Radiological evaluation of bone age from x-rays of the left hand is the diagnostic standard for physicians looking to assess pediatric growth disorders.
While assessing bone age, radiologists use the Greulich&Pyle method and must do a manual comparison of digital radiographs from patients with reference images in an atlas, a time-consuming task with a high level of inter-rater variability.
IB Lab PANDA™ provides a swift automated method to estimate bone age according to Greulich&Pyle in a standardized form to facilitate the monitoring of child growth and development.
5 radiological findings, measurements, and results including:
- Pediatric bone age according to Greulich & Pyle,
- Delayed/advanced bone age patient status,
- Growth potential and height estimation according to Bayley&Pinneau
- Saves time: less than 5 seconds for calculating the pediatric bone age according to Greulich & Pyle
- Enhances the consistency in reading and reporting of hand radiographs for bone age and
- Facilitates monitoring and forecasting of physicians’ therapeutic success
The estimation of pediatric bone age according to the Greulich & Pyle method on hand radiographs of children aged between 36 months and 192 months (girls) or 204 months (boys). The software 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, pediatricians, and endocrinologists.
The IB Lab PANDA™ software is intended to be used on juvenile humans aged between 36 months and 192 months (female) or 204 months (male) for the determination of bone age.
Training and Validation:
Trained on over 12,000 hand radiographs from two institutions in the US (Lucile Packard Children’s Hospital at Stanford University and Children’s Hospital Colorado).
IB Lab PANDA™ uses an ensemble of decision models to report bone age based on the Greulich & Pyle atlas.
The standard deviation for a given chronological age is determined by rounding down to the next age in the Brush table for the appropriate sex. 6
Validated on the Digital Hand Atlas dataset consisting of 1384 DICOM left-hand radiographs of normal children between 0 and 228 months of age, from different ethnicities (African-American, Asian, Caucasian, Hispanic). The data was collected from the Children’s Hospital of Los Angeles from the late 1990s through the late 2000’s.
Validated on the test-set of the RSNA 2017 bone age challenge. This Sex-stratified set of 200 hand radiographs (100 from male patients and 100 from female patients) comprises images from the Lucile Packard Children’s Hospital at Stanford University. Each image in this test set was reviewed by three fellowship-trained pediatric radiologists.
- D. G. King, D. M. Steventon, M. P. O’Sullivan, A. M. Cook, V. P. L. Hornsby, I. G. Jefferson, and P. R. King: Reproducibility of bone ages when performed by radiology registrars: an audit of Tanner and Whitehouse II versus Greulich and Pyle methods, The British Institute of Radiology, 2014.
- S.Serinellia, V.Panettab, P. Pasqualettib, D. Marchetti: Accuracy of three age determination X-ray methods on the left hand-wrist: A systematic review and meta-analysis, Legal Medicine, 2011.
- Halabi, S. S., Prevedello, L. M., Kalpathy-Cramer, J., Mamonov, A. B., Bilbily, A., Cicero, M., … Flanders, A. E.: The RSNA Pediatric Bone Age Machine Learning Challenge, Radiology, 290(2), 2018. 498–503.
- Gaskin, C. M., Kahn, S. L., Bertozzi, J. C., & Bunch, P. M.: Skeletal Development of the Hand and Wrist. Oxford University Press, 2011.
- IB Lab Clinical Evaluation Study
- Simmons K, Greulich WW. 1944. The Brush Foundation Study of Child Growth and Development: II. Physical Growth and Development. Monogr. Soc. Res. Child Dev. 9(1):i–87.