Advanced searches left 3/3

CT - U.S. Department of Veterans Affairs

Summarized by Plex Scholar
Last Updated: 23 April 2022

* If you want to update the article please login/register

Integrated Clinical and CT Based Artificial Intelligence Nomogram for Predicting Severity and Need for Ventilator Support in COVID-19 Patients: A Multi-Site Study.

Almost 75% of COVID-19 patients end up in ICU needing special mechanical ventilation assistance. For this research, eight69 patients from two sites with baseline medical history and chest CT scans were accepted. These regions were automatically classified and used alongside their respective CT volumes to prepare an imaging AI forecaster on the D1train to anticipate the need for mechanical ventilators for COVID-19 patients. An integrated clinical and AI imaging nomogram was developed using univariate analysis by the top five prognostic clinical factors identified using univariate analysis, which were combined with AIP to produce an integrated clinical and AI imaging nomogram. In predicting which COVID-19 patients would needing a ventilator, ClAIN outperformed AIP. ClAIN's results across a multitude of sites show that the disease could be identified more precisely and likely to end up on a life-saving mechanical ventilation.

Source link: https://doi.org/10.1109/JBHI.2021.3103389


Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas.

Methods and Methods The aim of this retrospective analysis, scanning or standard noncontrast CT images were obtained for 290 patients from two hospitals between 2007 and 2013. Features were reduced to prepare machine learning classifiers with 145 patients. Test Set Results Support vector machine classification curves with intranodular radiomic features reached an area under the receiver operating characteristic curve of 0. 75 on the test set. The AUC rose to 0. 80 percent after combining radiomics of intranodular with perinodular areas. RESNA, 2018 Web supplemental information is available for this article. Conclusion Intranodular and perinodular regions of nodules can tell non-small cell lung cancer adenocarcinomas from benign granulomas from benign granulomas at noncontrast CT. In this issue, see also the Nishino editorial.

Source link: https://doi.org/10.1148/radiol.2018180910

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions