IB LabKOALA™uses deep learning technology for detecting radiographic signs of knee osteoarthritis and augments the reporting workflow. The software application scores the stage of osteoarthritis according to the Kellgren & Lawrence grading system. It also provides precise and automated measurements of the minimum joint space width, as well as assessment of the severity of joint space narrowing, osteophytosis and sclerosis based on OARSI criteria.
IB LabKOALA™ 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. IB Lab KOALA™ facilitates monitoring of disease progression by facilitating comparison of radiographic disease parameters over time.
- Kellgren & Lawrence grade
- Minimum joint space width
- Joint space narrowing
- Enables instant, verifiable decision making in difficult cases
- Facilitates monitoring of knee osteoarthritis progression
- Enhances diagnosing and reporting knee osteoarthritis according to the latest clinical guidelines
- Empowers non-specialists to perform at specialist level in detecting radiographic signs of knee osteoarthritis
Knee osteoarthritis is a paralyzing joint disease that can lead to joint replacement. Knee osteoarthritis has a life timerisk as high as 45% , with the risk becoming even more severe due to two major risk factors: ageing and obesity [1, 2] .
Knee osteoarthritis affects over 200 million patients worldwide , resulting in approximately 100 million knee radiographs taken in the EU alone in 2020 . Consistent tracking of radiographic damage over time could help early diagnosis and prevention of disease progression.
However, diagnosing the loss of cartilage, the hallmark feature of knee osteoarthritis, is difficult to do consistently in practice, and especially for non-experts. Radiologists read an average of 10knee radiographs per day, amounting to approximately 40 minutes of the daily workload .
Training and Validation:
- Deep learning algorithms trained on over 35,000 individual knee radiographs
- Data from a longitudinal study with centers across the United States
- Each image was consensus-graded by board certified radiologists following OARSI criteria and the Kellgren and Lawrence scale
- The AI follows the established radiological workflow: measurement of anatomical distances and angles recognition of disease symptoms, standardized classification and reporting
- Validated on over 10,.000 knees
- Lifetime risk of symptomatic knee osteoarthritis, Murphyet al. 2008, Arthritis Care & Research
- Lifetime risk and age of diagnosis of symptomatic knee osteoarthritis in the US, Losina et al., 2013, Arthritis Care & Research
- Global, Regional, and National Incidence, Prevalence, and Years Lived with Disability for 310 Diseases and Injuries, 1990–2015: A Systematic Analysis for the Global Burden of Disease Study 2015: October 2016, The Lancet
- IB Lab Market Survey 2020