Search

Accurately predicting a fetus's gestational age (GA) is crucial in prenatal care. This study aimed to develop an artificial intelligence (AI) model to predict GA using biometric measurements from fetal brain magnetic resonance imaging (MRI). We assessed the significance of using different reference standards for interpreting GA predictions. Measurements of biparietal diameter (BPD), fronto-occipital diameter (FOD), and head circumference (HC) were obtained from 52 normal fetal MRI cases from Rush University. Both manual and AI-based methods were utilized, and comparisons were made using three reference standards (Garel, Freq, and Bio). The AI model showed a strong correlation with manual measurements, particularly for HC, which exhibited the highest correlation with actual values. Differences between GA predictions and picture archiving and communication system (PACS) records varied by reference, ranging from 0.47 to 2.17 weeks for BPD, 0.46 to 2.26 weeks for FOD, and 0.75 to 1.74 weeks for HC. Pearson correlation coefficients between PACS records and GA predictions exceeded 0.97 across all references. In conclusion, the AI model demonstrated high accuracy in predicting GA from fetal brain MRI measurements. This approach offers improved accuracy and convenience over manual methods, highlighting the potential of AI in enhancing prenatal care through precise GA estimation. [ABSTRACT FROM AUTHOR]

Objective: To analyze clinical and radiographic features that may impact the rate of focal hyperostosis (FH) on computed tomography (CT) for primary and recurrent sinonasal inverted papillomas (IPs) as well as highlight factors that may affect concordance between FH and IP true attachment point (TAP). Methods: All IPs resected between 2006 and 2022 were retrospectively reviewed. CTs were read by a neuroradiologist blinded to operative details. IP with malignancy was excluded. Operative reports and long‐term follow‐up data were evaluated. Results: Of 92 IPs, 60.1% had FH, 25% had no CT bony changes, and 20.7% were revision cases. The recurrence rate for rhinologists was 10.5% overall and 7.3% for primary IPs. Primary and revision IPs had a similar rate of FH (63% vs. 52.6%; p = 0.646) and FH–TAP agreement (71.7% vs. 90%; p = 0.664). Nasal cavity IPs, especially with septal attachment, were more likely to lack bony changes on CT (57.1%) compared to other subsites (p = 0.018). Recurrent tumors were 16 mm larger on average (55 mm vs. 39 mm; p = 0.008). FH (75.0% vs. 60.9%; p = 0.295), FH–TAP concordance (91.7% vs. 74.4%; p = 0.094), and secondary IP (18.8% vs. 20.3%; p = 0.889) rates were similar between recurrent and nonrecurrent tumors. Conclusion: Primary and revision IPs have a similar rate of FH and FH–TAP agreement. Nasal cavity IPs are less likely to exhibit bony CT changes. Lower recurrence was associated with smaller size and fellowship training but not multiple TAPs, revision, FH absence, or FH–TAP discordance. Level of Evidence: 3 Laryngoscope, 134:1591–1596, 2024 [ABSTRACT FROM AUTHOR]