Whitney J. Palmer has been with Diagnostic Imaging since 2011, serving as the Senior Editor since November 2019. She has 20 years experience in healthcare and academic medicine reporting.

Whitney J. Palmer

The performance of a new artificial intelligence (AI) algorithm used to assess chest X-rays for the presence of tuberculosis was virtually equivalent to that of radiologists.

, a team of investigators from South Korea shared the results of how well their algorithm evaluated these scans. Chest X-ray is the go-to scan for detecting and assessing tuberculosis.

Finding an effective and efficient way to analyze these scans quickly is critical, they said. The countries most affected by the disease are also ones that are least likely to have enough providers who are skilled in detection.

To meet this need, the team, led by Seowoo Lee from the Seoul National University Hospital’s radiology department, created an algorithm that could identify active pulmonary tuberculosis on chest X-rays. They used 6,654 scans from patients with active disease and those who had recovered to train their tool. Specifically, 3,327 X-rays came from patients with pulmonary tuberculosis, and 3,182 were from patients with normal chest X-rays.

The algorithm performed well. Not only was it capable of pinpointing the presence of tuberculosis, but it outperformed pulmonologists. Its abilities were also comparable to radiologists, the team said, and it could help with categorizing patients in low-resource areas.

“The network may help radiologically triage patients with active tuberculosis by excluding healed tuberculosis in high-burden countries and may assist in monitoring the activity of mycobacterial diseases that require long-term treatment,” they said.

To reach these results, the team assessed their model’s performance with two datasets. Set 1 included 89 patients and 148 X-rays, and Set 2 was comprised on controlled data from 366 patients and more than 3,700 images.

According to the analysis from two pulmonologists and two thoracic radiologists, the algorithm produced a slightly higher area under the curve for Set 1 than one pulmonologist – 0.83 compared with 0.69, respectively. Performance was similar to that from the radiologists – 0.79 to 0.80. With Set 2, the model’s area under the curve (0.84) was, once again, higher than the pulmonologists (0.71) and comparable to the radiologist (0.79 and 0.80).

Based on these outcomes, the team said, the algorithm has the potential to catch more cases of tuberculosis, bringing a higher level of patient care to infected individuals.

“If a deep learning network can accurately differentiate active tuberculosis from healed tuberculosis on radiographs, then this will provide more efficient triage for testing in limited-resource settings by decreasing unnecessary testing individuals less likely to have active tuberculosis,” they said.

For more coverage based on industry expert insights and research, subscribe to the Diagnostic Imaging e-Newsletter 

Articles

Tool outperformed pulmonologists for detection of the infection.

Chest X-Ray Algorithm on Par with Radiologists for Tuberculosis Detection

Pairing PET/MRI imaging with radiopharmaceuticals can offer double benefits to patients. Not only can it accurately pinpoint malignant brain tumors, but it can help individuals side-step invasive procedures.

Although this combination, including radiopharmaceuticals, such as 

F-FET), is already known to improve diagnostic performance, less is known about the role it plays in clinical decision-making.

a team of investigators from Germany examined how the combination worked with patients who have brain tumors.

For their study, the team led by Cornelia Brendle from the University Hospital Tuebingen radiology department, evaluated how well 

F-FET PET/MR performed in detecting malignant brain tumors. Not only did the combination pinpoint these tumors with 85-percent accuracy, it also changed patient management decisions in 33 percent of cases. Additionally, the findings from the combination helped 20 percent of patients avert unnecessary follow-up procedures.

Based on these outcomes, the team said, it is possible that the combination could help patients who have non-malignant brain tumors who could likely fare better with a watchful waiting approach.

To reach their results, the team conducted a retrospective investigation with 189 patients who had brain tumors and who underwent multi-parametric 

F-FET PET/MR imaging between 2017 and 2018. Patients were considered to have a new diagnosis if the scan detected any untreated, suspicious lesions.

According to their analysis, in 93 percent of cases, this combination approach was able to successfully detect both actively growing malignant tumors or those that were being successfully treated. Consequently, this type of imaging option could help inform clinical decisions that could bring the most appropriate treatment options to patients in the most timely way.

Although further research is needed, the team said, the combination approach can offer benefits to patients.

