Objective The aim of this study was to evaluate the validity of a semiautomated volumetric approach (5DCNS+) for the detailed assessment of the fetal brain in a clinical setting. Methods Stored 3D volumes of > 1100 consecutive 2nd and 3rd trimester pregnancies (range 15-36 gestational weeks) were analyzed using a workflow-based volumetric approach 5DCNS+, enabling semiautomated reconstruction of diagnostic planes of the fetal central nervous system (CNS). All 3D data sets were examined for plane accuracy, the need for manual adjustment, and fetal-maternal characteristics affecting successful plane reconstruction. We also examined the potential of these standardized views to give additional information on proper gyration and sulci formation with advancing gestation. Results Based on our data, we were able to show that gestational age with an OR of 1.085 (95% CI 1.041-1.132) and maternal BMI with an OR of 1.022 (95% CI 1.041-1.054) only had a slight impact on the number of manual adjustments needed to reconstruct the complete volume, while maternal age and fetal position during acquisition (p = 0.260) did not have a significant effect. For the vast majority (958/1019; 94%) of volumes, using 5DCNS+ resulted in proper reconstruction of all nine diagnostic planes. In less than 1% (89/9171 planes) of volumes, the program failed to give sufficient information. 5DCNS+ was able to show the onset and changing appearance of CNS folding in a detailed and timely manner (lateral/parietooccipital sulcus formation seen in < 65% at 16-17 gestational weeks vs. 94.6% at 19 weeks). Conclusions The 5DCNS+ method provides a reliable algorithm to produce detailed, 3D volume-based assessments of fetal CNS integrity through a standardized reconstruction of the orthogonal diagnostic planes. The method further gives valid and reproducible information regarding ongoing cortical development retrieved from these volume sets that might aid in earlier in utero recognition of subtle structural CNS anomalies.

The long-awaited progress in digitalisation is generating huge amounts of medical data every day, and manual analysis and targeted, patient-oriented evaluation of this data is becoming increasingly difficult or even infeasible. This state of affairs and the associated, increasingly complex requirements for individualised precision medicine underline the need for modern software solutions and algorithms across the entire healthcare system. The utilisation of state-of-the-art equipment and techniques in almost all areas of medicine over the past few years has now indeed enabled automation processes to enter – at least in part – into routine clinical practice. Such systems utilise a wide variety of artificial intelligence (AI) techniques, the majority of which have been developed to optimise medical image reconstruction, noise reduction, quality assurance, triage, segmentation, computer-aided detection and classification and, as an emerging field of research, radiogenomics. Tasks handled by AI are completed significantly faster and more precisely, clearly demonstrated by now in the annual findings of the ImageNet Large-Scale Visual Recognition Challenge (ILSVCR), first conducted in 2015, with error rates well below those of humans. This review article will discuss the potential capabilities and currently available applications of AI in gynaecological-obstetric diagnostics. The article will focus, in particular, on automated techniques in prenatal sonographic diagnostics.

(1) Objective: To scrutinize the reliability and the clinical value of routinely used fetal intelligent navigation echocardiography (FINE) static mode (5DHeartStatic™) for accelerated semiautomatic volumetric assessment of the normal fetal heart. (2) Methods: In this study, a total of 296 second and third trimester fetuses were examined by targeted ultrasound. Spatiotemporal image correlation (STIC) volumes of the fetal heart were acquired for further volumetric assessment. In addition, all fetal hearts were scanned by a fast acquisition time volume (1 s). The volumes were analyzed using the FINE software. The data were investigated regarding the number of properly reconstructed planes and cardiac axis. (3) Results: A total of 257 volumes were included for final analysis. The mean gestational age (GA) was 23.9 weeks (14.3 to 37.7 weeks). In 96.9 (standard acquisition time, FINE standard mode) and 94.2% (fast acquisition time, FINE static mode) at least seven planes were reconstructed properly (p = 0.0961, not significant). Regarding the overall depiction rate, the standard mode was able to reconstruct 96.9% of the planes properly, whereas the static mode showed 95.2% of the planes (p = 0.0098). Moreover, there was no significant difference between the automatic measurement of the cardiac axis (37.95 + 9.14 vs. 38.00 + 8.92 degrees, p = 0.8827, not significant). (4) Conclusions: Based on our results, the FINE static mode technique is a reliable method. It provides similar information of the cardiac anatomy compared to conventional STIC volumes assessed by the FINE method. The FINE static mode has the potential to minimize the influence of motion artifacts during volume acquisition and might therefore be helpful concerning volumetric cardiac assessment in daily routine.

No abstract