Situation
Leg or lower extremity length discrepancy are common deformities affecting 70-90% of the adult and pediatric population [1]. When left undetected or measured imprecisely, patients suffer from functional and biomechanical limitations as well as cosmetic impairments. Even minor deviations can cause imbalances and unilateral pain across the entire body and may trigger passive structural and degenerative changes in hip, spine, knee and muscles. The resulting degenerative diseases led to 1.5 million total knee replacements (TKA) in OECD countries in 2011, and knee replacement rates increased by 40% between 2007 and 2017 [2].
Accurate, reliable measurements of lower extremity geometry require expert training on established protocols, often requiring specialized software. An orthopedic surgeon spends over 8 minutes per reading of a single full-leg radiograph [3]. Surgeons new to complex measurements and procedures can see revision rates 3 times higher than normal [4] – lack of training is a key reason for adverse events [5].
Product
IB Lab’s diagnostic support tool LAMA uses deep learning technology for automated and precise measuring of leg geometry to evaluate lower limb deformities. LAMA aids in the detection of genu varum/valgum by measuring of mechanical axis deviation (MAD) and detection of leg length discrepancy by comparing right and left legs on bilateral images. Detailed analysis of mechanical and anatomical angles according to Paley allows informed decision making on next steps in treating the patient. LAMA’s measurements of HKA, JLCA and MAD are precise to within 0.3°, 0.8° and 1.1 mm and leg length discrepancy is accurate to 0.2 cm of expert readers augmenting reading results especially of non-experts. Reading time is brought down from 8 minutes to under 60 seconds needed for calculation [6].
LAMA highlights relevant clinical findings by applying 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 your pre-defined RIS-template for accelerated reporting. The AI facilitates monitoring of disease progression by facilitating comparison of radiographic disease parameters over time. See how it works.
Benefits
- Quicker pre-selection by instantly triaging normal and abnormal cases
- Increases workflow efficiency by saving reading and reporting time
- Enables non-experts providing precise results for measuring the lower extremity geometry
- Reduces the risk of inter-rater variability for reading long leg radiographs
Training & Validation
- AI is trained on over 10,000 individual knee, hip and full leg radiographs
Data from five large longitudinal multi-center datasets in the US and Europe - AI based on Deep Learning to automatically recognize and localize anatomically relevant landmarks on the hip, knee and ankle.
- CE-certified
Note: product description above is based on the product version V1.02
- Gary A Knutson: Anatomic and functional leg-length inequality: A review and recommendation for clinical decision-making. Part I, anatomic leg-length inequality: prevalence, magnitude, effects and clinical significance, Chiropractic & Osteopathy, 2005.
- G. McDaniel, K.L. Mitchell, C. Charles, V.B. Kraus: A comparison of five approaches to measurement of anatomic knee alignment from radiographs, November 16, 2009.
- James M Hartford, Michael J Bellino: The learning curve for the direct anterior approach for total hip arthroplasty: a single surgeon’s first 500 cases, September 19, 2017.
- World Health Organization: Increasing complexity of medical technology and consequences for training and outcome of care, August 2010.
- IB Lab LAMA Clinical Validation study
- IB Lab US Market Survey 2020
