Spatial Compounding of 3-D Fetal Brain Ultrasound Using Probabilistic Maps

A Clinical Approach to Semiautomated Three-Dimensional Fetal Brain Biometry-Comparing the Strengths and Weaknesses of Two Diagnostic Tools: 5DCNS+TM and SonoCNSTM

(1) Objective: We aimed to evaluate the accuracy and efficacy of AI-assisted biometric measurements of the fetal central nervous system (CNS) by comparing two semiautomatic postprocessing tools. We further aimed to discuss the additional value of semiautomatically generated sagittal and coronal planes of the CNS. (2) Methods: Three-dimensional (3D) volumes were analyzed with two semiautomatic software tools, 5DCNS+™ and SonoCNS™. The application of 5DCNS+™ results in nine planes (axial, coronal and sagittal) displayed in a single template; SonoCNS™ depicts three axial cutting sections. The tools were compared regarding automatic biometric measurement accuracy. (3) Results: A total of 129 fetuses were included for final analysis. Our data indicate that, in terms of the biometric quantification of head circumference (HC), biparietal diameter (BPD), transcerebellar diameter (TCD) and cisterna magna (CM), the accuracy of SonoCNS™ was higher with respect to the manual measurement of an experienced examiner compared to 5DCNS+™, whereas it was the other way around regarding the diameter of the posterior horn of the lateral ventricle (Vp). The inclusion of four orthogonal coronal views in 5DCNS+™ gives valuable information regarding spatial arrangements, particularly of midline structures. (4) Conclusions: Both tools were able to ease assessment of the intracranial anatomy, highlighting the additional value of automated algorithms in clinical use. SonoCNS™ showed a superior accuracy of plane reconstruction and biometry, but volume reconstruction using 5DCNS+™ provided more detailed information, which is needed for an entire neurosonogram as suggested by international guidelines.

Feasibility of Fetal Proximal Lateral Cerebral Ventricle Measurement

OBJECTIVES

Measuring the posterior horn of the lateral ventricle in the fetus during ultrasound scans may be challenging. We aimed to examine this measurement feasibility, in relation to gestational age.

METHODS

A cross-sectional study was conducted, including nonanomalous fetuses, in which both lateral ventricles measured less than 10 mm during anomaly scans. The measurements were performed according to the International Society of Ultrasound in Obstetrics and Gynecology guidelines. Success rate of measuring both ventricles was assessed at different gestational ages. Association between lateral ventricle width with contralateral ventricle width, gender, gestational age, and fetal head position were assessed.

RESULTS

A total of 156 cases were recruited. The lateral ventricle distal to the probe was measured in all cases. In 10 cases proximal lateral ventricle could not be adequately measured (failed proximal ventricle measurement group). In 146 scans both ventricle measurements were available. All 10 cases of failed proximal ventricle measurement were in third trimester (30-38 weeks). Success rate of measurement of both ventricles was 100%, 96.2%, 71.4%, and 37.5% for gestational week 14-29, 30-32, 33-35, and 36-38, respectively (P <.001). Proximal lateral ventricle width was strongly associated with the distal ventricle width (B = 0.422, 95% confidence interval 0.29, 0.555, P <.001), but not with head position, fetal gender, or gestational age.

CONCLUSIONS

Measurement of the proximal lateral ventricle is feasible in most cases, even during late third trimester scans. Efforts should be made to visualize both ventricles in every evaluation of the fetal brain.

Applicability of a semiautomated volumetric approach (5D CNS+™) for detailed antenatal reconstruction of abnormal fetal CNS anatomy

BACKGROUND

The aim of this study was to evaluate the accuracy and reliability of a semiautomated volumetric approach (5D CNS+™) when examining fetuses with an apparent abnormal anatomy of the central nervous system (CNS).

