Despite that deep learning has achieved state-of-the-art performance for automatic medical image segmentation, it often requires a large amount of pixel-level manual annotations for training. Obtaining these high-quality annotations is time-consuming and requires specialized knowledge, which hinders the widespread application that relies on such annotations to train a model with good segmentation performance. Using scribble annotations can substantially reduce the annotation cost, but often leads to poor segmentation performance due to insufficient supervision. In this work, we propose a novel framework named as ScribSD+ that is based on multi-scale knowledge distillation and class-wise contrastive regularization for learning from scribble annotations. For a student network supervised by scribbles and the teacher based on Exponential Moving Average (EMA), we first introduce multi-scale prediction-level Knowledge Distillation (KD) that leverages soft predictions of the teacher network to supervise the student at multiple scales, and then propose class-wise contrastive regularization which encourages feature similarity within the same class and dissimilarity across different classes, thereby effectively improving the segmentation performance of the student network. Experimental results on the ACDC dataset for heart structure segmentation and a fetal MRI dataset for placenta and fetal brain segmentation demonstrate that our method significantly improves the student\'s performance and outperforms five state-of-the-art scribble-supervised learning methods. Consequently, the method has a potential for reducing the annotation cost in developing deep learning models for clinical diagnosis.

BACKGROUND: According to prenatal ultrasonographic studies, single umbilical artery may be present alone or in association with other fetal abnormalities. So far, the exact pathogenesis of bladder exstrophy is unclear. Some scholars believe that bladder exstrophy and cloacal exstrophy should be regarded as a disease spectrum to explore their pathogenesis. If bladder exstrophy and cloacal exstrophy are regarded as the same disease spectrum, then we can speculate that the single umbilical artery should have the probability of being accompanied by bladder exstrophy at the same time.
METHODS: For the first time, we report a rare case of fetal bladder exstrophy with single umbilical artery in single pregnancy. This patient underwent targeted color Doppler ultrasound at 26 weeks of pregnancy which first suspected bladder exstrophy with single umbilical artery and fetal MRI for diagnosis at 38 + 3 weeks of pregnancy which confirmed the suspicion. After the diagnosis was confirmed, the patient was scheduled for a multidisciplinary discussion. Ultimately the patient opted for induced fetal demise at 38 + 5 weeks of pregnancy and the physical appearance of the fetal demise affirmed previous ultrasound and MRI examination results.
CONCLUSIONS: Our report is the first finding of single umbilical artery combined with bladder exstrophy in a singleton pregnancy. Accordingly, our case enhances the evidence that cloacal exstrophy and bladder exstrophy should be treated as the same disease spectrum. In addition, we conducted a literature review on the diagnostic progress of single umbilical artery combined with bladder exstrophy, hoping to provide useful references for the diagnosis of this disease.

BACKGROUND: Fetal brain magnetic resonance imaging (MRI)-based gestational age prediction has been widely used to characterize normal fetal brain development and diagnose congenital brain malformations.
OBJECTIVE: The uncertainty of fetal position and external interference leads to variable localization and direction of the fetal brain. In addition, pregnant women typically concentrate on receiving MRI scans during the fetal anomaly scanning week, leading to an imbalanced distribution of fetal brain MRI data. The above-mentioned problems pose great challenges for deep learning-based fetal brain MRI gestational age prediction.
METHODS: In this study, a pyramid squeeze attention (PSA)-guided dynamic feature fusion CNN (PDFF-CNN) is proposed to robustly predict gestational ages from fetal brain MRI images on an imbalanced dataset. PDFF-CNN contains four components: transformation module, feature extraction module, dynamic feature fusion module, and balanced mean square error (MSE) loss. The transformation and feature extraction modules are employed by using the PSA to learn multiscale and multi-orientation feature representations in a parallel weight-sharing Siamese network. The dynamic feature fusion module automatically learns the weights of feature vectors generated in the feature extraction module to dynamically fuse multiscale and multi-orientation brain sulci and gyri features. Considering the fact of the imbalanced dataset, the balanced MSE loss is used to mitigate the negative impact of imbalanced data distribution on gestational age prediction performance.
RESULTS: Evaluated on an imbalanced fetal brain MRI dataset of 1327 routine clinical T2-weighted MRI images from 157 subjects, PDFF-CNN achieved promising gestational age prediction performance with an overall mean absolute error of 0.848 weeks and an R 2 $R^2$ of 0.904. Furthermore, the attention activation maps of PDFF-CNN were derived, which revealed regional features that contributed to gestational age prediction at each gestational stage.
CONCLUSIONS: These results suggest that the proposed PDFF-CNN might have broad clinical applicability in guiding treatment interventions and delivery planning, which has the potential to be helpful with prenatal diagnosis.

