{"id":2272,"date":"2020-08-18T19:34:32","date_gmt":"2020-08-18T19:34:32","guid":{"rendered":"https:\/\/techclot.com\/index.php\/2020\/08\/18\/deep-learning-models-can-detect-covid-19-in-chest-ct-scans\/"},"modified":"2020-08-18T19:34:32","modified_gmt":"2020-08-18T19:34:32","slug":"deep-learning-models-can-detect-covid-19-in-chest-ct-scans","status":"publish","type":"post","link":"https:\/\/techclot.com\/index.php\/2020\/08\/18\/deep-learning-models-can-detect-covid-19-in-chest-ct-scans\/","title":{"rendered":"Deep Learning Models Can Detect COVID-19 in Chest CT Scans"},"content":{"rendered":"

Deep Learning Models Can Detect COVID-19 in Chest CT Scans<\/a><\/p>\n

<\/div>\n
\n

By Jessica Kent<\/a><\/p>\n<\/div>\n

study<\/a> published in Nature Communications<\/em>.<\/p>\n

For more coronavirus updates, visit our <\/em><\/strong>resource page<\/em><\/strong><\/a>, updated twice daily by Xtelligent Healthcare Media.<\/em><\/strong><\/p>\n

While CT scans have been useful in helping providers detect COVID-19, clinicians are discouraged from using these medical images for coronavirus diagnosis.<\/p>\n

\u201cCT evaluation has been an integral part of the initial evaluation of patients with suspected or confirmed COVID-19 in multiple centers in Wuhan China and northern Italy,\u201d researchers noted.<\/p>\n

\u201cHowever, these guidelines also recommend against using chest CT in screening or diagnostic settings in part due to similar radiographic presentation with other influenza-associated pneumonias. Techniques for distinguishing between these entities may strengthen support toward use of CT in diagnostic settings.\u201d<\/p>\n

READ MORE:<\/strong> AI, Deep Learning Start to Tackle Common Problems in Healthcare<\/a><\/p>\n

Because of the rapid increase in COVID-19 cases, artificial intelligence could play a role<\/a> in detecting and characterizing COVID-19 on medical images.<\/p>\n

\u201cCT provides a clear and expeditious window into this process, and deep learning of large multinational CT data could provide automated and reproducible biomarkers for classification and quantification of COVID-19 disease,\u201d researchers said.<\/p>\n

Investigators from NIH and NVIDIA set out to develop and evaluate a deep learning algorithm to detect COVID-19 on chest CT using data from a globally diverse, multi-institutional dataset. The team obtained COVID-19 CT scans from four hospitals across China, Italy, and Japan, where there was a wide variety in clinical timing and practice for CT use in outbreak settings.<\/p>\n

In total, researchers used 2,724 scans from 2,619 patients in this study. The study included two models that researchers used in series to come up with the COVID-19 final classification model.<\/p>\n

The first model was a segmentation model that was used to define the lung regions which were subsequently used by the classification model. Initially, the team developed two classification models \u2013 one utilizing the entire lung region with fixed input size (full 3D), and one utilizing average score of multiple regions within each lung at fixed image resolution (hybrid 3D).<\/p>\n

READ MORE:<\/strong> Deep Learning Tool Analyzes Chest X-Rays to Predict Mortality<\/a><\/p>\n

When distinguishing between COVID-19 and other conditions, the hybrid 3D model achieved validation accuracy of 92.4 percent, while the full 3D model achieved an accuracy of 91.7 percent.<\/p>\n

To evaluate the utility of these models for COVID-19 sensitivity at independent institutions, researchers removed the cohort of COVID-19 patients from Tokyo, Japan from the training and validation datasets and re-trained the models using identical algorithm configuration and hyperparameters as the original models. Overall, validation and testing accuracy were stable between models trained with and without patients from the leave-out institution.<\/p>\n

Because the models were able to distinguish between COVID-19 and other types of pneumonia demonstrates that there may be a role for AI as one element of a CT-enhanced diagnosis<\/a>, researchers said. Subsequent models could include resource allocation, point of care detection for isolation of asymptomatic patients, or monitoring for response in clinical trials for medical countermeasures.<\/p>\n

\u201cGiven the challenges in confidently distinguishing between COVID-19 associated pneumonia and other types of pneumonia, there may be a role for AI in CT-based diagnosis, characterization, or quantification of response,\u201d researchers stated.<\/p>\n

