Fetal MRI Analysis of Corpus Callosal Abnormalities: Classification, and Associated Anomalies.

BACKGROUND: Corpus callosal abnormalities (CCA) are midline developmental brain malformations and are usually associated with a wide spectrum of other neurological and non-neurological abnormalities. The study aims to highlight the diagnostic role of fetal MRI to characterize heterogeneous corpus callosal abnormalities using the latest classification system. It also helps to identify associated anomalies, which have prognostic implications for the postnatal outcome. METHODS: In this study, retrospective data from antenatal women who underwent fetal MRI between January 2014 and July 2023 at Rush University Medical Center were evaluated for CCA and classified based on structural morphology. Patients were further assessed for associated neurological and non-neurological anomalies. RESULTS: The most frequent class of CCA was complete agenesis (79.1%), followed by hypoplasia (12.5%), dysplasia (4.2%), and hypoplasia with dysplasia (4.2%). Among them, 17% had isolated CCA, while the majority (83%) had complex forms of CCA associated with other CNS and non-CNS anomalies. Out of the complex CCA cases, 58% were associated with other CNS anomalies, while 8% were associated with non-CNS anomalies. 17% of cases had both. CONCLUSION: The use of fetal MRI is valuable in the classification of abnormalities of the corpus callosum after the confirmation of a suspected diagnosis on prenatal ultrasound. This technique is an invaluable method for distinguishing between isolated and complex forms of CCA, especially in cases of apparent isolated CCA. The use of diffusion-weighted imaging or diffusion tensor imaging in fetal neuroimaging is expected to provide further insights into white matter abnormalities in fetuses diagnosed with CCA in the future.

Caudal regression syndrome type 1 with minimally invasive computed tomography and magnetic resonance imaging autopsy: a case report.

BACKGROUND: Caudal regression syndrome is a rare complex congenital anomaly with reduced penetrance and phenotypic variability characterized by osseous defects of the caudal spine, lower limb anomalies, and accompanying genitourinary, gastrointestinal/anorectal, and cardiac system soft tissue defects. We report a rare presentation of type 1 caudal regression syndrome in a pregnant woman with preexisting diabetes, in which early recognition of severe fetal anomalies on routine antenatal ultrasound facilitated confirmation with fetal magnetic resonance imaging to characterize extent of disease and prognosticate fetal outcome. CASE PRESENTATION: This case of type 1 caudal regression syndrome in the setting of maternal pregestational diabetes mellitus resulted in stillbirth. The mother was a 29-year-old Caucasian primigravida female with past medical history of poorly controlled type 2 diabetes managed with metformin prior to pregnancy, prompting admission for glucose management and initiation of insulin at 13 weeks. Baseline hemoglobin A1c was high at 8.0%. Fetal ultrasound at 22 weeks was notable for severe sacral agenesis, bilateral renal pelvis dilatation, single umbilical artery, and pulmonary hypoplasia. Fetal magnetic resonance imaging at 29 weeks showed absent lower two-thirds of the spine with corresponding spinal cord abnormality compatible with type 1 caudal regression syndrome. The mother delivered a male stillborn at 39 and 3/7 weeks. Minimally invasive postmortem magnetic resonance imaging and computed tomography autopsy were performed to confirm clinical findings when family declined conventional autopsy. Etiology of sacral agenesis was attributed to poorly controlled maternal diabetes early in gestation. CONCLUSION: Maternal preexisting diabetes is a known risk factor for development of congenital malformations. This rare case of type 1 caudal regression syndrome in a mother with preexisting diabetes with elevated hemoglobin A1c highlights the importance of preconception glycemic control in diabetic women and the utility of fetal magnetic resonance imaging for confirmation of ultrasound findings to permit accurate prognostication. Additionally, minimally invasive postmortem magnetic resonance imaging and computed tomography autopsy can facilitate diagnostic confirmation of clinical findings in perinatal death due to complex congenital anomalies while limiting the emotional burden on bereaved family members who decline conventional autopsy.

Automatic Localization of the Pons and Vermis on Fetal Brain MR Imaging Using a U-Net Deep Learning Model.

