IB Lab HIPPOTM

HIP POsitioning Assistant

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 based on digital x-rays. These include, for example, the CCD and LCE angles as well as numerous other relevant angles.

IB Lab HIPPOTM

HIP POsitioning Assistant

For measurement of hip positioning and pelvic morphology.

10 radiological findings and measurements including:
LCE-angle, acetabular dysplasia, femoroacetabular impingement, CCD-angle, coxa vara, coxa valga, pelvic obliquity/leg length difference

NEW acetabular coverage measurements: Tönnis angle, sharp angle, extrusion index / femoroacetabular coverage

This product is CE-certified.

Not for clinical use in the USA.

Situation

Femoroacetabular impingement and hip dysplasia are the two main causes of hip degeneration, with the an end stage being total hip arthroplasty. Hip arthroplasty will grow from 1.8 million/year in 2015 to 2.8 million/year in 2050 in OECD countries [1], resulting in an increased workload for radiologists. Reading pelvic x-ray images requires in-depth knowledge of 3D pelvic morphology to correctly interpret the 2D projection. This is hard, subjective and error-prone. And on top of that, there will be a lot more of it in the coming years. Stress and reporting fatigue lead to differing levels of performance on x-ray interpretation, especially for non-experts, with certain measurements on hip radiographs shown to have high inter-rater variability [2]. Unstructured reporting further leads to inconsistencies in the diagnosis process. Radiologists read an average of 10 hip radiographs per day, accounting for approximately 40 minutes of the daily workload [3].

Product

IB Lab’s diagnostic support tool HIPPO uses deep learning technology for automated and precise measurement of hip angles such as Corpus-Collum-Diaphysis (CCD) angle (also known as Neck-Shaft angle) and the Lateral Center-Edge Angle (LCE). On bilateral standing AP hip radiographs, HIPPO supports the medical expert in the detection of the presence or absence of leg length difference. Readings are precise and reading and reporting time can be reduced from 3.5 minutes to 30 seconds per image when using HIPPO [5].

HIPPO highlights relevant clinical findings by applying the latest international medical standards to enable timely and accurate decision making. The findings are summarized in a visual output report, attached to the original x-ray image and saved automatically in the PACS system. The AI-results are fed as text into the predefined RIS-template for accelerated reporting. HIPPO eases disease progression monitoring by facilitating comparison of radiographic disease parameters over time. See how it works.

Benefits

  • Increases patient throughput by automating report workflows
  • Enables instant, verifiable decision making in difficult cases
  • Reduces effects of inter-rater variability when assessing pelvic morphology
  • Facilitates monitoring of disease progression

Training & Validation

  • Deep learning algorithms trained on over 4,000 individual pelvis and hip radiographs
  • Data from five large longitudinal multi-center datasets in the US and Europe
  • Reproducible to automatically recognizes and localize anatomically relevant landmarks on the hip and pelvis (teardrops)
  • The AI follows the established radiological workflow: measurement of anatomical distances and angles, recognition of disease symptoms, standardized classification and reporting
  • Consensus grading of each radiograph: Each detection step is done by an ensemble of three AI-models voting for the best result increasing precision
  • Automatically detects implants at the hip
  • CE-certified

Example Cases

Expert opinion without AI measurements
Bilateral AP-pelvic radiograph of an eldery male person, with a slight acetabular overcoverage, further progression should be followed.

Automated AI measurements
HIPPO’s overlay corroborates the doctor’s intuition with concrete measurements, where LCE and CCD angles show slight abnormality. Consistent measurements of these angles enable precise tracking of changes over time.

Automated AI report
HIPPO’s summary report distinctly highlights both LCE and Coxa valga as increased helping to reduce the amount of under-reported findings. Provided reference values allow to quickly assess the severity of the detected abnormality as mild.

 

Expert opinion without AI measurements
Unilateral AP-pelvic radiograph of the right hip, with a normal CE and slight signs of a coxa valga.

Automated AI measurements
HIPPO provides automatic measurements and highlights the abnormal CCD-angle (in orange), supporting the doctor’s impression.

Automated AI report
HIPPO’s automated report includes all measurements and highlights the abnormal values, facilitating the documentation of findings.

Expert opinion without AI measurements
Bilateral AP-pelvic radiograph of an eldery female person. Normal CE and CCD Angels and signs of osteoarthritis on the left side and a previous total hip arthroplasty on the right side.

Automated AI measurements
HIPPO substantiates the doctor’s impression and documents the findings with automatic measurements on the pre-operative hip.

Automated AI report
HIPPO’s summary report shows the measured angles as within the norm, providing reference values and citations for criteria used.

Supporting evidence

[1] Christof Pabinger, Harold Lothaller, Nicole Portner, Alexander Geissler: Projections of hip arthroplasty in OECD countries up to 2050, HIP International, 2018. 

[2] LCE angle – S. Monazzam et al: Lateral Center-Edge Angle on Conventional Radiography and Computed Tomography. Clinical Orthopaedics and Related Research 471, no. 7, July 2013. 2233–37. 

[3] LCE, VCA, HNO, alpha, Tönnis, Tönnis OA – J. Carlisle: RELIABILITY OF VARIOUS OBSERVERS IN DETERMINING COMMON RADIOGRAPHIC PARAMETERS OF ADULT HIP STRUCTURAL ANATOMY, The Iowa Orthopaedic Journal 31, 2011. 52–58

[4] IB Lab US Market Survey 2020

[5] IB Lab HIPPO clinical validation study

[6] IB Lab US Market Study 2020

Literature

  • Leunig M, Ganz R: The evolution and concepts of joint-preserving surgery of the hip. The Bone & Joint Journal, 2014. 96-B(1):5-18. doi:10.1302/0301-620X.96B1.32823
  • Leitner L, Türk S, Heidinger M, et al.: Trends and Economic Impact of Hip and Knee Arthroplasty in Central Europe: Findings from the Austrian National Database, Sci Rep, 2018. 8(1):1-5. doi:10.1038/s41598-018-23266-w
  • Kraeutler MJ, Garabekyan T, Pascual-Garrido C, Mei-Dan O: Hip instability: a review of hip dysplasia and other contributing factors. Muscles Ligaments Tendons J, 2016. 6(3):343-353. doi:10.11138/mltj/2016.6.3.343
  • Ward D, Parvizi J.: Management of Hip Pain in Young Adults. Orthopedic Clinics. 2016. 47(3):485-496. doi:10.1016/j.ocl.2016.03.002
  • Nepple JJ, Byrd TJW, Siebenrock KA, Prather H, Clohisy JC.: Overview of Treatment Options, Clinical Results, and Controversies in the Management of Femoroacetabular Impingement, JAAOS – Journal of the American Academy of Orthopaedic Surgeons, 2013. 21:S53. doi:10.5435/JAAOS-21-07-S53
  • Henebry A, Gaskill T.: The Effect of Pelvic Tilt on Radiographic Markers of Acetabular Coverage, Am J Sports Med, 2013. 41(11):2599-2603. doi:10.1177/0363546513500632
  • Moritz Tannast, Markus S. Hanke, Guoyan Zheng, Simon D. Steppacher, Klaus A. Siebenrock.: What Are the Radiographic Reference Values for Acetabular Under- and Overcoverage?, Clinical Orthopaedics and Related Research®, 2015. 473 (4): 1234. doi:10.1007/s11999-014-4038-3 – Pubmed
  • Lee YK, Chung CY, Koo KH et-al.: Measuring acetabular dysplasia in plain radiographs. Arch Orthop Trauma Surg, 2011. 131 (9): 1219-26. doi:10.1007/s00402-011-1279-4 – Pubmed citation