Validation of BoneXpert in India
Dr Anuradha V. Khadilkar’s research group in Pune, India, has published a study of BoneXpert bone age, reporting its accuracy and presenting reference curves for Indian children.
Dr Anuradha V. Khadilkar’s research group in Pune, India, has published a study of BoneXpert bone age, reporting its accuracy and presenting reference curves for Indian children.
New results on Bone Health Index reference curves for 12 populations spanning Asia, Africa, Europe, and North America were presented at the recent International Conference on Children’s Bone Health in Salzburg.
At the European Society of Paediatric Radiology (ESPR) conference held in Sevilla in June 2024, Karen Rosendahl of Tromsø (awarded the ESPR 2024 Gold Medal) gave a talk titled “Revisiting Osteopenia.”
Read more “Hand radiographs as a potential replacement for DXA in osteopenia screening”
Auckland Radiology Group – Auckland’s largest independent radiology provider – has become the first private radiology clinic in New Zealand to adopt BoneXpert’s AI software-based medical device for automated bone age and adult height prediction.
Kicky van Leeuwen and the AIR Working Group of Radboud University (Nijmegen, the Netherlands) have performed an external validation of commercial AI systems for bone age and lung nodules.
Visiana welcomes Ruby Hall Clinic as a BoneXpert customer. Ruby Hall Clinic is a flagship hospital in Pune, India, providing healthcare through a system of 3 hospitals and 24 diagnostic centres.
Read more “Ruby Hall Clinic uses BoneXpert software”
In a new, open access paper in European Radiology, Kicky van Leeuwen and a team from Nijmegen surveyed which AIs are actually used in radiology departments in the Netherlands in 2022.
Bone Health Index is significantly lower in children with vertebral fractures than in children without.
BoneXpert has been installed in more than 80% of the major hospitals in the United Kingdom.
Read more “Widespread use of BoneXpert in the United Kingdom”
The accuracy of bone age determination by BoneXpert and Panda in 188 images was reported at ECR.
Federica Zanca from Leuven, together with four co-authors from Switzerland, presented a study comparing two bone age algorithms, BoneXpert from Visiana and Panda (based on deep learning) from ImageBiopsyLab. The study included 188 images taken under real-world conditions across 11 centres in Switzerland. The ground truth was provided by an exceptionally reliable manual rater. BoneXpert’s intended use includes autonomous use, while Panda’s is intended to only assist the radiologist. However, in this study, both algorithms were used without human interference.
The mean absolute deviation between the algorithm and the ground truth was 0.36 y for BoneXpert and 0.42 y for Panda, and this difference was significant with p=0.01.
In the Bland Altman plots below one can clearly see that the agreement is better with BoneXpert.
Figure 1: BoneXpert versus radiologist
Figure 2: Panda versus radiologist
The plots reveal that there are markedly fewer large deviations with BoneXpert.
So what is the clinical signficance of the different performance? The authors adressed this by defining the clinically acceptable limit of agreement to be ±1 year, and they found twice as many such significant deviations for Panda.
The table below summarises all the findings.
The poster is available though myESR (requiring log in)
Table: The deviation between the bone age algorithm and the radiologist
BoneXpert | Panda | |
Mean Absolute Deviation | 0.36 y | 0.42 y |
Root Mean Square Deviation | 0.47 y | 0.55 y |
Number of deviations > 1 y | 7 | 14 |
Largest deviation | 1.2 y | 1.9 y |