September 2019: BoneXpert version 3.0 released
The long-awaited version 3.0 of BoneXpert is now rolling out to all customers.
It represents the most significant update, since BoneXpert's launch 10 years ago.
The main features are:
- Improvement of the accuracy of the bone age measurement
- Carpal bone age determination
- Bone age and BHI determination down to age zero
- Fewer rejections of images and more accurate localisation of the bones
Below is a detailed account of the four new features in version 3:
The root mean square error (RMSE) of BoneXpert relative to manual bone age rating is reduceed from 0.72 y in version 2 to 0.63 y in version 3. This was reported at ESPE in Vienna in the talk by David Martin, who performed this validation on 8250 images from Tübingen. The improvement in accuracy is actually more dramatic than these numbers indicate, because the error 0.63 y is mainly due to the manual rater variability. If one instead compares BoneXpert to the average of six manual ratings, the RMSE is only 0.45 y. In fact, BoneXpert has the same accuracy as the average of four manual ratings. This is described in detail in the post about how RSNA boosts the accuracy of automated bone age rating.
2. Carpal bone age
Version 2 ignored carpals, because there is a consensus in most countries that carpals are less important. Bone age should primarily be determined from bones with epiphyses, i.e. radius, ulna and the 19 short bones. When version 3 now analyses the carpals, it provides carpal bone age as a separate number. The maturation of carpals and short bones are controlled by different hormones control: Short bones respond more to sex steroids than carpals. The main bone age result in BoneXpert therefore takes only the bones with epiphyses into account. A carpal bone age deviating from this "main bone age" is potentially a sign of hormonal imbalance. In some disorders, e.g. precocious puberty, this could be the effect of a treatment.
Version 2 did not analyse hands with bone age less than approx. 2 years. Version 3 extends the bone age range down to new-borns. This development was based on the Paris study of 425 normal children followed longitudinally with hand X-rays at ages 1, 3, 6, 9, 12, 18, 24, 36, 48 months etc. This study was also used to establish reference curves for bone age and BHI, so that the measurements of BA and BHI on infants are associated with BA SDS and BHI SDS values. The BHI reference curves were reported at the ICCBH conference in May.
4. Finding bones
Version 2 rejected some images due to postprocessing (edge enhancement), which is common in modern digital detectors. BoneXpert version 3 is much better adapted to these variations and rejects far fewer images. However, it is still advisable to not use strong postprocessing, because it can lead to skewed measurements or even rejection of images.
Version 3 also locates the bones more accurately than version 2; the accuracy is now SD = 0.1 mm. This is important for two reasons. Firstly, locating the bone contour accurately leads to more accurate bone age assessment. Secondly, it gives the user a visual feedback, or "explanation", on the bone age assessment, thereby yielding confidence in the measurement. For instance, the accurate delineation of the epiphyses shows that BoneXpert is capable of assessing the width of the epiphysis, which is a crucial maturity indicator.