How Automated Techniques Ease Functional Assessment of the Fetal Heart: Applicability of MPI+™ for Direct Quantification of the Modified Myocardial Performance Index.

(1) Objectives: In utero functional cardiac assessments using echocardiography have become increasingly important. The myocardial performance index (MPI, Tei index) is currently used to evaluate fetal cardiac anatomy, hemodynamics and function. An ultrasound examination is highly examiner-dependent, and training is of enormous significance in terms of proper application and subsequent interpretation. Future experts will progressively be guided by applications of artificial intelligence, on whose algorithms prenatal diagnostics will rely on increasingly. The objective of this study was to demonstrate the feasibility of whether less experienced operators might benefit from an automated tool of MPI quantification in the clinical routine. (2) Methods: In this study, a total of 85 unselected, normal, singleton, second- and third-trimester fetuses with normofrequent heart rates were examined by a targeted ultrasound. The modified right ventricular MPI (RV-Mod-MPI) was measured, both by a beginner and an expert. A calculation was performed semiautomatically using a Samsung Hera W10 ultrasound system (MPI+™, Samsung Healthcare, Gangwon-do, South Korea) by taking separate recordings of the right ventricle's in- and outflow using a conventional pulsed-wave Doppler. The measured RV-Mod-MPI values were assigned to gestational age. The data were compared between the beginner and the expert using a Bland-Altman plot to test the agreement between both operators, and the intraclass correlation was calculated. (3) Results: The mean maternal age was 32 years (19 to 42 years), and the mean maternal pre-pregnancy body mass index was 24.85 kg/m2 (ranging from 17.11 to 44.08 kg/m2). The mean gestational age was 24.44 weeks (ranging from 19.29 to 36.43 weeks). The averaged RV-Mod-MPI value of the beginner was 0.513 ± 0.09, and that of the expert was 0.501 ± 0.08. Between the beginner and the expert, the measured RV-Mod-MPI values indicated a similar distribution. The statistical analysis showed a Bland-Altman bias of 0.01136 (95% limits of agreement from -0.1674 to 0.1902). The intraclass correlation coefficient was 0.624 (95% confidence interval from 0.423 to 0.755). (4) Conclusions: For experts as well as for beginners, the RV-Mod-MPI is an excellent diagnostic tool for the assessment of fetal cardiac function. It is a time-saving procedure, offers an intuitive user interface and is easy to learn. There is no additional effort required to measure the RV-Mod-MPI. In times of reduced resources, such assisted systems of fast value acquisition represent clear added value. The establishment of the automated measurement of the RV-Mod-MPI in clinical routine should be the next level in cardiac function assessment.

Maximal Reduction of STIC Acquisition Time for Volumetric Assessment of the Fetal Heart-Benefits and Limitations of Semiautomatic Fetal Intelligent Navigation Echocardiography (FINE) Static Mode.

(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.

Semiautomatic Assessment of Fetal Fractional Limb Volume for Weight Prediction in Clinical Praxis: How Does It Perform in Routine Use?

OBJECTIVES: Semiautomatic fractional limb volume (FLV) models have recently produced promising results for fetal birth weight (BW) estimation. We tested those models in a more unselected population hypothesizing that the FLV models would improve accuracy and precision of fetal BW estimation compared to the Hadlock model. METHODS: We compared the performance of different BW prediction models: Hadlock (biparietal diameter [BPD], abdominal circumference (AC), femur diaphysis length) and modified Lee thigh volume (TVol) and arm volume (AVol) (BPD, AC, automated fractional TVol, and AVol). Accuracy (systematic errors, mean percent differences) and precision (random errors, ± 1 SD of percent differences) were calculated. RESULTS: A total of 75 fetuses were included for final analysis. The Hadlock model showed the most consistent results with accurate BW estimation not significantly different from zero (-0.37 ± 8.53%). The modified fractional thigh and arm volume models were less accurate but trended toward more precise results (-2.63 ± 7.69% and -3.85 ± 7.47%, respectively). In addition, the modified TVol model showed the trend to predict more BWs within ±10% of the actual BW compared to the Hadlock model (81.3 versus 74.67%, ns). CONCLUSIONS: Based on our results, fetal weight estimation using the modified semiautomatic FLV models generates less accurate results in third-trimester fetuses compared to the Hadlock model. Those models recently published might improve the results of BW prediction by showing a higher precision than conventional models, especially in small and large fetuses. Further studies are needed to investigate the clinical usefulness of the new models.