F-FET PET to MRI…in a hybrid scanner has been reported to be reasonable in terms of cost-effectiveness in selected patients,” they said.

Combination can also help patients avoid unnecessary invasive procedures.

PET/MRI + Radiopharmaceuticals Can Identify Malignant Brain Tumors

If you use ultrasound gel regularly, you’ll want to pay attention to a recent recall from the U.S. Food & Drug Administration (FDA).

In an Aug. 4 announcement, the FDA recalled eight lots of Eco-Med Pharmaceuticals ultrasound gel, citing contamination.

As of publication time 15 patients have contracted confirmed bacterial infections from the Eco-Gel 200 ultrasound gel. Additional cases are suspected but have not been confirmed.

Eco-Gel advised its customers to immediately discontinue use of the product and return it, if possible.

“Eco-Med has initiated this recall and quarantine due to bacterial contamination in the affected lots of ultrasound gel with 

complex (Bcc),” officials said in the FDA notification. “The source(s) of the bacterial contamination is currently unknown. Eco-Med is conducting a comprehensive investigation to determine the root cause of this contamination and take all necessary corrective action.”

Affected patients can be asymptomatic, or they could develop a serious infection, such as bloodstream infections that can cause sepsis or death.

Lot number B029, distributed March 26, 2021

Lot number B030, distributed March 30, 2021

Lot number B031, distributed April 5, 2021

Lot number B032, distributed April 7, 2021

Lot number B040, distributed April 26, 2021

Lot number B041, distributed April 26, 2021

Lot number B055, distributed May 26, 2021

The lots were sold under these brand names in the United States:

MediChoice Ultrasound Gel, by Owens & Minor

MediChoice Ultrasound Gel, by Mac Medical Supply Co.

Gel was sold under eight different brand names.

FDA Recalls 8 Lots of Ultrasound Gel for Contamination

Utilization of head and neck CT angiography (CTA) in the emergency department ballooned, outpacing all other neurological exams.

a team of investigators from the Georgia Institute of Technology (Georgia Tech) determined that the compound annual growth rate for these scans was 25 percent to 27 percent from 2007 to 2017. Unenhanced head CT was the most common neuroimaging exam in the emergency department, they said.

“The rapid growth of head and neck CTA observed in the fee-for-service Medicare population is also observed in the commercially insured and Medicare Advantage populations,” said Selin Merdan, Ph.D., associate director of the Value Analytics Lab in Georgia Tech’s department of industrial and systems engineering.

For their study, Merdan’s team evaluated the annual emergency department utilization of head CT, head MR, head CTA, neck CTA, head MR angiography (MRA), neck MRA, and carotid duplex ultrasound. They based their assessment on patient-level claims from Optum’s De-identified Clinformatics Data Mart database – a database that includes between 12 million and 14 million commercial and Medicare Advantage health plan enrollees.

They adjusted utilization rates using annual relative proportions of age groups and stratified by patient demographics, payer type, and provider state to account for an older sample population.

Based on their analysis, they determined emergency department neuroimaging use spiked 72 percent overall during the study period. Specifically, they found these increases: 69 percent for head CT, 67 percent for MRI, 1,100 percent for head CTA, 1,300 percent for neck CTA, 36 percent for head MRA, 52 percent for neck MRA. They also identified a slight drop of 8 percent for carotid duplex ultrasound.

Credit: American Journal of Roentgenology

In addition, among patients 65 and older, head CT and CTA of the head and neck experienced a continuous increase of 48 percent and 1,011 percent, respectively, for every 1,000 emergency department visits.

These findings, the team said, warrant paying closer attention to neuroimaging use in the emergency department.

“The appropriateness of this growth should be monitored as the indications for CTA expand and more incidental findings are uncovered,” the team said.

Use of head and neck CTA has increased significantly among commercially insured and Medicare Advantage patients. 

Whitney J. Palmer

Articles

Chest X-Ray Algorithm on Par with Radiologists for Tuberculosis Detection

PET/MRI + Radiopharmaceuticals Can Identify Malignant Brain Tumors

FDA Recalls 8 Lots of Ultrasound Gel for Contamination

ED Neuroimaging Spikes over Decade