Fetal brain tissue segmentation is essential for quantifying the presence of congenital disorders in the developing fetus. Manual segmentation of fetal brain tissue is cumbersome and time-consuming, so using an automatic segmentation method can greatly simplify the process. In addition, the fetal brain undergoes a variety of changes throughout pregnancy, such as increased brain volume, neuronal migration, and synaptogenesis. In this case, the contrast between tissues, especially between gray matter and white matter, constantly changes throughout pregnancy, increasing the complexity and difficulty of our segmentation. To reduce the burden of manual refinement of segmentation, we proposed a new deep learning-based segmentation method. Our approach utilized a novel attentional structural block, the contextual transformer block (CoT-Block), which was applied in the backbone network model of the encoder-decoder to guide the learning of dynamic attentional matrices and enhance image feature extraction. Additionally, in the last layer of the decoder, we introduced a hybrid dilated convolution module, which can expand the receptive field and retain detailed spatial information, effectively extracting the global contextual information in fetal brain MRI. We quantitatively evaluated our method according to several performance measures: dice, precision, sensitivity, and specificity. In 80 fetal brain MRI scans with gestational ages ranging from 20 to 35 weeks, we obtained an average Dice similarity coefficient (DSC) of 83.79%, an average Volume Similarity (VS) of 84.84%, and an average Hausdorff95 Distance (HD95) of 35.66 mm. We also used several advanced deep learning segmentation models for comparison under equivalent conditions, and the results showed that our method was superior to other methods and exhibited an excellent segmentation performance.

Brain extraction is a fundamental prerequisite step in neuroimage analysis for fetus. Due to surrounding maternal tissues and unpredictable movement, brain extraction from fetal Magnetic Resonance (MR) images is a challenging task. In this paper, we propose a novel deep learning-based multi-step framework for brain extraction from 3D fetal MR images. In the first step, a global localization network is applied to estimate probability maps for brain candidates. Connected-component labeling algorithm is applied to eliminate small erroneous components and accurately locate the candidate brain area. In the second step, a local refinement network is implemented in the brain candidate area to obtain fine-grained probability maps. Final extraction results are derived by a fusion network with the two cascaded probability maps obtained from previous two steps. Experimental results demonstrate that our proposed method has superior performance compared with existing deep learning-based methods.

Meconium peritonitis (MP) is a rare fetal disease that needs to be urgently identified for surgical intervention. We report a series of 35 patients diagnosed prenatally with MP by magnetic resonance imaging (MRI), illustrate the imaging findings and investigate the predictive value of these findings for postpartum management.
A consecutive cohort of patients diagnosed with MP who were born at our institution from 2013 to 2018 was enrolled retrospectively. The prenatal ultrasound and MRI findings were analyzed. Fisher\'s exact probability test was used to evaluate the predictive value of MRI for surgical intervention between the operative group and the nonoperative group.
Ascites (30/35) and distended bowel loops (27/35) were two of the most common prenatal MP-related findings on fetal MRI. Of the 35 infants, 26 received surgical intervention. All fetuses with MRI scans showing bowel dilatation (14/26, p = 0.048) and micro-colorectum (13/26, p = 0.013) required surgery. There were no significant differences in the number of fetuses with meconium pseudocysts and peritoneal calcifications between the two groups.
Fetuses with bowel dilatation and micro-colorectum on MRI may need postpartum surgical intervention. Infants with only a small amount of ascites and slight bowel distention were likely to receive conservative treatment.

High-resolution volume reconstruction from multiple motion-corrupted stacks of 2D slices plays an increasing role for fetal brain Magnetic Resonance Imaging (MRI) studies. Currently existing reconstruction methods are time-consuming and often require user interactions to localize and extract the brain from several stacks of 2D slices. We propose a fully automatic framework for fetal brain reconstruction that consists of four stages: 1) fetal brain localization based on a coarse segmentation by a Convolutional Neural Network (CNN), 2) fine segmentation by another CNN trained with a multi-scale loss function, 3) novel, single-parameter outlier-robust super-resolution reconstruction, and 4) fast and automatic high-resolution visualization in standard anatomical space suitable for pathological brains. We validated our framework with images from fetuses with normal brains and with variable degrees of ventriculomegaly associated with open spina bifida, a congenital malformation affecting also the brain. Experiments show that each step of our proposed pipeline outperforms state-of-the-art methods in both segmentation and reconstruction comparisons including expert-reader quality assessments. The reconstruction results of our proposed method compare favorably with those obtained by manual, labor-intensive brain segmentation, which unlocks the potential use of automatic fetal brain reconstruction studies in clinical practice.

