No abstract

Midline shift (MLS) is a well-established factor used for outcome prediction in traumatic brain injury, stroke and brain tumors. The importance of automatic estimation of MLS was recently highlighted by ACR Data Science Institute. In this paper we introduce a novel deep learning based approach for the problem of MLS detection, which exploits task-specific structural knowledge. We evaluate our method on a large dataset containing heterogeneous images with significant MLS and show that its mean error approaches the inter-expert variability. Finally, we show the robustness of our approach by validating it on an external dataset, acquired during routine clinical practice.

During the pandemic of novel coronavirus infection (COVID-19), computed tomography (CT) showed its effectiveness in diagnosis of coronavirus infection. However, ionizing radiation during CT studies causes concern for patients who require dynamic observation, as well as for examination of children and young people. For this retrospective study, we included 15 suspected for COVID-19 patients who were hospitalized in April 2020, Russia. There were 4 adults with positive polymerase chain reaction (PCR) test for COVID-19. All patients underwent magnetic resonance imaging (MRI) examinations using MR-LUND PROTOCOL: Single-shot Fast Spin Echo (SSFSE), LAVA 3D and IDEAL 3D, Echo-planar imaging (EPI) diffusion-weighted imaging (DWI) and Fast Spin Echo (FSE) T2 weighted imaging (T2WI). On T2WI changes were identified in 9 (60,0%) patients, on DWI – in 5 (33,3%) patients. In 5 (33,3%) patients lesions of the parenchyma were visualized on T2WI and DWI simultaneously. At the same time, 4 (26.7%) patients had changes in lung tissue only on T2WI. (P(McNemar) = 0,125; OR = 0,00 (95%); kappa = 0,500). In those patients who had CT scan, the changes were comparable to MRI. The results showed that in case of CT is not available, it is advisable to conduct a chest MRI for patients with suspected or confirmed COVID-19. Considering that T2WI is a fluid-sensitive sequence, if imaging for the lung infiltration is required, we can recommend the abbreviated MRI protocol consisting of T2 and T1 WI. These data may be applicable for interpreting other studies, such as thoracic spine MRI, detecting signs of viral pneumonia of asymptomatic patients. MRI can detect features of viral pneumonia.

No abstract

In recent years, there has been tremendous interest in the use of artificial intelligence (AI) in radiology in order to automate the interpretation. However, uncontrolled and widespread use of AI solutions may have negative consequences. Therefore, before implementing such technologies in healthcare, thorough training of personnel, adaptation of information systems, and standardized datasets for an external validation are required. All this necessitates a formation of a unique unified methodology. The best practices of AI introduction in diagnostic radiology are still subject to debate and require new results of a scientific-practical research with the assessment of implementation conditions. This work discusses expected issues and potential solutions for the introduction of computer vision-based technologies for automatic analysis of radiological examinations with an emphasis on the real-life experience gained during simultaneous AI implementation into practice of more than a hundred state radiology departments in 2020-2021 in Moscow, Russia (an experiment). The experiment used end-user software testing approaches, quality assurance of AI-based radiological solutions, and accuracy assessment of the AI-empowered diagnostic tools on local data. The methods were adapted and optimized to ensure a successful real-life radiological AI deployment on the extraordinary large scale. The experiment involved in total around thousand diagnostic devices and thousand radiologists. AI deployment was associated with additional options in a routine radiologists workflow: triage; additional series formed by AI with indication of pathological findings and their classification; report template prepared by AI in accordance with the target clinical task, user feedback on AI performance. A multi-stage methodology for implementing AI into radiological practice that was developed and advanced during the experiment is described in this report.