Automated intracranial vessel segmentation of 4D flow MRI data in patients with atherosclerotic stenosis using a convolutional neural network.

Introduction: Intracranial 4D flow MRI enables quantitative assessment of hemodynamics in patients with intracranial atherosclerotic disease (ICAD). However, quantitative assessments are still challenging due to the time-consuming vessel segmentation, especially in the presence of stenoses, which can often result in user variability. To improve the reproducibility and robustness as well as to accelerate data analysis, we developed an accurate, fully automated segmentation for stenosed intracranial vessels using deep learning. Methods: 154 dual-VENC 4D flow MRI scans (68 ICAD patients with stenosis, 86 healthy controls) were retrospectively selected. Manual segmentations were used as ground truth for training. For automated segmentation, deep learning was performed using a 3D U-Net. 20 randomly selected cases (10 controls, 10 patients) were separated and solely used for testing. Cross-sectional areas and flow parameters were determined in the Circle of Willis (CoW) and the sinuses. Furthermore, the flow conservation error was calculated. For statistical comparisons, Dice scores (DS), Hausdorff distance (HD), average symmetrical surface distance (ASSD), Bland-Altman analyses, and interclass correlations were computed using the manual segmentations from two independent observers as reference. Finally, three stenosis cases were analyzed in more detail by comparing the 4D flow-based segmentations with segmentations from black blood vessel wall imaging (VWI). Results: Training of the network took approximately 10 h and the average automated segmentation time was 2.2 ± 1.0 s. No significant differences in segmentation performance relative to two independent observers were observed. For the controls, mean DS was 0.85 ± 0.03 for the CoW and 0.86 ± 0.06 for the sinuses. Mean HD was 7.2 ± 1.5 mm (CoW) and 6.6 ± 3.7 mm (sinuses). Mean ASSD was 0.15 ± 0.04 mm (CoW) and 0.22 ± 0.17 mm (sinuses). For the patients, the mean DS was 0.85 ± 0.04 (CoW) and 0.82 ± 0.07 (sinuses), the HD was 8.4 ± 3.1 mm (CoW) and 5.7 ± 1.9 mm (sinuses) and the mean ASSD was 0.22 ± 0.10 mm (CoW) and 0.22 ± 0.11 mm (sinuses). Small bias and limits of agreement were observed in both cohorts for the flow parameters. The assessment of the cross-sectional lumen areas in stenosed vessels revealed very good agreement (ICC: 0.93) with the VWI segmentation but a consistent overestimation (bias ± LOA: 28.1 ± 13.9%). Discussion: Deep learning was successfully applied for fully automated segmentation of stenosed intracranial vasculatures using 4D flow MRI data. The statistical analysis of segmentation and flow metrics demonstrated very good agreement between the CNN and manual segmentation and good performance in stenosed vessels. To further improve the performance and generalization, more ICAD segmentations as well as other intracranial vascular pathologies will be considered in the future.

MR Vessel Wall Imaging for Atherosclerosis and Vasculitis.

Conventional imaging modalities, such as computed tomography angiography, MR angiography, transcranial Doppler ultrasonography, and digital subtraction angiography, are utilized in evaluating intraluminal or intravascular pathology of the intracranial vessels. Limitations of luminal imaging techniques can lead to inaccurate diagnosis, evaluation, and risk stratification, as many cerebrovascular pathologies contain an extrinsic vessel wall component. Furthermore, vessel wall imaging can provide information regarding extent, treatment response, and biopsy targets for vasculitis cases. Overall, while vessel wall imaging can provide robust data regarding intracranial pathologies, further prospective, multicenter studies are required to improve diagnostic application and accuracy.

Declining groundwater and its impacts along Ganga riverfronts using combined Sentinel-1, GRACE, water levels, and rainfall data.

