ABSTRACT
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. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Omoumi and Richiardi in this issue.
Subject(s)
Artificial Intelligence , Software , Humans , Female , Male , Child , Middle Aged , Retrospective Studies , Algorithms , LungABSTRACT
BACKGROUND: Although cardiac MR and T1 mapping are increasingly used to diagnose diffuse fibrosis based cardiac diseases, studies reporting T1 values in healthy and diseased myocardium, particular in nonischemic cardiomyopathies (NICM) and populations with increased cardiovascular risk, seem contradictory. PURPOSE: To determine the range of native myocardial T1 value ranges in patients with NICM and populations with increased cardiovascular risk. STUDY TYPE: Systemic review and meta-analysis. POPULATION: Patients with NICM, including hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM), and patients with myocarditis (MC), iron overload, amyloidosis, Fabry disease, and populations with hypertension (HT), diabetes mellitus (DM), and obesity. FIELD STRENGTH/SEQUENCE: (Shortened) modified Look-Locker inversion-recovery MR sequence at 1.5 or 3T. ASSESSMENT: PubMed and Embase were searched following the PRISMA guidelines. STATISTICAL TESTS: The summary of standard mean difference (SMD) between the diseased and a healthy control populations was generated using a random-effects model in combination with meta-regression analysis. RESULTS: The SMD for HCM, DCM, and MC patients were significantly increased (1.41, 1.48, and 1.96, respectively, P < 0.01) compared with healthy controls. The SMD for HT patients with and without left-ventricle hypertrophy (LVH) together was significantly increased (0.19, P = 0.04), while for HT patients without LVH the SMD was zero (0.03, P = 0.52). The number of studies on amyloidosis, iron overload, Fabry disease, and HT patients with LVH did not meet the requirement to perform a meta-analysis. However, most studies reported a significantly increased T1 for amyloidosis and HT patients with LVH and a significant decreased T1 for iron overload and Fabry disease patients. DATA CONCLUSIONS: Native T1 mapping by using an (Sh)MOLLI sequence can potentially assess myocardial changes in HCM, DCM, MC, iron overload, amyloidosis, and Fabry disease compared to controls. In addition, it can help to diagnose left-ventricular remodeling in HT patients. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:891-912.