METHODS

Stored 3D volumes extracted from a cohort of > 1.400 consecutive 2nd and 3rd trimester pregnancies (range 15-36 gestational weeks) were analyzed using the semiautomatic software tool 5D CNS+™, enabling detailed reconstruction of nine diagnostic planes of the fetal brain. All 3D data sets were examined and judged for plane accuracy, the need for manual adjustment, and fetal CNS anomalies affecting successful plane reconstruction.

RESULTS

Based on our data of 91 fetuses with structural cerebral anomalies, we were able to reveal details of a wide range of CNS anomalies with application of the 5D CNS+™ technique. The corresponding anatomical features and consecutive changes of neighboring structures could be clearly demonstrated. Thus, a profound assessment of the entire altered CNS anatomy could be achieved in nearly all cases. The comparison with matched controls showed a significant difference in volume acquisition (p < 0.001) and in need for manual adjustment (p < 0.001) but not in the drop-out rates (p = 0.677) of both groups.

CONCLUSION

5D CNS+™ is applicable in the majority of cases with brain lesions and constitutes a reliable tool even if the integrity of the fetal CNS is compromised by structural anomalies. Using volume data that were acquired in identical cutting sections needed for conventional biometry allows for detailed anatomic surveys grossly independent of the examiner's experience.

A review of image processing methods for fetal head and brain analysis in ultrasound images

BACKGROUND AND OBJECTIVE

Examination of head shape and brain during the fetal period is paramount to evaluate head growth, predict neurodevelopment, and to diagnose fetal abnormalities. Prenatal ultrasound is the most used imaging modality to perform this evaluation. However, manual interpretation of these images is challenging and thus, image processing methods to aid this task have been proposed in the literature. This article aims to present a review of these state-of-the-art methods.

METHODS

In this work, it is intended to analyze and categorize the different image processing methods to evaluate fetal head and brain in ultrasound imaging. For that, a total of 109 articles published since 2010 were analyzed. Different applications are covered in this review, namely analysis of head shape and inner structures of the brain, standard clinical planes identification, fetal development analysis, and methods for image processing enhancement.

RESULTS

For each application, the reviewed techniques are categorized according to their theoretical approach, and the more suitable image processing methods to accurately analyze the head and brain are identified. Furthermore, future research needs are discussed. Finally, topics whose research is lacking in the literature are outlined, along with new fields of applications.

CONCLUSIONS

A multitude of image processing methods has been proposed for fetal head and brain analysis. Summarily, techniques from different categories showed their potential to improve clinical practice. Nevertheless, further research must be conducted to potentiate the current methods, especially for 3D imaging analysis and acquisition and for abnormality detection.

Probabilistic Learning Coherent Point Drift for 3D Ultrasound Fetal Head Registration

Quantification of brain growth is crucial for the assessment of fetal well being, for which ultrasound (US) images are the chosen clinical modality. However, they present artefacts, such as acoustic occlusion, especially after the 18^th gestational week, when cranial calcification appears. Fetal US volume registration is useful in one or all of the following cases: to monitor the evolution of fetometry indicators, to segment different structures using a fetal brain atlas, and to align and combine multiple fetal brain acquisitions. This paper presents a new approach for automatic registration of real 3D US fetal brain volumes, volumes that contain a considerable degree of occlusion artefacts, noise, and missing data. To achieve this, a novel variant of the coherent point drift method is proposed. This work employs supervised learning to segment and conform a point cloud automatically and to estimate their subsequent weight factors. These factors are obtained by a random forest-based classification and are used to appropriately assign nonuniform membership probability values of a Gaussian mixture model. These characteristics allow for the automatic registration of 3D US fetal brain volumes with occlusions and multiplicative noise, without needing an initial point cloud. Compared to other intensity and geometry-based algorithms, the proposed method achieves an error reduction of 7.4% to 60.7%, with a target registration error of only 6.38 ± 3.24 mm. This makes the herein proposed approach highly suitable for 3D automatic registration of fetal head US volumes, an approach which can be useful to monitor fetal growth, segment several brain structures, or even compound multiple acquisitions taken from different projections.