To assess the accuracy of prenatal diagnosis and the prognosis of fetal-abdominal masses, we reviewed all of the cases which had been diagnosed as having abdominal masses from January 2014 to December 2016. In total, 264 cases were identified as having abdominal masses. Among them, 141 cases (53%) had received specific prenatal diagnoses by prenatal ultrasound (US). MRI had assisted in the diagnosis and prognostic evaluation in 69 cases, increasing the diagnostic rate to 65%. The prenatal diagnoses of 111 cases (65%) were concordant with the postnatal diagnoses. Surgical intervention after birth was needed in 96 cases (39%). Most outcomes were good (89%). We suggest that prenatal US can detect and identify most fetal abdominal masses and that MRI helps to further describe the masses. With early intervention after birth, the prognosis was good in most cases. Impact Statement What is already known on this subject? Fetal-abdominal masses are commonly detected in antenatal examinations. A prenatal ultrasound is the main screening tool for detecting fetal intra-abdominal cystic lesions. What the results of this study add? We suggest that MRI is more helpful in some systems to reveal locations and structures. Even prenatal diagnosis cannot reach before birth, prognosis is quite good and expectant therapy is sufficient. What the implications are of these findings for clinical practice and/or future research? Our data strengthens the current knowledge of fetal abdominal masses to help relieve anxious parents by telling them that this congenital malformation has good outcomes. But multidiscipline consultation is necessary.

To present three fetal vein of Galen aneurysmal malformations (VGAMs), which were diagnosed through magnetic resonance imaging (MRI), and highlight these cardiovascular findings.
We retrospectively reviewed three fetuses with VGAM at 31, 32, and 33 weeks of gestation. Feeding arteries and draining veins were observed by MRI. Secondary changes in the brain and high-output heart failure caused by high blood flow in the lesion were evaluated. Two fetuses were born, and neonatal MRI was performed. One fetus was terminated.
A characteristic dilated structure in the midline of the brain presented in each fetus. The arteriovenous fistula led to anatomical brain changes such as in the hydrocephalus, dilated feeding vessels (one or more), jugular vein, and/or superior vena cava. Substantial brachiocephalic vessel dilation was observed in two fetuses. Following parturition, one baby had neonatal asphyxia and sinus thrombosis, and MRI revealed hypoxic-ischemic encephalopathy. Cardiomegaly was detected in all three cases.
With a large field of view, fetal MRI can observe brain VGAM, as well as the heart and affected large vessels. It can determine hydrocephalus, ischemia, intracranial hemorrhage, and sinus thrombosis. Providing such information on the infant\'s entire body can aid clinicians in determining the most appropriate treatment.
4 J. Magn. Reson. Imaging 2017;46:1535-1539.

During the second trimester, the human fetal brain undergoes numerous changes that lead to substantial variation in the neonatal in terms of its morphology and tissue types. As fetal MRI is more and more widely used for studying the human brain development during this period, a spatiotemporal atlas becomes necessary for characterizing the dynamic structural changes. In this study, 34 postmortem human fetal brains with gestational ages ranging from 15 to 22 weeks were scanned using 7.0 T MR. We used automated morphometrics, tensor-based morphometry and surface modeling techniques to analyze the data. Spatiotemporal atlases of each week and the overall atlas covering the whole period with high resolution and contrast were created. These atlases were used for the analysis of age-specific shape changes during this period, including development of the cerebral wall, lateral ventricles, Sylvian fissure, and growth direction based on local surface measurements. Our findings indicate that growth of the subplate zone is especially striking and is the main cause for the lamination pattern changes. Changes in the cortex around Sylvian fissure demonstrate that cortical growth may be one of the mechanisms for gyration. Surface deformation mapping, revealed by local shape analysis, indicates that there is global anterior-posterior growth pattern, with frontal and temporal lobes developing relatively quickly during this period. Our results are valuable for understanding the normal brain development trajectories and anatomical characteristics. These week-by-week fetal brain atlases can be used as reference in in vivo studies, and may facilitate the quantification of fetal brain development across space and time.