En Es
Categories

Industry News

Artificial Intelligence (AI) Program Accurately Predicts Lung Cancer Risk from CT Images

By Medimaging International staff writers
12 May 2021

IllustrationAn artificial intelligence (AI) program accurately predicts the risk that lung nodules detected on screening CT will become cancerous, according to a study published in the journal Radiology.

In the new study, researchers at the Radboud University Medical Center (Nijmegen, The Netherlands) developed an algorithm for lung nodule assessment using deep learning, an AI application capable of finding certain patterns in imaging data. The researchers trained the algorithm on CT images of more than 16,000 nodules, including 1,249 malignancies, from the National Lung Screening Trial. They validated the algorithm on three large sets of imaging data of nodules from the Danish Lung Cancer Screening Trial.

The deep learning algorithm delivered excellent results, outperforming the established Pan-Canadian Early Detection of Lung Cancer model for lung nodule malignancy risk estimation. It performed comparably to 11 clinicians, including four thoracic radiologists, five radiology residents and two pulmonologists. The researchers plan to continue improving the algorithm by incorporating clinical parameters like age, sex and smoking history. They are also working on a deep learning algorithm that takes multiple CT examinations as input. The current algorithm is highly suitable for analyzing nodules at the initial, or baseline, screening, but for nodules detected at subsequent screenings, growth and appearance in comparison to the previous CT are important. The researchers have developed other algorithms to reliably extract imaging features from the chest CT related to chronic obstructive pulmonary diseases and cardiovascular diseases. They will be investigating how to effectively integrate these imaging features into the current algorithm.

“The algorithm may aid radiologists in accurately estimating the malignancy risk of pulmonary nodules,” said the study’s first author, Kiran Vaidhya Venkadesh, a Ph.D. candidate with the Diagnostic Image Analysis Group at Radboud University Medical Center in Nijmegen, the Netherlands. “This may help in optimizing follow-up recommendations for lung cancer screening participants.”

“As it does not require manual interpretation of nodule imaging characteristics, the proposed algorithm may reduce the substantial interobserver variability in CT interpretation,” said senior author Colin Jacobs, Ph.D., assistant professor in the Department of Medical Imaging at Radboud University Medical Center in Nijmegen. “This may lead to fewer unnecessary diagnostic interventions, lower radiologists’ workload and reduce costs of lung cancer screening.”

Related Links:
Radboud University Medical Center



E-mail Print
FaceBook Twitter Google+ Linked in

Additional news

15 Jun 2021
Quidel Receives Amended FDA Emergency Use Authorization for New AI-Powered Sofia Q Rapid Antigen Test Device
Quidel Corporation (San Diego, CA, USA) has received an amended Emergency Use Authorization (EUA) from the US Food and Drug Administration (FDA) allowing the company to market Sofia Q, its latest addition to the Sofia and Sofia 2 line of Fluorescent Immunoassay Analyzers (FIA).
Read More
15 Jun 2021
Global PET-CT Scanner Device Market to Reach USD 3.34 Billion by 2028
The global PET-CT scanner device market size is expected to register a CAGR of 6.6% from 2021 to 2028 to reach USD 3.34 billion by 2028, driven primarily by the increasing need to overcome the shortfalls of CT and PET in oncology imaging.
Read More
11 Jun 2021
Global Clinical Chemistry Analyzers Market to Reach USD 15.97 Billion by 2028
The global clinical chemistry analyzers market is projected to grow at a CAGR of 4.25% from USD 11.45 billion in 2020 to USD 15.97 billion by 2028, driven by growth in technology, rising global population, technological improvements in point of care testing devices, and development of laboratory automation.
Read More
09 Jun 2021
Global COVID-19 Saliva Screening Test Market to Reach USD 3,406.2 Billion by 2023
The global COVID-19 saliva screening test potential market size is expected to expand at a CAGR of 4.8% from USD 2955.9 billion in 2021 to USD 3,406.2 billion by 2023, driven by a rise in the demand for rapid, efficient, saliva-based screening tests.
Read More
20 May 2021
Global Lateral Flow Assays Market to Reach USD 13.85 Billion by 2027 Due to Benefits of Rapid Tests and Growing Demand for POC Testing
The global lateral flow assays market is expected to grow at a CAGR of 8.8% from 2020 to 2027 to reach USD 13.85 billion by 2027, driven mainly by the benefits of LFA-based rapid tests over laboratory testing and growing demand for point-of-care testing.
Read More
18 May 2021
PerkinElmer to Acquire UK In-Vitro Diagnostics Company Immunodiagnostic Systems
PerkinElmer, Inc. (Waltham, MA; USA) and Immunodiagnostic Systems Holdings PLC (IDS; Boldon, Tyne and Wear, UK) have reached an agreement whereby PerkinElmer will acquire IDS for approximately USD 155 million.
Read More
14 May 2021
Siemens Launches its Fastest, Single-Source CT Scanner, Somatom X.ceed
Siemens Healthineers (Erlangen, Germany) has launched Somatom X.ceed, a new high-resolution, high-speed CT (computed tomography) scanner engineered specifically for the most challenging clinical areas where time and precision are of essence.
Read More
14 May 2021
Carestream Unveils Groundbreaking AI-Based Technology that Advances X-Ray Image Quality
Carestream Health (Rochester, N.Y., USA) has released Smart Noise Cancellation (SNC), a groundbreaking artificial intelligence (AI)-based technology that greatly improves image quality - producing images that are significantly clearer than with standard processing.
Read More
05 May 2021
Beckman Coulter Becomes First Diagnostics Company to Offer Workflow Automation Specifically for Mid-Volume Laboratories
Beckman Coulter (Brea, CA, USA) has announced the global launch of the DxA 5000 Fit, a workflow-automation solution designed to fit into medium-sized labs that run fewer than 5,000 tests a day.
Read More
Copyright © 2000-2021 TradeMed.com. All rights reserved. | Terms And Conditions