News | Advanced Visualization | May 29, 2018

Researchers Use Radiomics to Overcome False Positives in Lung Cancer CT Screening

Technology identifies 8 out of a possible 57 image feature variables that could distinguish benign and malignant tumors

Researchers Use Radiomics to Overcome False Positives in Lung Cancer CT Screening

May 29, 2018 — A team of researchers including investigators from Mayo Clinic has identified a technology to address the problem of false positives in computed tomography (CT)-based lung cancer screening. The team’s findings are published in the current issue of PLOS One.

“As physicians, one of the most challenging problems in screening patients for lung cancer is that the vast majority of the detected pulmonary nodules are not cancer,” said Tobias Peikert, M.D., a pulmonologist at Mayo Clinic. “Even in individuals who are at high risk for lung cancer, up to 96 percent of nodules are not cancer.”

Peikert said false-positive test results cause significant patient anxiety and often lead to unnecessary additional testing, including surgery. “False-positive lung cancer screening results also increase healthcare costs and may lead to unintentional physician-caused injury and mortality,” Peikert said.

To address the problem of false positives in lung cancer screening, Peikert and Fabien Maldonado, M.D., from Vanderbilt University, along with their collaborators, used a radiomics approach to analyze the CT images of all lung cancers diagnosed as part of the National Lung Cancer Screening Trial. Radiomics is a field of medicine that involves extracting large amounts of quantitative data from medical images and using computer programs to identify disease characteristics that cannot be seen by the naked eye.

Researchers tested a set of 57 variables for volume, nodule density, shape, nodule surface characteristics and texture of the surrounding lung tissue. They identified eight variables which enabled them to distinguish a benign nodule from a cancerous nodule. None of the eight variables were directly linked to nodule size and the researchers did not include any demographic variables such as age, smoking status and prior cancer history as part of their testing.

Peikert said that while the technology looks very promising and has the potential to change the way physicians evaluate incidentally detected lung nodules, it still requires additional validation.

Funding for this research was provided by the Department of Defense, in collaboration with Vanderbilt University School of Medicine.

For more information: www.journals.plos.org/plosone

Related Lung Cancer Content

Artificial Intelligence Improves Lung Cancer Detection

ACR Urges Stricter Adherence to Lung Cancer Screening Guidelines

Related Content

IBM collected a dataset of 52,936 images from 13,234 women who underwent at least one mammogram between 2013 and 2017.

IBM collected a dataset of 52,936 images from 13,234 women who underwent at least one mammogram between 2013 and 2017, and who had health records for at least one year prior to the mammogram. The algorithm was trained on 9,611 mammograms. Image courtesy of Radiology.

Feature | Artificial Intelligence | July 19, 2019 | Michal Chorev
Breast cancer is the global leading cause of cancer-related deaths in women, and the most commonly diagnosed cancer...
Videos | Computed Tomography (CT) | July 19, 2019
Quynh Truong, M.D., MPH, associate professor of radio
Low Doses of Radiation Promote Cancer-capable Cells
News | Radiation Dose Management | July 18, 2019
Low doses of radiation equivalent to three computed tomography (CT) scans, which are considered safe, give cancer-...
Paragon Biosciences Launches Qlarity Imaging to Advance FDA-cleared AI Breast Cancer Diagnosis System

Qlarity Imaging’s software is used to assist radiologists in the assessment and characterization of breast lesions. Imaging features are synthesized by an artificial intelligence algorithm into a single value, the QI score, which is analyzed relative to a database of reference abnormalities with known ground truth. Image courtesy of Business Wire.

Technology | Artificial Intelligence | July 18, 2019
Paragon Biosciences LLC announced the launch of its seventh portfolio company, Qlarity Imaging LLC, which was founded...
New Lung Ambition Alliance Aims to Double Five-year Lung Cancer Survival by 2025
News | Lung Cancer | July 17, 2019
The International Association for the Study of Lung Cancer (IASLC), Guardant Health, the Global Lung Cancer Coalition (...
Example of an intentionally truncated CT image

Figure 1: Example of an intentionally truncated CT image. The truncation percentage was calculated as the ratio of the patient border touching the field of view to the total patient border (red/(read+blue)). Image courtesy of Qaelum.

Feature | Radiation Dose Management | July 15, 2019 | Niki Fitousi, Ph.D., and An Dedulle
One of the main benefits of a radiation dose management system is the possibility to automatically generate alerts when...
Routine scan of abdomen pelvis taken with the UW-Madison’s Revolution 256 CT scanner using the FDA-cleared reconstruction algorithm, called TrueFidelity.

Routine scan of abdomen pelvis taken with the UW-Madison’s Revolution 256 CT scanner using the FDA-cleared reconstruction algorithm, called TrueFidelity. UW-Madison was the first site in the U.S. to get this technology. Its use is now being integrated into UW CT protocols. Image courtesy of Timothy P. Szczykutowicz

Feature | Computed Tomography (CT) | July 12, 2019 | By Greg Freiherr
When providers develop their own imaging protocols, they are wasting time and money, according to...
FDA Clears Koios DS Breast 2.0 AI-based Software
News | Ultrasound Women's Health | July 11, 2019
Koios Medical announced its second 510(k) clearance from the U.S. Food and Drug Administration (FDA).
Mednax National Cardiac Centers of Excellence Program Highlighted at SCCT 2019
News | CT Angiography (CTA) | July 11, 2019
Mednax Inc. and Mednax Radiology Solutions announced that Chief Medical Officer Ricardo C. Cury, M.D., FSCCT, will...