Investigative radiology
-
Investigative radiology · Jun 2021
Deep Learning-Based Automated Abdominal Organ Segmentation in the UK Biobank and German National Cohort Magnetic Resonance Imaging Studies.
The aims of this study were to train and evaluate deep learning models for automated segmentation of abdominal organs in whole-body magnetic resonance (MR) images from the UK Biobank (UKBB) and German National Cohort (GNC) MR imaging studies and to make these models available to the scientific community for analysis of these data sets. ⋯ Automated segmentation of abdominal organs is possible with high qualitative and quantitative accuracy on whole-body MR imaging data acquired as part of UKBB and GNC. The results obtained and deep learning models trained in this study can be used as a foundation for automated analysis of thousands of MR data sets of UKBB and GNC and thus contribute to tackling topical and original scientific questions.
-
Investigative radiology · Dec 2020
The Limited Sensitivity of Chest Computed Tomography Relative to Reverse Transcription Polymerase Chain Reaction for Severe Acute Respiratory Syndrome Coronavirus-2 Infection: A Systematic Review on COVID-19 Diagnostics.
Several studies suggest the sensitivity of chest computed tomography (CT) is far greater than that of reverse transcription polymerase chain reaction (RT-PCR) in diagnosing COVID-19 patients, and therefore, CT should be included as a primary diagnostic tool. This systematic review aims to stratify studies as high or low risk of bias to determine the true sensitivity of CT for severe acute respiratory syndrome coronavirus-2 infection according to the unbiased (low risk) studies, a topic of particular importance given the insufficient quantity of RT-PCR kits in many countries. We focus on sensitivity as that is the chief advantage perceived of CT. ⋯ The difference between the sensitivities of CT and RT-PCR for severe acute respiratory syndrome coronavirus-2 infection is lower than previously thought, as after stratifying the studies, the true sensitivity for CT based on the unbiased studies is limited.
-
Investigative radiology · Nov 2020
Inversion Recovery Susceptibility Weighted Imaging With Enhanced T2 Weighting at 3 T Improves Visualization of Subpial Cortical Multiple Sclerosis Lesions.
Cortical demyelination is common in multiple sclerosis (MS) and can be extensive. Cortical lesions contribute to disability independently from white matter lesions and may form via a distinct mechanism. However, current magnetic resonance imaging methods at 3 T are insensitive to cortical, and especially subpial cortical, lesions. Subpial lesions are well seen on T2*-weighted imaging at 7 T, but T2*-weighted methods on 3 T scanners are limited by poor lesion-to-cortex and cerebrospinal fluid-to-lesion contrast. We aimed to develop and evaluate a cerebrospinal fluid-suppressed, T2*-weighted sequence optimized for subpial cortical lesion visualization. ⋯ Subpial lesions are better visualized on IR-SWIET compared with other 3 T methods. A 3 T protocol combining IR-SWIET with MP2RAGE, in which leukocortical lesions are well seen, improves cortical lesion visualization over existing approaches. Therefore, IR-SWIET may enable improved MS diagnostic specificity and a better understanding of the clinical implications of cortical demyelination.
-
Investigative radiology · Aug 2020
Super-Resolution Magnetic Resonance Imaging of the Knee Using 2-Dimensional Turbo Spin Echo Imaging.
The purpose of this study was to assess the technical feasibility of 3-dimensional (3D) super-resolution reconstruction (SRR) of 2D turbo spin echo (TSE) knee magnetic resonance imaging (MRI) and to compare its image quality with conventional 3D TSE sampling perfection with application optimized contrast using different flip angle evolutions (SPACE) MRI. ⋯ We demonstrate the technical feasibility of SRR for high-resolution isotropic knee MRI. Our SRR results show superior image quality in terms of edge blurring, but lower image contrast and fluid brightness when compared with conventional 3D SPACE acquisitions. Further contrast optimization and shortening of the acquisition time with state-of-the-art acceleration techniques are necessary for future clinical validation of SRR knee MRI.
-
Investigative radiology · Aug 2020
Comparative StudyDeep Convolutional Neural Network-Based Diagnosis of Anterior Cruciate Ligament Tears: Performance Comparison of Homogenous Versus Heterogeneous Knee MRI Cohorts With Different Pulse Sequence Protocols and 1.5-T and 3-T Magnetic Field Strengths.
The aim of this study was to clinically validate a Deep Convolutional Neural Network (DCNN) for the detection of surgically proven anterior cruciate ligament (ACL) tears in a large patient cohort and to analyze the effect of magnetic resonance examinations from different institutions, varying protocols, and field strengths. ⋯ Deep Convolutional Neural Network performance of ACL tear diagnosis can approach performance levels similar to fellowship-trained full-time academic musculoskeletal radiologists at 1.5 T and 3 T; however, the performance may decrease with increasing MRI examination heterogeneity.