With the ongoing COVID-19 pandemic decreasing availability of polymerase chain reaction with reverse transcription and the snowballing growth of medical imaging, especially the number of chest computed tomography (CT) scans being performed, methods to augment and automate the image analysis, increasing productivity and minimizing human error are of particular importance. The creation of high-quality datasets is essential for the development and validation of artificial intelligence algorithms. Such technologies have sufficient accuracy in diagnosing COVID-19 in medical imaging. The presented large-scale dataset contains anonymized human CT scans with COVID-19 features as well as normal studies. Some studies were tagged by radiologists using binary pixel masks of regions of interest (e.g., characteristic areas of consolidation and ground-glass opacities). CT data were acquired between March 1, 2020, and April 25, 2020, and provided by municipal hospitals in Moscow, Russia. The presented dataset is licensed under Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0).
ГБУЗ «Научно-практический центр медицинской радиологии Департамента здравоохранения города Москвы», Москва, Россия В 2017 г. в г. Москве начат проект «Московский скрининг рака легкого» путем применения низкодозной компьютерной томографии (НДКТ), направленный на проведение селективного скрининга злокачественных новообразований (ЗНО) легкого в амбулаторно-поликлиническом звене. Основная задача проекта: повысить выявляемость рака легкого на ранних стадиях и в перспективе снизить смертность от этого заболевания. Цель исследования: оценить значимость случайных находок, выявляемых в процессе селективного скрининга рака легкого методом НДКТ в г. Москве. Материал и методы. В ретроспективное исследование включены случайно отобранные 254 НДКТ, выполненные в рамках программы скрининга. При повторном просмотре изображений и протоколов учитывали все патологические находки (кроме очагов в легких, оцененных по классификации «LungRADS-2014»). Результаты. При анализе распространенности и характера случайных находок, выявляемых при НДКТ-скрининге, установлено, что в большинстве случаев такие находки имеют высокую клиническую и/или прогностическую значимость. Наиболее часто выявляются (% от числа лиц со случайными находками): кальциноз коронарных артерий-49,3%; утолщение стенок бронхов-34,9%; бронхоэктазы-34,9%; эмфизема-21,6%. При первичных интерпретациях результатов НДКТ недостаточное внимание уделяется описанию патологических изменений, кроме классифицируемых по «Lung RADS-2014» очагов. Требуется дальнейшая научно-методическая работа по организации выявления и обоснованной маршрутизации лиц со случайными находками. Выводы. Случайные находки встречаются в 87,1% случаев при проведении селективного скрининга рака легкого методом НДКТ. Наиболее часто случайные находки локализуются в сердечно-сосудистой (75,4%) и дыхательной (68,3%) системах, при этом они носят клинически и прогностически значимый характер.
BACKGROUND: The increased frequency of chest computed tomography utilization in the fight against COVID-19 has made usage of low-dose computed tomography necessary to reduce the radiation dose while preserving diagnostic quality. However, in the published literature, there were no data on the effect of body mass index on low-dose computed tomography accuracy in patients with COVID-19. AIM: To assess the effect of patient body mass index on the level of agreement between radiologists interpreting standard-dose computed tomography and low-dose computed tomography in COVID-19-associated pneumonia using visual semiquantitative CT 04 scale. MATERIALS AND METHODS: In this retrospective multicenter study, each participant underwent two consecutive chest scans at a single visit using standard-dose and low-dose protocols. Standard-dose and low-dose computed tomography with pulmonary and soft tissue kernels were interpreted using a visual semiquantitative CT 04 grading system. Data for each protocol were grouped by body mass index value (threshold value for pathology was equal to 25 kg/m2). Agreement was calculated based on binary and weighted classifications. One-way ANOVA analysis of variance was used to assess the presence of statistically significant differences in the mean for the groups. RESULTS: Two hundred thirty patients met the established inclusion criteria for the study. The experts processed 4 studies for each patient: standard-dose and low-dose computed tomography with pulmonary and soft tissue kernels. The proportion of normal-weight patients was 31% (71 subjects), and the samples median body mass index was 27.5 (18.3; 48.3) kg/m2. There were no statistically significant differences in intergroup pairwise comparisons for both the binary and weighted classifications (p values were 0.09 and 0.12, respectively). The group of overweight patients was further subdivided according to the degrees of obesity; however, the results were invariant to this division (no statistically significant differences: for the most different body mass index groups normal and 3rd degree obesity p-value 0.17). CONCLUSION: Body mass index does not affect chest standard-dose and low-dose computed tomography interpretation in COVID-19 using the visual semiquantitative CT 04 grading system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.