Deep Learning-based Approach for Brainstem and Ventricular MR Planimetry: Application in Patients with Progressive Supranuclear Palsy.

Purpose To develop a fast and fully automated deep learning (DL)-based method for the MRI planimetric segmentation and measurement of the brainstem and ventricular structures most affected in patients with progressive supranuclear palsy (PSP). Materials and Methods In this retrospective study, T1-weighted MR images in healthy controls (n = 84) were used to train DL models for segmenting the midbrain, pons, middle cerebellar peduncle (MCP), superior cerebellar peduncle (SCP), third ventricle, and frontal horns (FHs). Internal, external, and clinical test datasets (n = 305) were used to assess segmentation model reliability. DL masks from test datasets were used to automatically extract midbrain and pons areas and the width of MCP, SCP, third ventricle, and FHs. Automated measurements were compared with those manually performed by an expert radiologist. Finally, these measures were combined to calculate the midbrain to pons area ratio, MR parkinsonism index (MRPI), and MRPI 2.0, which were used to differentiate patients with PSP (n = 71) from those with Parkinson disease (PD) (n = 129). Results Dice coefficients above 0.85 were found for all brain regions when comparing manual and DL-based segmentations. A strong correlation was observed between automated and manual measurements (Spearman ρ > 0.80, P < .001). DL-based measurements showed excellent performance in differentiating patients with PSP from those with PD, with an area under the receiver operating characteristic curve above 0.92. Conclusion The automated approach successfully segmented and measured the brainstem and ventricular structures. DL-based models may represent a useful approach to support the diagnosis of PSP and potentially other conditions associated with brainstem and ventricular alterations. Keywords: MR Imaging, Brain/Brain Stem, Segmentation, Quantification, Diagnosis, Convolutional Neural Network Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Mohajer in this issue.

Cerebral Venous Thrombosis after SARS-CoV-2 Infection and Pfizer-BioNTech Vaccination against COVID-19.

In the last 3 years, COVID-19 pandemic has produced great impacts on global population in terms of health and social costs. Pneumonia represents only one of several pathologies associated to COVID-19 disease. Among these, the cerebral venous thrombosis (CVT), constitutes an important cause of stroke. Here, we report a case of CVT diagnosed approximately 2 weeks after first dose of Pfizer-BioNTech vaccination, in a patient affected by COVID-19 few months earlier. He presented with headache and severe asthenia. The laboratory tests put in evidence thrombocytopenia and D-dimer elevation. A brain magnetic resonance imaging (MRI) and a computed tomography (CT) demonstrated hemorrhagic and ischemic phenomena on the right ventral thalamic nuclei, left thalamus, hippocampal and parahippocampal regions and the splenium of the corpus callosum. The study revealed a poorly opacified vein of Galeno and straight sinus. Heparin administration improved his clinical status; platelets values also arose over time.

Streak artefacts in Computed Tomography Urography: Comparative evaluation between two different iodinated contrast media.

INTRODUCTION: The objective of this study was to compare the frequency and entity, in computed tomography (CT) urography, of streak artefacts on the urinary tract generated by two contrast agents with a different iodine concentration and osmolarity. METHODS: Computed tomography scans including an excretory renal phase, performed on adult subjects in the period May-July 2020, were retrospectively evaluated in consensus by three expert radiologists, to detect any streak artefacts located in the urinary tract. Patients were administered either 1.6 mL/kg of Iodixanol 320 mgI/mL or 1.3 mL/kg of Iomeprol 400 mgI/mL. RESULTS: In total, 144 CT scans were analysed, subdivided into two groups administered either Iodixanol (71/144 (49.3%) patients) or Iomeprol (73/144 (50.7%) patients). In 41% cases, no beam hardening artefacts were found; among these, 12/59 (20.3%) patients had received Iodixanol and 47/59 (79.7%) Iomeprol. In the Iodixanol group, the mean contrast density on the renal pelvis was 2565.6 HU and streak artefacts occurred in 59/71 cases (83.1%); in 33/59 (55.9%) cases, the artefacts were marked, and in 26/59 (44.1%) minimal. In the Iomeprol group, the mean contrast density on the renal pelvis was 1666 HU and streak artefacts occurred in 26/73 cases (35.6%); in 7/26 (27%) cases, the artefacts were marked and in 19/26 (73%) minimal. CONCLUSION: The study data demonstrate a significant difference in the attenuation values of iodine urine in the excretory system between the Iodixanol and Iomeprol group. Iodixanol induced a higher frequency and burden of artefacts, compared to Iomeprol.