BACKGROUND AND PURPOSE: An MRI of the fetus can enhance the identification of perinatal developmental disorders, which improves the accuracy of ultrasound. Manual MRI measurements require training, time, and intra-variability concerns. Pediatric neuroradiologists are also in short supply. Our purpose was developing a deep learning model and pipeline for automatically identifying anatomic landmarks on the pons and vermis in fetal brain MR imaging and suggesting suitable images for measuring the pons and vermis. MATERIALS AND METHODS: We retrospectively used 55 pregnant patients who underwent fetal brain MR imaging with a HASTE protocol. Pediatric neuroradiologists selected them for landmark annotation on sagittal single-shot T2-weighted images, and the clinically reliable method was used as the criterion standard for the measurement of the pons and vermis. A U-Net-based deep learning model was developed to automatically identify fetal brain anatomic landmarks, including the 2 anterior-posterior landmarks of the pons and 2 anterior-posterior and 2 superior-inferior landmarks of the vermis. Four-fold cross-validation was performed to test the accuracy of the model using randomly divided and sorted gestational age-divided data sets. A confidence score of model prediction was generated for each testing case. RESULTS: Overall, 85% of the testing results showed a ≥90% confidence, with a mean error of <2.22 mm, providing overall better estimation results with fewer errors and higher confidence scores. The anterior and posterior pons and anterior vermis showed better estimation (which means fewer errors in landmark localization) and accuracy and a higher confidence level than other landmarks. We also developed a graphic user interface for clinical use. CONCLUSIONS: This deep learning-facilitated pipeline practically shortens the time spent on selecting good-quality fetal brain images and performing anatomic measurements for radiologists.

Automatic Ventriculomegaly Detection in Fetal Brain MRI: A Step-by-Step Deep Learning Model for Novel 2D-3D Linear Measurements.

In this study, we developed an automated workflow using a deep learning model (DL) to measure the lateral ventricle linearly in fetal brain MRI, which are subsequently classified into normal or ventriculomegaly, defined as a diameter wider than 10 mm at the level of the thalamus and choroid plexus. To accomplish this, we first trained a UNet-based deep learning model to segment the brain of a fetus into seven different tissue categories using a public dataset (FeTA 2022) consisting of fetal T2-weighted images. Then, an automatic workflow was developed to perform lateral ventricle measurement at the level of the thalamus and choroid plexus. The test dataset included 22 cases of normal and abnormal T2-weighted fetal brain MRIs. Measurements performed by our AI model were compared with manual measurements performed by a general radiologist and a neuroradiologist. The AI model correctly classified 95% of fetal brain MRI cases into normal or ventriculomegaly. It could measure the lateral ventricle diameter in 95% of cases with less than a 1.7 mm error. The average difference between measurements was 0.90 mm in AI vs. general radiologists and 0.82 mm in AI vs. neuroradiologists, which are comparable to the difference between the two radiologists, 0.51 mm. In addition, the AI model also enabled the researchers to create 3D-reconstructed images, which better represent real anatomy than 2D images. When a manual measurement is performed, it could also provide both the right and left ventricles in just one cut, instead of two. The measurement difference between the general radiologist and the algorithm (p = 0.9827), and between the neuroradiologist and the algorithm (p = 0.2378), was not statistically significant. In contrast, the difference between general radiologists vs. neuroradiologists was statistically significant (p = 0.0043). To the best of our knowledge, this is the first study that performs 2D linear measurement of ventriculomegaly with a 3D model based on an artificial intelligence approach. The paper presents a step-by-step approach for designing an AI model based on several radiological criteria. Overall, this study showed that AI can automatically calculate the lateral ventricle in fetal brain MRIs and accurately classify them as abnormal or normal.

Review of deep learning and artificial intelligence models in fetal brain magnetic resonance imaging.

