News | Artificial Intelligence | December 03, 2019

AI Improves Chest X-ray Interpretation

#RSNA19 A sophisticated type of artificial intelligence (AI) can detect clinically meaningful chest X-ray findings as effectively as experienced radiologists, according to a study published in the journal Radiology.

Image courtesy of GE Healthcare

December 3, 2019 — A sophisticated type of artificial intelligence (AI) can detect clinically meaningful chest X-ray findings as effectively as experienced radiologists, according to a study published in the journal Radiology. Researchers said their findings, based on a type of AI called deep learning, could provide a valuable resource for the future development of AI chest radiography models.

Chest radiography, or X-ray, one of the most common imaging exams worldwide, is performed to help diagnose the source of symptoms like cough, fever and pain. Despite its popularity, the exam has limitations.

“We’ve found that there is a lot of subjectivity in chest X-ray interpretation,” said study co-author Shravya Shetty, an engineering lead at Google Health in Palo Alto, Calif. “Significant inter-reader variability and suboptimal sensitivity for the detection of important clinical findings can limit its effectiveness.”

Deep learning, a sophisticated type of AI in which the computer can be trained to recognize subtle patterns, has the potential to improve chest X-ray interpretation, but it too has limitations. For instance, results derived from one group of patients cannot always be generalized to the population at large.

Researchers at Google Health developed deep learning models for chest X-ray interpretation that overcome some of these limitations. They used two large datasets to develop, train and test the models. The first dataset consisted of more than 750,000 images from five hospitals in India, while the second set included 112,120 images made publicly available by the National Institutes of Health (NIH).

A panel of radiologists convened to create the reference standards for certain abnormalities visible on chest X-rays used to train the models.

“Chest X-ray interpretation is often a qualitative assessment, which is problematic from deep learning standpoint,” said Daniel Tse, M.D., product manager at Google Health. “By using a large, diverse set of chest X-ray data and panel-based adjudication, we were able to produce more reliable evaluation for the models.”

Tests of the deep learning models showed that they performed on par with radiologists in detecting four findings on frontal chest X-rays, including fractures, nodules or masses, opacity (an abnormal appearance on X-rays often indicative of disease) and pneumothorax (the presence of air or gas in the cavity between the lungs and the chest wall).

Radiologist adjudication led to increased expert consensus of the labels used for model tuning and performance evaluation. The overall consensus increased from just over 41 percent after the initial read to more than almost 97 percent after adjudication.

The rigorous model evaluation techniques have advantages over existing methods, researchers said. By beginning with a broad, hospital-based clinical image set, and then sampling a diverse set of cases and reporting population adjusted metrics, the results are more representative and comparable. Additionally, radiologist adjudication provides a reference standard that can be both more sensitive and more consistent than other methods.

“We believe the data sampling used in this work helps to more accurately represent the incidence for these conditions,” Tse said. “Moving forward, deep learning can provide a useful resource to facilitate the continued development of clinically useful AI models for chest radiography.”

“The NIH database is a very important resource, but the current labels are noisy, and this makes it hard to interpret the results published on this data,” Shetty said. “We hope that the release of our labels will help further research in this field.”

For more information: www.rsna.org

Related Content

Table 1. Compared to 2-D mammography, which yields four images per patient, digital breast tomosynthesis (DBT), or 3-D mammography, produces hundreds of images per patient. While this provides more information for clinicians, the exponential increase in data can result in reader fatigue and burnout, which may ultimately affect patient care.

Table 1. Compared to 2-D mammography, which yields four images per patient, digital breast tomosynthesis (DBT), or 3-D mammography, produces hundreds of images per patient. While this provides more information for clinicians, the exponential increase in data can result in reader fatigue and burnout, which may ultimately affect patient care.

Sponsored Content | Case Study | Artificial Intelligence | April 09, 2020
As the largest independent imaging group in Michigan with 10 locations across the state,...
The interior of the German air force Airbus A-310 Medivac in Cologne, Germany, before its departure to Bergamo, Italy, March 28 to being ferrying COVID-19 patients to Germany for treatment to aid the Italians, whose healthcare system has been overwhelmed by the rapid spread of the coronavirus pandemic. Bundeswehr Photo by Kevin Schrief.

The interior of the German air force Airbus A-310 Medivac in Cologne, Germany, before its departure to Bergamo, Italy, March 28 to being ferrying COVID-19 patients to Germany for treatment to aid the Italians, whose healthcare system has been overwhelmed by the rapid spread of the coronavirus pandemic. Bundeswehr Photo by Kevin Schrief. Find more images from the COVID-19 pandemic.

