Physis received Health Canada clearance as a Class II device on July 5, 2022. The journey of Physis began at the RSNA inaugural machine learning challenge in 2017. Mark and Alex earned first place with their bone age algorithm, achieving a mean absolute difference (MAD) from the ground truth (a weighted mean of 6 reads) of 4.3 months. As a comparison, the MAD of one of the six pediatric radiologist reviewers to the ground truth, unaided by an algorithm, was 7.0 months.
Bone age assessment from pediatric hand radiographs is a routine task that determines an important developmental indicator, but one that is “considered tedious, time consuming, and limited by considerable interrater and intrarater variability”. Physis acts as a smart atlas, estimating bone age age to identify what it thinks is the closest Greulich & Pyle standard to the patient's image. The user can start at that page of the G&P Atlas, scroll to neighbouring standards, and use their clinical judgment to agree with, or modify, that Physis bone age estimate. Physis optionally includes a licenced digital copy of the G&P Atlas and a customizable report.
Recent publications by independent investigators are available:
Beheshtian E, Putman K, Santomartino SM, Parekh VS, Yi PH. Generalizability and Bias in a Deep Learning Pediatric Bone Age Prediction Model Using Hand Radiographs. Radiology. 2022 Sep 27:220505. doi: 10.1148/radiol.220505. Epub ahead of print. PMID: 36165796.
Klimont M et al. Evaluation of an Automated Bone Age Assessment Shows Better Performance in Older Patients. Journal of Medical Imaging and Health Informatics. 2021 Apri;11(4): 1063–1067.
Gerges M et al. Modernization of bone age assessment: comparing the accuracy and reliability of an artificial intelligence algorithm and shorthand bone age to Greulich and Pyle. Skeletal Radiology. 2020 Sep;49(9):1449-1457.