\u201cFurther work regarding the diagnostic utility of this algorithm in the setting of early vs. advanced COVID-19 related pneumonia is warranted.\u201d<\/p>\n

READ MORE:<\/strong> Deep Learning Bests Traditional Models in Risk Stratification<\/a><\/p>\n

The researchers expect that this deep learning tool could be used in cases beyond the COVID-19 pandemic.<\/p>\n

\u201cWhile CT imaging may not necessarily be actively used in the diagnosis and screening for COVID-19, this deep learning-based AI approach may serve as a standardized and objective tool to assist the assessment of imaging findings of COVID-19 and may potentially be useful as a research tool, clinical trial response metric, or perhaps as a complementary test tool in very specific limited populations or for recurrent outbreaks settings,\u201d researchers concluded.<\/p>\n

Researchers have increasingly examined medical imaging and imaging analytics as a way to better diagnose COVID-19. The New England Complex Systems Institutes recently announced<\/a> a partnership with the XPRIZE Pandemic Alliance to launch the COVID-19 CT Scan Collaborative.<\/p>\n

The initiative aims to significantly accelerate the use of CT scans for COVID-19 diagnosis and treatment.<\/p>\n

\u201cCT scans can be a real game-changer in our global battle to end coronavirus,\u201d said Yaneer Bar-Yam, PhD, President and Founder of the New England Complex Systems Institute, an independent academic research and educational institution.<\/p>\n

\u201cWe need aggressive and bold actions to reduce transmission of COVID-19 to get ahead of the outbreak so that it is stopped. It will take the global community to accelerate how we meet these challenges.\u201d<\/p>\n


<\/p>\n

Published at Tue, 18 Aug 2020 17:02:12 +0000<\/p>\n

Global Artificial Intelligence in Agriculture Market Research Report to 2030 – Growth Opportunities …<\/a><\/p>\n

DUBLIN–(BUSINESS WIRE<\/a><\/span><\/span>)–The “Artificial Intelligence in Agriculture Market Research Report: By Type, Technology, Application – Global Industry Analysis and Growth Forecast to 2030”<\/a> report has been added to ResearchAndMarkets.com’s<\/strong> offering.\n<\/p>\n

<\/blockquote>\n

\nThe revenue generated in the global AI in agriculture market share is expected to increase to $11,200.1 million in 2030 from $671.6 million in 2019, at a 30.5% CAGR during 2020-2030.\n<\/p>\n

\nService, based on type, is projected to be the faster-growing category during the forecast period. With an increasing number of farmers wanting to implement AI in their practices, the demand for training and equipment installation and maintenance services is also rising.\n<\/p>\n

\nThe highest CAGR, under the application segment of the AI in agriculture market, would be experienced by the drone analytics division. With the surging requirement for high-quality crops by the continuously growing population, heavy investments are being put into agricultural drones. The demand for such devices is rising rapidly in China and the U.S., which is driving the advance of the drone analytics division.\n<\/p>\n

\nThe most important factor leading to the growth of the AI in agriculture market is the increasing demand for food. The United Nations Department of Economic and Social Affairs (UN-DESA) claims that the worldwide population would rise from 7.7 billion currently to 8.6 billion by 2030. Additionally, with the changing consumption pattern of the populace, increasing disposable income, and high rate of urbanization, the demand for agricultural products is burgeoning.\n<\/p>\n

\nDeveloping regions are expected to offer ample opportunities to the players in the AI in agriculture market in the coming years. In emerging economies such as Brazil, India, and South Africa, the usage of AI in the agricultural domain is quite low; however, with the governments in these countries extending their support for the adoption of advanced technologies to grow crops, market players can hope to augment their revenue substantially here. For instance, the Maharashtra government began a partnership with the World Economic Forum in January 2019, to use drones for collecting insights on farmlands.\n<\/p>\n

\nSoftware is expected to witness the fastest advance in the AI in agriculture market, on the basis of product type, in the coming years. This is attributed to the fact that the use of AI for smart greenhouse management, soil management, and livestock monitoring necessitates advanced software to control and operate the complex devices and instruments. In 2019, machine learning was the largest technology category in the market, as farmers are rapidly adopting it to augment their yield, by combining data technologies with advanced agricultural science.\n<\/p>\n

\nMarket Dynamics<\/strong>\n<\/p>\n

\nTrends<\/em><\/strong>\n<\/p>\n