The Indo-Gangetic Plains (IGP) in northern India are vast alluvial tracts with huge shallow aquifers, densely populated and agriculturally productive regions. In the last few decades, IGP has been facing water scarcity driven by erratic monsoon dynamics, anthropogenic activity, and hydroclimatic variability. In urban centers, continuous groundwater withdrawal leads to high stress, affecting surface deformation and a threat to buildings and infrastructures. An attempt has been made to explore the possible linkage and coupling between groundwater level, hydroclimatic variables, and subsidence in the Central Ganga Plains (CGP), in Varanasi metropolis using the combined multisensory multitemporal data, Sentinel-1 (2017-2023), GRACE (2003-2023), groundwater levels (1998-2023), and precipitation (2002-2023). Long-term hydrological response in the CGP shows continuous depletion (14.6 ± 5.6 mm/yr) in response to precipitation variability. Results show spatiotemporal variations between GWS, and precipitation estimate with nonlinear trend response due to associated inter-annual/inter-seasonal climate variability and anthropogenic water withdrawal, specifically during the observed drought years. The significant storage response in the urban center compared to a regional extent suggests the potential impact of exponentially increasing urbanization and building hydrological stress in the cities. The implications of reducing storage capacity show measured land subsidence (∼2-8 mm/yr) patterns developed along the meandering stretch of the Ganga riverfronts in Varanasi. The groundwater level data from the piezometric supports the hydroclimatic variables and subsidence coupling. Considering the vital link between water storage, food security, and socioeconomic growth, the results of this study require systematic inclusion in water management strategies as climate change seriously impacts water resources in the future.

Prostate Cancer-PET Imaging Update.

Prostate cancer is the most common non-dermatologic cancer in men, and one of the leading causes of cancer-related mortality. The incidence of prostate cancer increases precipitously after the age of 65 and demonstrates variable aggressiveness, depending on its grade and stage at diagnosis. Despite recent advancements in prostate cancer treatment, recurrence is seen in 25% of patients. Advancements in prostate cancer Positron Emission Tomography (PET) molecular imaging and recent United States Food and Drug Administration (FDA) approvals have led to several new options for evaluating prostate cancer. This manuscript will review the commonly used molecular imaging agents, with an emphasis on Fluorine-18 fluciclovine (Axumin) and PSMA-ligand agents, including their protocols, imaging interpretation, and pitfalls.

Glioma-Induced Seizure in a Neurofibromatosis Type 1 Patient: A Case Report.

Neurofibromatosis type 1 (NF-1), also known as Von Recklinghausen's disease, is an autosomal-dominant disease that is characterized by high-frequency mutations leading to multiple benign tumors called neurofibromas and café au lait spots on the skin. Although NF-1 mainly affects the nervous system, it can have multisystem involvement as well, associated with the cardiovascular, orthopedic, gastrointestinal, and dermatologic systems. Psychiatric complications like anxiety, dysthymia, and depression have also been reported in patients with NF-1. The prevalence of this disorder is one in 3,000 births. NF-1 patients have a higher prevalence of seizures compared to the general population. A 20-year-old male with a diagnosis of NF-1 at the age of three months presented to the emergency room (ER) of a local hospital for the evaluation of an unwitnessed seizure characterized by loss of consciousness and bladder control. MRI of the brain without contrast revealed hyperintensities in the mesial temporal lobe bilaterally, with a hyperintense FLAIR lesion in the splenium of the corpus callosum. The patient exhibited sudden aggression and combativeness while in the ER and also experienced a second seizure, which prompted immediate intubation. A second MRI with contrast confirmed the presence of the lesion. The patient also underwent electroencephalogram (EEG) monitoring later during his hospital stay, the results of which were unremarkable. This case report discusses an adult male with NF-1 and a tumor of the splenium of the corpus callosum. The displayed imaging suggested a possible etiology for high seizure frequency in patients with NF-1 compared to the general population.

COVID-19 Infection and Myocarditis: A State-of-the-Art Systematic Review.

