RESUMO
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.
Assuntos
Inteligência Artificial , Software , Humanos , Feminino , Masculino , Criança , Pessoa de Meia-Idade , Estudos Retrospectivos , Algoritmos , PulmãoRESUMO
OBJECTIVE: Aneurysmal bone cysts (ABC) rarely present in soft tissue locations (STABC). The 30 cases of STABC reported in the English literature were reviewed. Six new cases retrieved from the files of the Netherlands Committee on Bone Tumors were compared to the six cases described in the radiological literature. MATERIALS AND METHODS: Imaging studies and histopathology of six new STABC cases were reviewed. Follow-up was recorded with respect to local recurrence. FISH for USP6 rearrangement and/or anchored multiplex PCR-based targeted NGS using Archer FusionPlex Sarcoma Panel were attempted. RESULTS: On imaging, the six STABC cases presented as a solid or multicystic intramuscular soft tissue mass, usually with thin peripheral mineralized bone shell. On MRI, perilesional edema was visualized in nearly all cases. Fluid-fluid levels were observed in one case. All lesions had the distinct histologic features of STABC. In three cases suitable for NGS, the diagnosis of STABC was confirmed by a COL1A1-USP6 fusion gene. In one additional case, USP6 gene rearrangement was detected by FISH. After marginal excision, none of the six STABC recurred after a mean follow-up period of 50 months (range, 39-187 months). CONCLUSIONS: On imaging, it can be difficult to discriminate between STABC and myositis ossificans. The presence of a thin bony shell and fluid-fluid levels can be helpful in discriminating these two entities. STABC is readily diagnosed after histopathologic examination of the resection specimen. STABC belongs to the spectrum of tumors with USP6 rearrangements, which includes ABC, myositis ossificans, and nodular fasciitis.