MRI in Patients with Cardiovascular Implantable Electronic Devices and Fractured or Abandoned Leads.

Purpose To examine the clinical effect of lead length and lead orientation in patients with cardiac implantable electronic devices (CIEDs) and lead fragments or abandoned leads undergoing 1.5-T MRI. Materials and Methods This Health Insurance Portability and Accountability Act-compliant retrospective study included patients with CIEDs and abandoned leads or lead fragments undergoing 1.5-T MRI from March 2014 through July 2020. CIED settings before and after MRI were reviewed, with clinically significant variations defined as a composite of the change in capture threshold of at least 50%, in sensing of at least 40%, or in lead impedance of at least 30% between before MRI and after MRI interrogation. Adverse clinical events were assessed at MRI and up to 30 days after. Univariable and multivariable analysis was performed. Results Eighty patients with 126 abandoned CIED leads or lead fragments underwent 107 1.5-T MRI examinations. Sixty-seven patients (median age, 74 years; IQR, 66-78 years; 44 male patients, 23 female patients) had abandoned leads, and 13 (median age, 66 years; IQR, 52-74 years; nine male patients, four female patients) had lead fragments. There were no reported deaths, clinically significant arrhythmias, or adverse clinical events within 30 days of MRI. Three patients with abandoned leads had a significant change in the composite of capture threshold, sensing, or lead impedance. In a multivariable generalized estimating equation analysis, lead orientation, lead length, MRI type, and MRI duration were not associated with a significant change in the composite outcome. Conclusion Use of 1.5-T MRI in patients with abandoned CIED leads or lead fragments of varying length and orientation was not associated with adverse clinical events. Keywords: Cardiac Assist Devices, MRI, Cardiac Implantable Electronic Device Supplemental material is available for this article. © RSNA, 2024.

Reducing annotation burden in MR: A novel MR-contrast guided contrastive learning approach for image segmentation.

BACKGROUND: Contrastive learning, a successful form of representational learning, has shown promising results in pretraining deep learning (DL) models for downstream tasks. When working with limited annotation data, as in medical image segmentation tasks, learning domain-specific local representations can further improve the performance of DL models. PURPOSE: In this work, we extend the contrastive learning framework to utilize domain-specific contrast information from unlabeled Magnetic Resonance (MR) images to improve the performance of downstream MR image segmentation tasks in the presence of limited labeled data. METHODS: The contrast in MR images is controlled by underlying tissue properties (e.g., T1 or T2) and image acquisition parameters. We hypothesize that learning to discriminate local representations based on underlying tissue properties should improve subsequent segmentation tasks on MR images. We propose a novel constrained contrastive learning (CCL) strategy that uses tissue-specific information via a constraint map to define positive and negative local neighborhoods for contrastive learning, embedding this information in the representational space during pretraining. For a given MR contrast image, the proposed strategy uses local signal characteristics (constraint map) across a set of related multi-contrast MR images as a surrogate for underlying tissue information. We demonstrate the utility of the approach for downstream: (1) multi-organ segmentation tasks in T2-weighted images where a DL model learns T2 information with constraint maps from a set of 2D multi-echo T2-weighted images (n = 101) and (2) tumor segmentation tasks in multi-parametric images from the public brain tumor segmentation (BraTS) (n = 80) dataset where DL models learn T1 and T2 information from multi-parametric BraTS images. Performance is evaluated on downstream multi-label segmentation tasks with limited data in (1) T2-weighted images of the abdomen from an in-house Radial-T2 (Train/Test = 30/20), (2) public Cartesian-T2 (Train/Test = 6/12) dataset, and (3) multi-parametric MR images from the public brain tumor segmentation dataset (BraTS) (Train/Test = 40/50). The performance of the proposed CCL strategy is compared to state-of-the-art self-supervised contrastive learning techniques. In each task, a model is also trained using all available labeled data for supervised baseline performance. RESULTS: The proposed CCL strategy consistently yielded improved Dice scores, Precision, and Recall metrics, and reduced HD95 values across all segmentation tasks. We also observed performance comparable to the baseline with reduced annotation effort. The t-SNE visualization of features for T2-weighted images demonstrates its ability to embed T2 information in the representational space. On the BraTS dataset, we also observed that using an appropriate multi-contrast space to learn T1+T2, T1, or T2 information during pretraining further improved the performance of tumor segmentation tasks. CONCLUSIONS: Learning to embed tissue-specific information that controls MR image contrast with the proposed constrained contrastive learning improved the performance of DL models on subsequent segmentation tasks compared to conventional self-supervised contrastive learning techniques. The use of such domain-specific local representations could help understand, improve performance, and mitigate the scarcity of labeled data in MR image segmentation tasks.

MRI Imaging Appearance of Hyperostosis Frontalis Interna (HFI): A Case Report of Focal Benign Enhancement.

Hyperostosis frontalis interna (HFI) is a common and often incidental finding seen on imaging. There is a significant paucity of radiology literature, particularly regarding the MRI imaging appearance of HFI. We reported two cases of HFI on MRI, which showed focal enhancement. These were stable on long-term follow-up studies and thought to be most consistent with benign enhancement. Further studies are needed to elucidate the underlying pathogenesis; however, it is important to be aware that regions of HFI may demonstrate variable enhancement and are sometimes mistaken for osseous metastatic disease.

Cerebrospinal fluid flushing as a means of neuroprotection.

Central nervous system (CNS) injury or disease states are often difficult to treat due to the closed system of the dura mater/blood-brain barrier and the bony skull and vertebrae. The closed system results in at least partial containment of any pro-inflammatory molecules, pathogens, or toxic byproducts in the case of brain or spinal cord lesions, which can result in a destructive feedback loop. Cervical-approach access techniques (lateral C1-C2, suboccipital and lateral atlanto-occipital space punctures) are less-common methods of cerebrospinal fluid (CSF) sampling due to the relative ease and safety of lumbar spinal taps. However, with improved image-guidance, these cervical-level CSF access points are still useful when there are certain contraindications and difficulties when attempting to sample the CSF via the typical lumbar spinal approach. With the advent of microcatheters and minimally invasive techniques, combined with body fluid filtration technology, the question arises: could dual microcatheters be introduced for inflow and outflow of purified or artificial CSF to break the destructive feedback loop and thus diminish CNS damage?. We hypothesize that intrathecal spinal catheters could be placed in 2 positions (e.g., via a cervical route and the typical lumbar spinal route) to allow for both an input and output to more effectively filter or "flush" the CSF. This could have broad implications in the treatment of strokes, traumatic brain or spinal cord injury, infections, autoimmune diseases, and even malignancies within the CNS-in short, any disease with abnormalities detectable in the CSF.

Paracaval lipoma: Case study and literature review.

Paracaval lipoma refers to a fatty tissue collection surrounding the intrahepatic portion of the inferior vena cava (IVC). It is a relatively infrequent benign finding on abdominal CT imaging, speculated to be a result of negative thoracic pressure on the IVC during inspiration. If not recognized, paracaval lipoma can be confused for thrombus or, worse yet, malignant invasion of the IVC, resulting in a costly and unnecessary workup. Here we describe a 51-year-old white male presenting to our institution with a 2-week history of abdominal pain, increasing abdominal girth, jaundice, and ascites; subsequent CT of the abdomen and pelvis without contrast revealed an incidental finding of fat deposition around the caudate lobe with a juxtacaval distribution, consistent with paracaval lipoma.