Severe hemolysis, elevated liver enzymes, and low platelet syndrome requiring differentiation of thrombotic microangiopathy: Four cases from a nationwide survey in Japan.

Severe cases of hemolysis, elevated liver enzymes, and low platelet (HELLP) syndrome requiring plasma exchange or dialysis should be differentiated from other thrombotic microangiopathy (TMA) and treated appropriately. To evaluate the prevalence and clinical characteristics of such cases in Japan, a questionnaire-based survey was conducted among obstetricians who are members of the Perinatal Research Network Group in Japan. There were a total of 335 cases of HELLP syndrome over a 3-year period in the 48 facilities that responded to the survey. Four patients required plasma exchange or dialysis, of which two were diagnosed with atypical hemolytic uremic syndrome and two with TMA secondary to systemic lupus erythematosus. Although such severe HELLP syndrome is rare, identifying the clinical features and making accurate differential diagnosis are critical for optimal clinical outcomes for mothers and neonates.

Fetal Cerebellar Growth Curves Based on Biomathematics in Normally Developing Japanese Fetuses and Fetuses with Trisomy 18.

We used biomathematics to describe and compare cerebellar growth in normally developing and trisomy 18 Japanese fetuses. This retrospective study included 407 singleton pregnancies with fetuses at 14-39 weeks of gestation and 33 fetuses with trisomy 18 at 17-35 weeks. We used ultrasonography to measure fetal transverse cerebellar diameter (TCD) and anteroposterior cerebellar diameter (APCD). We hypothesized that cerebellar growth is proportional to cerebellar length at any given time point. We determined the formula L(t) ≒Keat+r, where e is Napier's number, t is time, L is cerebellar length, and a, K, and r are constants. We then obtained regression functions for each TCD and APCD in all fetuses. The regression equations for TCD and APCD values in normal fetuses, expressed as exponential functions, were TCD(t)=27.85e0.02788t-28.62 (mm) (adjusted R2=0.997), and APCD(t)=324.29e0.00286t-322.62 (mm) (adjusted R2=0.995). These functions indicated that TCD and APCD grew at constant rates of 2.788%/week and 0.286%/week, respectively, throughout gestation. TCD (0.0153%/week) and APCD (0.000430%/week) grew more slowly in trisomy 18 fetuses. This study demonstrates the potential of biomathematics in clinical research and may aid in biological understanding of fetal cerebellar growth.

Medical Professional Enhancement Using Explainable Artificial Intelligence in Fetal Cardiac Ultrasound Screening.

Diagnostic support tools based on artificial intelligence (AI) have exhibited high performance in various medical fields. However, their clinical application remains challenging because of the lack of explanatory power in AI decisions (black box problem), making it difficult to build trust with medical professionals. Nevertheless, visualizing the internal representation of deep neural networks will increase explanatory power and improve the confidence of medical professionals in AI decisions. We propose a novel deep learning-based explainable representation "graph chart diagram" to support fetal cardiac ultrasound screening, which has low detection rates of congenital heart diseases due to the difficulty in mastering the technique. Screening performance improves using this representation from 0.966 to 0.975 for experts, 0.829 to 0.890 for fellows, and 0.616 to 0.748 for residents in the arithmetic mean of area under the curve of a receiver operating characteristic curve. This is the first demonstration wherein examiners used deep learning-based explainable representation to improve the performance of fetal cardiac ultrasound screening, highlighting the potential of explainable AI to augment examiner capabilities.

Model-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos.

The application of segmentation methods to medical imaging has the potential to create novel diagnostic support models. With respect to fetal ultrasound, the thoracic wall is a key structure on the assessment of the chest region for examiners to recognize the relative orientation and size of structures inside the thorax, which are critical components in neonatal prognosis. In this study, to improve the segmentation performance of the thoracic wall in fetal ultrasound videos, we proposed a novel model-agnostic method using deep learning techniques: the Multi-Frame + Cylinder method (MFCY). The Multi-frame method (MF) uses time-series information of ultrasound videos, and the Cylinder method (CY) utilizes the shape of the thoracic wall. To evaluate the achieved improvement, we performed segmentation using five-fold cross-validation on 538 ultrasound frames in the four-chamber view (4CV) of 256 normal cases using U-net and DeepLabv3+. MFCY increased the mean values of the intersection over union (IoU) of thoracic wall segmentation from 0.448 to 0.493 for U-net and from 0.417 to 0.470 for DeepLabv3+. These results demonstrated that MFCY improved the segmentation performance of the thoracic wall in fetal ultrasound videos without altering the network structure. MFCY is expected to facilitate the development of diagnostic support models in fetal ultrasound by providing further accurate segmentation of the thoracic wall.

Image Segmentation of the Ventricular Septum in Fetal Cardiac Ultrasound Videos Based on Deep Learning Using Time-Series Information.

Image segmentation is the pixel-by-pixel detection of objects, which is the most challenging but informative in the fundamental tasks of machine learning including image classification and object detection. Pixel-by-pixel segmentation is required to apply machine learning to support fetal cardiac ultrasound screening; we have to detect cardiac substructures precisely which are small and change shapes dynamically with fetal heartbeats, such as the ventricular septum. This task is difficult for general segmentation methods such as DeepLab v3+, and U-net. Hence, here we proposed a novel segmentation method named Cropping-Segmentation-Calibration (CSC) that is specific to the ventricular septum in ultrasound videos in this study. CSC employs the time-series information of videos and specific section information to calibrate the output of U-net. The actual sections of the ventricular septum were annotated in 615 frames from 421 normal fetal cardiac ultrasound videos of 211 pregnant women who were screened. The dataset was assigned a ratio of 2:1, which corresponded to a ratio of the training to test data, and three-fold cross-validation was conducted. The segmentation results of DeepLab v3+, U-net, and CSC were evaluated using the values of the mean intersection over union (mIoU), which were 0.0224, 0.1519, and 0.5543, respectively. The results reveal the superior performance of CSC.

Proline might have been the first amino acid in the primitive genetic code.

Stereochemical assignment of amino acids and corresponding codons or anticodons has not been successful so far. Here, we focused on proline and GGG (anticodon of tRNA(Pro)) and investigated their mutual interaction. Circular dichroism spectroscopy revealed that guanosine nucleotides (GG, GGG) formed G-quartet structures. The structures were destroyed by adding high concentrations of proline. We propose that the possibility of the reversible proline/G-quartet interaction could have contributed to the specific assignment of proline on GGG and that this coding could have been the first in the genetic code.