Central nervous system abnormalities in fetuses are fairly common, happening in 0.1% to 0.2% of live births and in 3% to 6% of stillbirths. So initial detection and categorization of fetal Brain abnormalities are critical. Manually detecting and segmenting fetal brain magnetic resonance imaging (MRI) could be time-consuming, and susceptible to interpreter experience. Artificial intelligence (AI) algorithms and machine learning approaches have a high potential for assisting in the early detection of these problems, improving the diagnosis process and follow-up procedures. The use of AI and machine learning techniques in fetal brain MRI was the subject of this narrative review paper. Using AI, anatomic fetal brain MRI processing has investigated models to predict specific landmarks and segmentation automatically. All gestation age weeks (17-38 wk) and different AI models (mainly Convolutional Neural Network and U-Net) have been used. Some models' accuracy achieved 95% and more. AI could help preprocess and post-process fetal images and reconstruct images. Also, AI can be used for gestational age prediction (with one-week accuracy), fetal brain extraction, fetal brain segmentation, and placenta detection. Some fetal brain linear measurements, such as Cerebral and Bone Biparietal Diameter, have been suggested. Classification of brain pathology was studied using diagonal quadratic discriminates analysis, K-nearest neighbor, random forest, naive Bayes, and radial basis function neural network classifiers. Deep learning methods will become more powerful as more large-scale, labeled datasets become available. Having shared fetal brain MRI datasets is crucial because there aren not many fetal brain pictures available. Also, physicians should be aware of AI's function in fetal brain MRI, particularly neuroradiologists, general radiologists, and perinatologists.

MR Imaging of the Fetal Face: Comprehensive Review.

The human face is a complex anatomic structure with an equally complex embryologic development. Derangement of the developmental process can result in various structural anomalies, which range from a mainly cosmetic deformity, such as cleft lip, to potentially life-threatening conditions such as arhinia. These anomalies (a) can occur as isolated anomalies; (b) can be associated with intracranial, spinal, or dental anomalies; or (c) can be a part of various syndromes, thus serving as diagnostic clues in such cases. Proper evaluation of fetal facial deformities can help in prognostication, family counseling, and prenatal or early postnatal intervention. Ultrasonography (US) is the first line of investigation in these cases. However, when US does not allow complete evaluation of these anomalies owing to its inherent limitations, magnetic resonance (MR) imaging allows comprehensive evaluation of the anomaly itself and also evaluation of various associations and the treatment approach. The embryology of the fetal facial structures is considered with regard to the MR imaging technique and the MR imaging anatomy. The MR imaging features of various structural anomalies are described and classified into six groups, namely, orofacial clefts, orbital anomalies, nasal anomalies, facial masses, external ear anomalies, and abnormal face shape or profile. Also, the key associations and relevant treatment implications are reviewed. The article provides a "one-stop shop" review of these unique disorders-from basic understanding of the embryology to applying the knowledge in clinical practice, helping the interprofessional team and the patients alike. ©RSNA, 2018.

Magnetic resonance imaging characteristics of typical and atypical/anaplastic meningiomas - Case series and literature review.

OBJECTIVE: The histologic grades of meningiomas have a significant impact on the risk of recurrence, prognosis, and the need for adjuvant treatment such as radiation therapy. The purpose of this study is to investigate the magnetic resonance imaging (MRI) characteristics of typical and atypical/anaplastic meningiomas. METHODS: The medical records of 32 consecutive patients who underwent meningioma resections between April 2004 and November 2006 were retrospectively reviewed. Preoperative MR studies were reviewed by board-certified neuroradiologists. Both univariate and multivariate analyses were used to analyze the MR characteristics of the typical and atypical/anaplastic meningiomas. A review of pertinent literature was also conducted. RESULTS: Thirty-two patients were identified during the study period. Histopathologic examination of the surgical specimens revealed 27 (84.4% - Group I) typical meningiomas and 5 (15.6% - Group 2) atypical/anaplastic meningiomas. The chi-square test showed that restricted diffusion was much more likely to be present in Group 2 (p < 0.01), and the choline-to-creatinine (Cho/Cr) ratio was significantly higher in Group 2 (8.8 vs. 5.1, p = 0.01). The multivariate analysis confirmed that the atypical/anaplastic group is much more likely to have restricted diffusion (p = 0.02) and higher Cho/Cr ratios (p = 0.03). CONCLUSION: Meningiomas with restricted diffusion and higher Cho/Cr ratio on MR spectroscopy are more likely to be atypical/anaplastic types. Preoperative MRI utilizing these sequences can provide important information which can be valuable to counsel patients regarding prognosis, risk of recurrence and the need for adjuvant radiation in addition to surgical resection.

