Deploying artificial intelligence (AI)-based image analysis software for hip dysplasia diagnosis can save time and money without compromising diagnostic reliability. This is the result of a recently published external validation study that tested IB Lab HIPPO – a musculoskeletal software tool by ImageBiopsy Lab, Austria (IB Lab). Currently, the diagnosis of hip dysplasia, an abnormality of the hip joint, relies on time-consuming and expensive manual radiological measurements. The study conducted at the University of Texas Southwestern Medical Center shows that using an AI tool for image analysis can significantly speed up diagnosis and lead to labor savings of highly qualified experts. In a cohort of 256 hips, HIPPO was successful in performing all six measurements relevant to the assessment of hip dysplasia and the study confirmed good to excellent inter-reader reliability for important bone parameters measured by HIPPO and trained experts, demonstrating the reliability of automated analysis based on artificial intelligence. . Recently, the results were presented at the annual meeting of the Radiological Society of North America (RSNA).
About 5-10% of the population is affected by hip dysplasia, a developmental condition where the bones in the hip joint are misaligned. If left untreated or treated too late, it leads to pain, instability and premature osteoarthritis. Several complex radiological measurements are used to assess the extent of the joint abnormality. However, unstandardized measurements and high inter-reader variability lead to statistically and clinically relevant differences in hip diagnosis and potentially to inadequate treatment. Using AI-based image analysis software, however, can contribute to more standardized and repeatable measurements – if it proves to be as accurate as the current, time-consuming gold standard, manual measurements of images by trained experts.
Reliable. quickly. profitable
“In summary,” says Dr. Richard Ljuhar, CEO and co-founder of IB Lab, “the study confirms that for the vast majority of images analyzed, the AI-based method essentially returns the same measurements as those obtained. by trained experts – just much faster and therefore considerably cheaper. »
In detail, the UTSW Medical Center team used radiological images of 256 hips. From each image, 6 measurements were taken: center-lateral edge angle, caput-collum-diaphyseal angle, pelvic obliquity, Tönnis angle, Sharp angle and coverage of the femoral head, either by HIPPO or by three experts. trained. Comparing the results obtained by either method, they showed good to excellent correlations, ranging on average from 0.6 to 0.98 (1 being identical results). Even better results were obtained when the most commonly used clinical measurements (lateral central edge and Tönnis angle) were compared. Here, the correlation was 0.71 to 0.86 and 0.82 to 0.90, respectively.
saving time and money
In the study, three trained human experts were asked to perform manual readings. The median time to read a single image varied widely between the three individuals, from 131 seconds to 734 seconds. “This highlights a problem with the standard diagnostic approach,” says Dr. Ljuhar. “The time required for human analysis is largely individual and impedes efficient and coordinated workflows between institutions. HIPPO, in comparison, took only 41 seconds per image (median) with very little variation, resulting in a 70-90% time saving and the ability to standardize diagnostic procedures between establishments.
But time is not all that can be saved by using HIPPO. Based on the average salaries of orthopedic surgeons or radiologists and the aforementioned time savings, up to 80% of the labor costs for evaluating x-rays can be saved. In detail, the average cost of an image analysis by an orthopedic surgeon is 36.50 USD while the assessment supported by HIPPO would cost the equivalent of 4.18 USD of the surgeon’s time. For a radiologist, the values are $28.66 to $3.27. In an internal calculation, IB Lab extrapolated these figures for medical institutions that analyze 10,000 X-rays per year.
For analysis by orthopedic surgeons which totals 320,000 USD per year. Considering the license fees for such a volume of hip x-rays, this equates to over 85% potential annual savings. »
Dr. Richard Ljuhar, CEO and Co-Founder, IB Lab
The recent study confirms IB Lab’s position at the forefront of AI-based medical image analysis. In addition to HIPPO for hip abnormalities, the company offers analysis modules such as PANDA for bone age assessments, FLAMINGO for detection and quantification of silent vertebral spine fractures, and SQUIRREL for spinal disorders. spine. Other modules are constantly being developed and evaluated in conjunction with some of the world’s most prestigious medical institutions.
We want to say thanks to the writer of this article for this amazing content
AI-based image analysis software for hip dysplasia diagnosis can save time and money
You can view our social media profiles here , as well as other pages related to them here.https://www.ai-magazine.com/related-pages/