Deep Learning-based Identification of Brain MRI Sequences Using a Model Trained on Large Multicentric Study Cohorts.

Purpose To develop a fully automated device- and sequence-independent convolutional neural network (CNN) for reliable and high-throughput labeling of heterogeneous, unstructured MRI data. Materials and Methods Retrospective, multicentric brain MRI data (2179 patients with glioblastoma, 8544 examinations, 63 327 sequences) from 249 hospitals and 29 scanner types were used to develop a network based on ResNet-18 architecture to differentiate nine MRI sequence types, including T1-weighted, postcontrast T1-weighted, T2-weighted, fluid-attenuated inversion recovery, susceptibility-weighted, apparent diffusion coefficient, diffusion-weighted (low and high b value), and gradient-recalled echo T2*-weighted and dynamic susceptibility contrast-related images. The two-dimensional-midsection images from each sequence were allocated to training or validation (approximately 80%) and testing (approximately 20%) using a stratified split to ensure balanced groups across institutions, patients, and MRI sequence types. The prediction accuracy was quantified for each sequence type, and subgroup comparison of model performance was performed using χ2 tests. Results On the test set, the overall accuracy of the CNN (ResNet-18) ensemble model among all sequence types was 97.9% (95% CI: 97.6, 98.1), ranging from 84.2% for susceptibility-weighted images (95% CI: 81.8, 86.6) to 99.8% for T2-weighted images (95% CI: 99.7, 99.9). The ResNet-18 model achieved significantly better accuracy compared with ResNet-50 despite its simpler architecture (97.9% vs 97.1%; P ≤ .001). The accuracy of the ResNet-18 model was not affected by the presence versus absence of tumor on the two-dimensional-midsection images for any sequence type (P > .05). Conclusion The developed CNN (www.github.com/neuroAI-HD/HD-SEQ-ID) reliably differentiates nine types of MRI sequences within multicenter and large-scale population neuroimaging data and may enhance the speed, accuracy, and efficiency of clinical and research neuroradiologic workflows. Keywords: MR-Imaging, Neural Networks, CNS, Brain/Brain Stem, Computer Applications-General (Informatics), Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2023.

Corticosteroids use and neurocognitive functioning in patients with recurrent glioblastoma: Evidence from European Organization for Research and Treatment of Cancer (EORTC) trial 26101.

Background: In patients with recurrent glioblastoma, corticosteroids are frequently used to mitigate intracranial pressure and to improve patient neurological functioning. To date, in these patients, no systematic studies have been performed to assess neurocognitive functioning (NCF) in relation to corticosteroid treatment. Methods: Using baseline data (ie, prior to randomization) of European Organization for Research and Treatment of Cancer (EORTC) trial 26101, we performed regression analysis to assess the predictive value of corticosteroid intake on performance of the EORTC brain tumor clinical trial NCF test battery. The battery is comprised of the Hopkins Verbal Learning Test-Revised (HVLT-R), Controlled Oral Word Association Test (COWA), and Trail Making Test (A and B). Results: Out of 321 patients, 148 (46.1%) were not using corticosteroids, and 173 were using dexamethasone (34.3%), methylprednisolone (9.7%), or other corticosteroids (9.9%). Patients on corticosteroids had worse performance on all neurocognitive tests. Regression analyses demonstrated a negative association between corticosteroids use and the HVLT-R free recall score (R 2 change = 0.034, F change (1, 272) = 13.392, P < .001) and HVLT-R Delayed Recall score (R 2 change = 0.028, F change (1, 270) = 10.623, P = .002). No statistically significant association was found for HVLT-R Delayed recognition, COWA, TMT part A and TMT part B (P > .05). Conclusions: Glioblastoma patients prescribed with corticosteroids show poorer memory functions, expressive language, visual-motor scanning speed, and executive functioning than patients not using corticosteroids. Furthermore, we found a negative association between corticosteroid intake and memory functions. The possibility of deleterious effects of corticosteroids on NCF should be considered during clinical decision making.

A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging.

Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging community.