For the use cases of bone age prediction and lung nodule detection on radiographs, commercial AI products were retrospectively assessed according to the Project AIR methodology. With this method, the authors aim to provide comparable, transparent information on AI performance. All vendors with eligible products on AIforRadiology.com were invited to participate. A total of nine products were evaluated. Want to have a quick view of the results and how they compare to human readers? You can check out the leaderboards for bone age and lung nodule detection. Over time, new products or new versions of the products may be added here.
Read full study.
Abstract
In independent validation, nine artificial intelligence products for detecting lung nodules on chest radiographs or predicting bone age on hand radiographs showed improved or comparable performance to human readers.
Background
Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited.
Purpose
To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs.
Materials and Methods
This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience.
Results
Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard (r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86–0.93; P value range, <.001 to .04).
Conclusions
Compared with human readers, four AI algorithms for detecting lung nodules on chest radiographs showed improved performance, whereas the remaining algorithms tested showed no evidence of a difference in performance.
