HIPPO is a support tool for doctors to aid triaging adult patients with hip pain towards the appropriate follow-up treatment pathway.
Femoroacetabular impingement (FAI) and hip dysplasia are the two main causes of early hip degeneration. The end-stage of these degenerative changes is always hip-replacement. However, many patients become symptomatic long before degenerative changes occur. Treatments of pathology prior to OA are available upon early detection: hip preservation surgery, hip arthroscopy and open realignment osteotomies which are applied more and more frequently. In addition, congenital or traumatic deformities, Rheumatoid arthritis or spinal deformities might cause hip pain. Also differences in leg length might cause hip pain. X-ray is still the gold standard for patients with hip pain. Knowledge on how to fully evaluate the AP pelvic radiograph can lead to earlier diagnosis, minimize unnecessary additional imaging and prompt the provider as to the correct next steps in workup and management. For this purpose, HIPPO can determine the following measurements:
- CCD angle
- LCE angle
- Leg length discrepancy and pelvic obliquity (if image contains no implants at both hip joints and the acquisition was standing)
The measurement of hip angles is relevant in that doctors can take appropriate measures and therapies for early signs of hip disease. These include, for example, hip arthritis and hip dysplasia. HIPPO supports the objective and standardized measurement of the most important hip angles and distances based on digital x-rays. These include the CCD and LCE angles as well as leg length discrepancy and pelvic obliquity. Reading cases over several hours, fatigue impacts interpretation performance and decreases the observers’ performance. Our artificial intelligence driven HIPPO solution supports medical experts in their decision making and consequently in the selection of matching therapies.
HIPPO receives radiographs from a PACS, analyzes the images and stores the analysis results in the PACS. As soon as HIPPO receives the image, the analysis and the generation of reports are fully automated and entail no user interaction besides the user viewing the reports. The user can send images to HIPPO via standardized DICOM commands or the file interface and receive reports over the same interface. In this sense, the user does not “operate” the device but simply reviews the reports and can accept or reject them. The HIPPO software does not provide a graphical user interface that uses the DICOM-viewers of existing workflows by attaching reports to the original study. All relevant images can be pre-analyzed by HIPPO automatically by appropriate filter rules in the PACS. With this the original workflow is seamlessly augmented by HIPPO.
IB Lab HIPPO is a radiological fully-automated image processing software device of either computed (CR) or directly digital (DX) images of the pelvis or hip. On either standing or supine, unilateral or bilateral AP radiographs, HIPPO is intended to aid medical professionals in the measurement of the Corpus-Collum Diaphysen (CCD) angle (also known as Neck-Shaft angle), and the Lateral Center-Edge Angle (LCE). On bilateral standing AP hip radiographs, HIPPO aids in the detection of the presence or absence of pelvic obliquity and leg length discrepancy. It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by trained professionals including, but not limited to, radiologists and orthopedics.
The quality of most measurements depends on the operation of the imaging device and the image acquisition processes. A correct image and therefore, an accurate examination will be the result of a healthcare professional that uses standardized methods to acquire an AP standing or AP supine image, with or without the help of technical devices. Only hips without surgical devices are processed. HIPPO should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The system is to be used by trained professionals including, but not limited to, radiologists and orthopedics.
Model performance metrics
The total number of images in the Standalone Performance Testing data set was 52 with a total of 104 individual hips available for annotation. Prior to the assessment of HIPPO angles and measurements, 9 hips were removed from the dataset: 9 hips with implants based on the ground truth. The remaining dataset included 95 hips from 52 images. For the LCE parameter, the mean paired difference between HIPPO and ground truth amounted to 0.47° ± 3.31°. For the CCD parameter, the mean paired difference between HIPPO and ground truth amounted to 0.02°±4.18°. For the Orthograde angle parameter, the mean paired difference between HIPPO and ground truth amounted to -0.06°±0.39°. And for the Orthograde distance parameter, the mean paired difference between HIPPO and ground truth amounted to 0.07mm ± 0.94mm.
Musculoskeletal (MSK) diagnoses are often subjective and inconsistent. This and the general need to bring MSK-measurements to the digital age finally drove us to change the status quo. Our software offers simplification and standardization and full integration to your existing system. Furthermore, we provide quantitative disease parameters to support treatment decisions of medical experts. ImageBiopsy Lab offers AI-driven solutions for anatomical regions such as the knee, the hand, and hip while constantly working on additional MSK solutions.