting the need for more precise diagnostic accuracy.