The Use of Artificial Intelligence in Automation in the Fields of Gynaecology and Obstetrics - an Assessment of the State of Play.

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.

Fetal intra-abdominal tumors: assessment of spectrum, accuracy of prenatal diagnosis, perinatal outcome and therapy at a tertiary referral center.

OBJECTIVE: To describe the varieties and ultrasound characteristics of prenatally diagnosed fetal abdominal tumors and to scrutinize the accuracy of prenatal diagnosis as well as the postnatal outcome and therapy of affected pregnancies. STUDY DESIGN: Retrospective study of 354 fetuses found to have abdominal tumors on prenatal sonogram, identified from 1993 to 2009 at a tertiary referral center for prenatal medicine. The cohort was classified into subgroups according to the sonographic appearance of the fetal tumor and the affected anatomic structure (urinary, gastrointestinal and genital tracts and other locations). Sensitivity, specificity, positive predictive value and false-positive rate of ultrasonography in identifying the system of origin were calculated. Relationships between relevant outcome domains and the different subgroups were assessed using the chi-square test and Fisher's exact test. RESULTS: Our cohort comprised 222 urinary tract lesions, 37 genital tract lesions, 80 gastrointestinal lesions and 15 tumors of other origins. The mean gestational age at diagnosis was 26+0 wks. The prenatally established diagnosis was exactly concordant with postnatal findings in 88.9%. Sensitivity, specificity, positive predictive value and false-positive rate of ultrasonography in identifying the system of origin (urinary, gastrointestinal, genital tracts and other locations) were 98.3%, 97.6%, 92.6% and 2.4%, respectively. The favorable postnatal outcome rate was highest among fetuses with genital tract lesions (95%) and lowest among those with tumors of the urinary tract (62%, p=<0.001). Twenty per cent of tumors regressed spontaneously, mostly gastrointestinal tumors (36%, p=<0.001). In 75/354 cases (21%) the parents opted to terminate the pregnancy: intra-uterine fetal demise and neonatal death were each noted in 4%. Prenatal therapy was performed in 24 of 354 cases (7%) and postnatal surgery in 64 cases (18%). CONCLUSION: The majority of fetal abdominal anomalies were accurately diagnosed and the vast majority of affected fetuses had a favorable outcome, some tumors even resolved with advancing pregnancy. Pre- and post-natal invasive surgical interventions were mandatory in only a small number of cases.

Fetal micrognathia: objective assessment and associated anomalies on prenatal sonogram.

OBJECTIVE: To determine the accuracy and characteristics of prenatally detected fetal micrognathia. METHODS: A retrospective analysis of all pregnancies with the suspicion of fetal micrognathia was performed. The affected fetuses were reassessed by estimation of the inferior facial angle (IFA) and the frontal nasomental angle on stored gray scale images to objectively establish the diagnosis. RESULTS: Of the 28.935 ultrasounds (USs) reviewed, 58 cases were eligible and 4 were excluded because of inconclusive data. The mean values for IFA and frontal nasomental angle were 44.8° and 123.3°, respectively. In 33 cases, the pregnancy was terminated. Four fetuses died sub partu or immediately after birth, five were stillborn. Invasive testing in 40/54 cases revealed aneuploidies in 35%. Associated anomalies comprised musculoskeletal disorders (43%) and non-skeletal anomalies (15%). Less than one fifth (9/54) were alive beyond postnatal period. Four fetuses had an isolated micrognathia, one of which was found to have a cleft palate postnatally. CONCLUSION: The diagnosis of micrognathia has a crucial impact on both prenatal and postnatal outcomes of affected individuals due to its association with additional abnormalities. A detailed sonographic survey using objective criteria for defining micrognathia is mandatory. Once the diagnosis is confirmed, an intensive interdisciplinary counseling of the parents is needed.