 

Feature | Coronavirus (COVID-19) | April 08, 2020 | By Melinda Taschetta-Millane and Dave Fornell
In an effort to keep the imaging field updated on the latest information being released on coronavirus (COVID-19), th
#COVID19 #Coronavirus #2019nCoV #Wuhanvirus #SARScov2  The first of three clinical scenarios presented to the panel with final recommendations. Mild features refer to absence of significant pulmonary dysfunction or damage. Pre-test probability is based upon background prevalence of disease and may be further modified by individual’s exposure risk. The absence of resource constraints corresponds to sufficient availability of personnel, personal protective equipment, COVID-19 testing, hospital beds, and/or ve

 The first of three clinical scenarios presented to the panel with final recommendations. Mild features refer to absence of significant pulmonary dysfunction or damage. Pre-test probability is based upon background prevalence of disease and may be further modified by individual’s exposure risk. The absence of resource constraints corresponds to sufficient availability of personnel, personal protective equipment, COVID-19 testing, hospital beds, and/or ventilators with the need to rapidly triage patients. Contextual detail and considerations for imaging with CXR (chest radiography) versus CT (computed tomography) are presented in the text. (Pos=positive, Neg=negative, Mod=moderate). [Although not covered by this scenario and not shown in the figure, in the presence of significant resources constraints, there is no role for imaging of patients with mild features of COVID-19.] Image courtesy of the journal Radiology

News | Coronavirus (COVID-19) | April 07, 2020
April 7, 2020 — A multinational consens...
#COVID19 #Coronavirus #2019nCoV #Wuhanvirus #SARScov2 Chest CT findings of pediatric patients with COVID-19 on transaxial images. (a) Male, 2 months old, 2 days after symptom onset. Patchy ground-glass opacities GGO in the right lower lobe

Chest CT findings of pediatric patients with COVID-19 on transaxial images. Male, 2 months old, 2 days after symptom onset. Patchy ground-glass opacities GGO in the right lower lobe. Image courtesy of Radiology: Cardiothoracic Imaging

News | Coronavirus (COVID-19) | April 06, 2020
April 6, 2020 — Children and teenagers with COVID-19...
A recent study earlier this year in the journal Nature, which included researchers from Google Health London, demonstrated that artificial intelligence (AI) technology outperformed radiologists in diagnosing breast cancer on mammograms
Feature | Breast Imaging | April 06, 2020 | By Samir Parikh
A recent study earlier this year in the journal Nature,
Varian received FDA clearance for its Ethos therapy in February 2020. It is an adaptive intelligence solution that uses onboard AI in the treatment system to take the cone beam CT imaging on the system, compare it to the treatment plan and deliver an entire adaptive treatment plan in a typical 15-minute treatment time slot, from patient setup through treatment delivery.

Varian received FDA clearance for its Ethos therapy in February 2020, shown here displayed for the first time at ASTRO 2019. It is an adaptive intelligence solution that uses onboard AI in the treatment system to take the cone beam CT imaging on the system, compare it to the treatment plan and deliver an entire adaptive treatment plan in a typical 15-minute treatment time slot, from patient setup through treatment delivery.

Feature | Treatment Planning | April 03, 2020 | Dave Fornell, Editor
The traditional treatment planning process takes days to create an optimized radiation therapy delivery plan, but new
An example of Philips’ TrueVue technology, which offers photo-realistic rendering and the ability to change the location of the lighting source on 3-D ultrasound images. In this example of two Amplazer transcatheter septal occluder devices in the heart, the operator demonstrating the product was able to push the lighting source behind the devices into the other chamber of the heart. This illuminated a hole that was still present that the occluders did not seal.

An example of Philips’ TrueVue technology, which offers photo-realistic rendering and the ability to change the location of the lighting source on 3-D ultrasound images. In this example of two Amplazer transcatheter septal occluder devices in the heart, the operator demonstrating the product was able to push the lighting source behind the devices into the other chamber of the heart. This illuminated a hole that was still present that the occluders did not seal. Photo by Dave Fornell

Feature | Radiology Imaging | April 02, 2020 | By Katie Caron
A new year — and decade — offers the opportunity to reflect on the advancements and challenges of years gone by and p
#COVID19 #Coronavirus #2019nCoV #Wuhanvirus

Getty Images

Feature | Coronavirus (COVID-19) | April 02, 2020 | Jilan Liu and HIMSS Greater China Team
Information technologies have played a pivotal role in China’s response to the novel coronavirus...