BACKGROUND: COVID-19 was initially considered to be a respiratory illness, but current findings suggest that SARS-CoV-2 is increasingly expressed in cardiac myocytes as well. COVID-19 may lead to cardiovascular injuries, resulting in myocarditis, with inflammation of the heart muscle. OBJECTIVE: This systematic review collates current evidence about demographics, symptomatology, diagnostic, and clinical outcomes of COVID-19 infected patients with myocarditis. METHODS: In accordance with PRISMA 2020 guidelines, a systematic search was conducted using PubMed, Cochrane Central, Web of Science and Google Scholar until August, 2021. A combination of the following keywords was used: SARS-CoV-2, COVID-19, myocarditis. Cohorts and case reports that comprised of patients with confirmed myocarditis due to COVID-19 infection, aged >18 years were included. The findings were tabulated and subsequently synthesized. RESULTS: In total, 54 case reports and 5 cohorts were identified comprising 215 patients. Hypertension (51.7%), diabetes mellitus type 2 (46.4%), cardiac comorbidities (14.6%) were the 3 most reported comorbidities. Majority of the patients presented with cough (61.9%), fever (60.4%), shortness of breath (53.2%), and chest pain (43.9%). Inflammatory markers were raised in 97.8% patients, whereas cardiac markers were elevated in 94.8% of the included patients. On noting radiographic findings, cardiomegaly (32.5%) was the most common finding. Electrocardiography testing obtained ST segment elevation among 44.8% patients and T wave inversion in 7.3% of the sample. Cardiovascular magnetic resonance imaging yielded 83.3% patients with myocardial edema, with late gadolinium enhancement in 63.9% patients. In hospital management consisted of azithromycin (25.5%), methylprednisolone/steroids (8.5%), and other standard care treatments for COVID-19. The most common in-hospital complication included acute respiratory distress syndrome (66.4%) and cardiogenic shock (14%). On last follow up, 64.7% of the patients survived, whereas 31.8% patients did not survive, and 3.5% were in the critical care unit. CONCLUSION: It is essential to demarcate COVID-19 infection and myocarditis presentations due to the heightened risk of death among patients contracting both myocardial inflammation and ARDS. With a multitude of diagnostic and treatment options available for COVID-19 and myocarditis, patients that are under high risk of suspicion for COVID-19 induced myocarditis must be appropriately diagnosed and treated to curb co-infections.

Radiology of Abnormal Globe Contour.

The orbits are easily identified on routine computed tomography (CT) and magnetic resonance imaging (MRI) imaging of the head and neck. Although there are many structures within the orbits, the overall structure of the globe is the most noticeable and can be an important source for pathology. In particular, many disease processes alter globe morphology and it is imperative that the radiologist be aware of not only the most common, but uncommon etiologies as well. This article provides an image-rich review of the wide range of emergent and non-emergent pathology that can result in altered globe contour.

Imaging of acute gastric emergencies: a case-based review.

The stomach is one of the most frequently imaged organs in the body with dedicated and incidental inclusion in chest imaging modalities. Gastric emergencies often present clinically with non-specific abdominal, nausea, and vomiting. As such, imaging plays a critical role in early identification and treatment of a myriad of gastric emergencies. The goal of this paper is to showcase gastric emergencies as they appear on multimodality imaging.

Mycotic Aneurysm of the Hepatic Artery: A Case Report and its Management.

Cholecystectomies are one of the most common surgical procedures performed in the United States, with complications being relatively common. We submit a case of a ruptured mycotic aneurysm of the hepatic artery, a complication of a recent cholecystectomy which was successfully treated with the use of transarterial thrombin.

Untreated Superior Vena Cava Aneurysm: Radiological Significance and Review of the Literature.

Superior vena cava (SVC) aneurysms are a rare entity. The majority of the literature is in the form of case reports. SVC aneurysms are often an incidental finding with iatrogenic, congenital, or idiopathic etiologies. Treatment goals focus on preventing theoretical rupture or thrombus formation. Management options include observation, conservative medical management, surgical excision, and thrombin injection. We present a 73-year-old female with an incidental SVC aneurysm discovered on computed tomography (CT) of the thorax. The patient was observed without intervention for greater than 6 years. No complications were attributable to the SVC aneurysm during follow-up or over the course of the patient's life.