A joint convolutional-recurrent neural network with an attention mechanism for detecting intracranial hemorrhage on noncontrast head CT.

To investigate the performance of a joint convolutional neural networks-recurrent neural networks (CNN-RNN) using an attention mechanism in identifying and classifying intracranial hemorrhage (ICH) on a large multi-center dataset; to test its performance in a prospective independent sample consisting of consecutive real-world patients. All consecutive patients who underwent emergency non-contrast-enhanced head CT in five different centers were retrospectively gathered. Five neuroradiologists created the ground-truth labels. The development dataset was divided into the training and validation set. After the development phase, we integrated the deep learning model into an independent center's PACS environment for over six months for assessing the performance in a real clinical setting. Three radiologists created the ground-truth labels of the testing set with a majority voting. A total of 55,179 head CT scans of 48,070 patients, 28,253 men (58.77%), with a mean age of 53.84 ± 17.64 years (range 18-89) were enrolled in the study. The validation sample comprised 5211 head CT scans, with 991 being annotated as ICH-positive. The model's binary accuracy, sensitivity, and specificity on the validation set were 99.41%, 99.70%, and 98.91, respectively. During the prospective implementation, the model yielded an accuracy of 96.02% on 452 head CT scans with an average prediction time of 45 ± 8 s. The joint CNN-RNN model with an attention mechanism yielded excellent diagnostic accuracy in assessing ICH and its subtypes on a large-scale sample. The model was seamlessly integrated into the radiology workflow. Though slightly decreased performance, it provided decisions on the sample of consecutive real-world patients within a minute.

Inter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study.

There is little evidence on the applicability of deep learning (DL) in the segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n = 2986) and B (n = 3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80%), validation (10%), and internal test (10%) sets, and six neuroradiologists created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B. The models subsequently fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist's performance, but demonstrated lower performance than the radiologist on the external tests. Fine-tuned models A and B achieved median Dice scores of 0.832 and 0.846, which were non-inferior to the radiologist's performance on the external tests. The present work shows that the inter-vendor operability of deep learning for the segmentation of ischemic lesions on DWI might be enhanced via transfer learning; thereby, their clinical applicability and generalizability could be improved.

Intrathecal use of gadobutrol for gadolinium-enhanced MR cisternography in the evaluation of patients with otorhinorrhea.

PURPOSE: Intrathecal gadolinium-enhanced MR cisternography (IGE-MRC) has a high sensitivity to detect accurate localization of cerebrospinal fluid (CSF) leakage in otorhinorrhea patients. Our purpose in this study was to describe our experience in analyzing clinically suspected CSF leakage by IGE-MRC by using gadobutrol with emphasis on its safety and diagnostic performance. METHODS: We retrospectively reviewed our imaging and clinical database for the evaluation of patients admitted to our clinic with complaints of otorhinorrhea between 2017 and 2019. Two radiologists evaluated the imaging studies independently. Consensus data was used in the analysis. Medical record review and phone call were used for the follow-up. RESULTS: Of the 85 patients included in the retrospective analysis, 82 (96.5%) had rhinorrhea and 3 (3.5%) had otorrhea. Overall, 29 patients (34.1% of all patients) underwent operation for repair of the CSF leakage site. Beta-transferrin test was available and positive in 33 patients (38.8%). Five (5.9%) patients complained headaches after the procedure and complaints were resolved with increased water intake. Postprocedurally, 3 patients (3.5%) had vertigo and 1 patient (1.2%) complained nausea but spontaneous regression were observed in a few hours. None of the patients experienced a significant complication or adverse reaction during follow-up period. Sixty-seven patients (78.8%) had medical record and telephone follow-up. Mean follow-up duration with call was 14.2 months. CONCLUSION: IGE-MRC is a minimally invasive and highly sensitive imaging technique. The current results during our follow-up demonstrate the relative safety and feasibility of IGE-MRC by using gadobutrol to evaluate CSF leakage.