Topics in magnetic resonance imaging : TMRI
-
Top Magn Reson Imaging · Aug 2020
ReviewApplying Artificial Intelligence to Mitigate Effects of Patient Motion or Other Complicating Factors on Image Quality.
Artificial intelligence, particularly deep learning, offers several possibilities to improve the quality or speed of image acquisition in magnetic resonance imaging (MRI). In this article, we briefly review basic machine learning concepts and discuss commonly used neural network architectures for image-to-image translation. ⋯ As patients occasionally are unable to tolerate lengthy acquisition times or gadolinium agents, machine learning can potentially assist MRI workflow and patient comfort by facilitating faster acquisitions or reducing exogenous contrast dosage. Although artificial intelligence approaches often have limitations, such as problems with generalizability or explainability, there is potential for these techniques to improve diagnostic utility, throughput, and patient experience in clinical MRI practice.
-
This manuscript will review emerging applications of artificial intelligence, specifically deep learning, and its application to glioblastoma multiforme (GBM), the most common primary malignant brain tumor. Current deep learning approaches, commonly convolutional neural networks (CNNs), that take input data from MR images to grade gliomas (high grade from low grade) and predict overall survival will be shown. There will be more in-depth review of recent articles that have applied different CNNs to predict the genetics of glioma on pre-operative MR images, specifically 1p19q codeletion, MGMT promoter, and IDH mutations, which are important criteria for the diagnosis, treatment management, and prognostication of patients with GBM. Finally, there will be a brief mention of current challenges with DL techniques and their application to image analysis in GBM.
-
Top Magn Reson Imaging · Apr 2020
ReviewAdult Glioma WHO Classification Update, Genomics, and Imaging: What the Radiologists Need to Know.
Recent advances in the understanding of the genetic makeup of gliomas have led to a paradigm shift in the diagnosis and classification of these tumors. Driven by these changes, the World Health Organization (WHO) introduced an update to its classification system of central nervous system (CNS) tumors in 2016. ⋯ Familiarity with this new classification scheme, the individual molecular markers, and corresponding imaging findings is critical for the radiologists who play an important role in diagnostic and surveillance imaging of patients with CNS tumors. The goals of this article are to review these updates to the WHO classification of CNS tumors with a focus on adult gliomas, provide an overview of key genomic markers of gliomas, and review imaging features pertaining to various genomic subgroups of adult gliomas.
-
Top Magn Reson Imaging · Aug 2019
ReviewLanguage Mapping With fMRI: Current Standards and Reproducibility.
Clinical use of blood oxygen level dependent (BOLD) functional magnetic resonance imaging (fMRI) is a relatively new phenomenon, with only about 3 decades of collective experience. Nevertheless, task-based BOLD fMRI has been widely accepted for presurgical planning, over traditional methods, which are invasive and at times perilous. Many studies have demonstrated the ability of BOLD fMRI to make substantial clinical impact with respect to surgical planning and preoperative risk assessment, especially to localize the eloquent motor and visual areas. ⋯ There are national efforts currently underway to standardize language fMRI. The American Society of Functional Neuroradiology (ASFNR) has recently provided guidelines on fMRI paradigm algorithms for presurgical language assessment for language lateralization and localization. In this review article, we provide a comprehensive overview of current standards of language fMRI mapping and its reproducibility.
-
Top Magn Reson Imaging · Apr 2019
ReviewUpdates in the Neuoroimaging and WHO Classification of Primary CNS Gliomas: A Review of Current Terminology, Diagnosis, and Clinical Relevance From a Radiologic Prospective.
As new advances in the genomics and imaging of CNS tumors continues to evolve, a standardized system for classification is increasingly essential to diagnosis and management. The molecular markers introduced in the 2016 WHO classification of CNS tumors bring both practical and conceptual advances to the characterization of gliomas, strengthening the prognostic and predictive value of terminology while shedding light on the underlying mechanisms that drive biologic behavior. ⋯ An update of the molecular markers pertinent to defining the major lineages of brain gliomas will be provided, followed by discussion of the terminology, grading and imaging features associated with individual entities. Neuroradiologists should be aware of the key genomic and radiomic features of common brain gliomas, and familiar with an integrated approach to their diagnosis and grading.