MRI: is there a role in obstetrics?

Magnetic resonance imaging has a complementary role in obstetrical imaging to ultrasound (US). Although US has advantages as an initial imaging technique, there are significant numbers of patients who cannot be adequately evaluated for a variety of reasons including calvarial calcification, oligoanhydramnios, or simply obesity. MR can provide additional information that cannot be obtained by US and is invaluable in central nervous system anomaly evaluation, airway management, and planning for postnatal intervention. Newer techniques established in the postnatal population such as spectroscopy, diffusion-weighted imaging, and functional imaging have future applications in the fetus.

Fetal MR imaging of posterior intracranial dural sinus thrombosis: a report of three cases with variable outcomes.

BACKGROUND: Thrombosis of fetal intracranial dural sinuses is a rare entity. A specific type of midline dural sinus thrombosis (DST) at the torcular Herophili with extension into the superior sagittal sinus (SSS) was initially seen on fetal US and was referred to fetal MRI for definite diagnosis and better delineation. OBJECTIVE: Retrospective comparison to medical literature of three cases, diagnosed at our institution, of midline fetal DST with MR imaging findings and clinical outcomes. MATERIALS AND METHODS: We reviewed MRI findings on T2-weighted images of our three cases of fetal midline DST and clinical outcomes of these fetuses and compared our findings to medical literature. The MR imaging and clinical findings of our cases extend over 6 years. They consist of three pregnant women, 31-39 years of age each with a single fetus, with fetal MR imaging performed at different gestational ages (GA). Case 1 the MR imaging was performed at 21 5/7 weeks' GA, case 2 at 24 and 33 4/7 weeks' GA, and case 3 at 22 and 25 weeks' GA. Postnatal MRI was performed in case 2 at 6 months of life and case 3 at 1 day of life. Clinical follow-up occurred during the last 6 years. RESULTS: In all of our cases, T2-W MR imaging demonstrated ballooned midline torcular Herophili with iso- to hypointense mass with or without focal eccentric area of greater hypointensity occupying the torcular Herophili with extension into the SSS. Case 3 had associated leptomeningeal dural vascular malformation overlying the left cerebral hemisphere with development of migrational disorder in the left cerebral hemisphere. Clinical outcome consisted of fetal demise in case 1, normal postnatal outcome in case 2 and severe brain damage with poor postnatal outcome in case 3. CONCLUSION: Our findings of large iso-hypointense thrombus with or without a focal eccentric area more hypointense to thrombus in a dilated torcular Herophili with extension into the SSS on T2-W images corresponds to the majority of cases of this rare type of DST in the medical literature.

Postnatal maturation and radiology of the growing spine.

Postnatal maturation of the spine is marked by the ossification process and by changes in the shape of the vertebrae, spinal curvature, spinal canal, discs, and bone marrow. Different aspects of the spine's maturation process are demonstrated on the three most common radiologic modalities used to evaluate the spine. Conventional plain spine imaging (plain spine radiography) provides a good initial evaluation of the bony spine. CT provides better bone detail and allows finer evaluation of subtle structures, the soft tissues of the spine (discs, ligaments), and the spinal cord. MRI provides excellent resolution of the bone marrow, ligaments, and discs of the spine, and can be used as an adjunct for evaluating the soft tissue of the spine and intraspinal contents.

Neural larva migrans caused by the raccoon roundworm Baylisascaris procyonis.

Baylisascaris procyonis, the common raccoon roundworm, is a rare cause of devastating or fatal neural larva migrans in infants and young children. We describe the clinical features of two children from suburban Chicago who developed severe, nonfatal B. procyonis neural larva migrans. Despite treatment with albendazole and high dose corticosteroids, both patients are neurologically devastated. In many regions of North America, large populations of raccoons with high rates of endemic B. procyonis infection live in proximity to humans, which suggests that the risk of human infection is probably substantial. In the absence of effective treatment, prevention of infection remains the most important public health strategy.