One metric used to diagnose TAOD is the 10 mm increase in the basion-dens interval (BDI), which refers to the distance between the basion and the top of the C1 cervical bone by 10 mm 9. Images of the cervical spine are taken either through MRI, CT, or X-rays, then studied for particular dislocations of specific cervical and cranial areas. There are several guidelines used to diagnose TAOD through radiological methods 7, 8. To appropriately diagnose TAOD before complications from delayed treatment occur, radiological methods using MRI, CT, and X-rays are used to screen patients suspected of TAOD 1, 6. However, there lies some difficulty in consistently diagnosing TAOD in patients without neurological deficits due to the nature of certain symptoms, which can be as vague as severe neck pain, or injury to other areas of the body masking pain in the cervical area, to being completely asymptomatic 2. Patients who experience TAOD often present debilitating symptoms such as unconsciousness, respiratory arrest, and in severe cases, sensory, motor, and neurological deficits 2. In cases of patients that survive the injury, it is vital that the dislocation is diagnosed and treated rapidly to improve the success rate of stabilization 4, 5. Due to the high-energy nature of the trauma often associated with the injury such as motor vehicle accidents, most patients who experience atlanto-occipital dislocation have a high likelihood of mortality 3. Traumatic atlanto-occipital dislocation (TAOD) is a traumatic injury stemming from damage to the spinal area resulting in dislocation of the upper cervical spine and the skull base 1, 2. Results showed that all 4 tested U-Net models were capable of segmenting bones used in measuring TAOD metrics with high accuracy. The accuracy of U-Net models ranged from 99.07 to 99.12%, and dice coefficient values ranged from 88.55 to 89.41%. Additionally, we tested U-Net derivatives, recurrent residual U-Net, attention U-Net, and attention recurrent residual U-Net to observe any notable differences in segmentation behavior. For this study, we trained a U-Net model on 513 sagittal X-ray images with segmentations of both cervical and cranial bones for an automated solution to segmenting important features for diagnosing TAOD. Additionally, there has yet to be a study that includes cranial bone segmentations necessary for determining TAOD diagnosing metrics, which are usually defined by measuring the distance between certain cervical (C1 ~ C7) and cranial (hard palate, basion, opisthion) bones. Previous studies utilizing automated segmentation methods have been limited to segmenting parts of the cervical spine (C3 ~ C7), due to difficulties in defining the boundaries of C1 and C2 bones. Segmentation of the cervical spine in tandem with three cranial bones, hard palate, basion, and opisthion using X-ray images is crucial for measuring metrics used to diagnose traumatic atlanto-occipital dislocation (TAOD).