Sponsored Content | Case Study | Artificial Intelligence | April 09, 2020

From Surviving to Thriving: How Regional Medical Imaging Enhanced Productivity and Profitability with ProFound AI for Digital Breast Tomosynthesis

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.

As the largest independent imaging group in Michigan with 10 locations across the state, Regional Medical Imaging (RMI) has been providing superior imaging services for 35 years. Co-owner and CEO, Randy Hicks, M.D., MBA, provides both a clinical and pragmatic approach to running the business, which has led RMI to become one of the leading radiology facilities in the state, with a team of experts in women’s imaging and other subspecialties.

Hicks takes pride in ensuring that RMI features the latest in state-of-the-art technology that empowers his team to provide the best possible patient care. In 2018, RMI adopted DBT systems across all 10 of its locations. But while digital breast tomosynthesis (DBT), also known as 3-D mammography, offers a number of benefits to patients, such as enhanced breast cancer detection and fewer false positives and unnecessary recalls, it produces hundreds of images per patient, compared to 2-D mammography which typically only produces four images per patient. 

“We were starting to feel like we were on the Titanic. The exponential increase of images quickly began to take its toll on the team,” Hicks said. “Mammograms can be anxiety inducing for women, and ultimately they just want the report that says negative. With the increased workload from DBT we were taking longer to get those results to our patients. We needed a solution to manage this workload, and we needed it badly. The minute ProFound AI was FDA-cleared, we knew we had to have it at RMI.”

In December 2018, ProFound AI for DBT became the first and only software for DBT with artificial intelligence (AI) to be FDA-cleared. Designed to be used concurrently by radiologists reading 3-D mammography, the technology was trained with the latest in deep-learning AI to detect malignant soft tissue densities and calcifications with unrivaled accuracy. It is the only software of its kind that rapidly and accurately analyzes each DBT image, or slice, and provides radiologists with crucial information, such as Certainty of Finding lesion and Case Scores, which can assist in clinical decision-making and prioritizing caseloads. 

Positive clinical results from a large reader study were recently published in Radiology: Artificial Intelligence. In a large reader study, ProFound AI for DBT increased radiologists’ sensitivity by 8 percent, minimized the rate of false positives and unnecessary recalls by 7 percent, and reduced reading time for radiologists by 52.7 percent.1

 

The Paradigm Shift

Upon implementation of ProFound AI, the team at RMI immediately began to experience a number of benefits, including improved cancer detection, a reduction in biopsy rates and a reduction in unnecessary recalls. Reading time for radiologists was also substantially reduced — and the team at RMI found ProFound AI to be even more reliable than expected. 

“The paradigm really shifts when you get ProFound AI — it changes the way you read. Once you use it, it’s really quite shocking how impressive it is,” said Hicks. “The technology itself is better than humans. Once we started using ProFound AI, we realized we are finding more cancers,” Hicks stated. “It takes time to trust it — but believe me, you can trust it. ProFound AI definitely finds more cancers than we do.”

Hicks and the radiologists at RMI found the software to be particularly helpful not just in finding cancers and reducing the time to read, but also in prioritizing caseloads.

“If I am behind on mammograms, I can easily sort by which ones need to be prioritized. We can be much more efficient in sorting cases and getting things done. Speed is important and this technology really does speed our reading time up,” he added.

Hicks also found that ProFound AI improved radiologist performance as a whole across all of the radiologists in his practice. 

“The variability in which people read mammograms is real,” said Hicks. “As a large radiology practice reading 31,000 mammograms per year, we don’t want outliers when it comes to our radiologist performance. ProFound AI acts as a friend in the room for radiologists and actually helps them to learn and improve over time.”

 

The Bottom Line

As the owner and CEO of RMI, Hicks is not only concerned about the health of his patients, he is also concerned about the welfare of the business. Although adopting DBT offered better image quality and more information than ever before, the time it took to read cases was starting to affect the company’s bottom line.

“Although DBT offered improved image quality, we found it required a steep learning curve and the increased workload resulted in a case backlog that required additional staffing to combat,” Hicks mentioned. “For example, a radiologist reviewing 100 cases per day with 2-D would typically review 400 images per day, whereas a radiologist reading 100 cases per day with DBT would be required to read almost 30,000 images per day.” (See Table 1.)

“ProFound AI improved our reading efficiency and eliminated the need to hire more staff,” he added. “The cost of ProFound AI pays for itself based on improved productivity alone.”

For more information: www.icadmed.com

Reference

1. Conant, E. et al. (2019). Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis. Radiology: Artificial Intelligence. 1 (4). Accessed via https://pubs.rsna.org/doi/10.1148/ryai.2019180096

Related Content

Radiologists have recently taken on the role of activists and are tackling pressing issues in healthcare, including breast density

Getty Images

Feature | Women's Health | January 20, 2021 | By Fazila Seker, Ph.D.
Radiologists — who have long been professionals in the metaphorical and literal back-rooms of healthcare — have recen
The key trends Clinicians reviewing a COVID-19 patient's lung CT that reveals the severity of COVID-caused pneumonia. The impact of COVID on radiology was a major, over arching trend at  the 2020 Radiological Society of North America (RSNA) meeting. Getty Imagesbserved at 2020 Radiological Society of North America (RSNA) meeting all focused around COVID-19 (SARS-CoV-2) and the impact it has had on radiology. #RSNA #RSNA20 #RSNA2020

Clinicians reviewing a COVID-19 patient's lung CT that reveals the severity of COVID-caused pneumonia. The impact of COVID on radiology was a major, over arching trend at  the 2020 Radiological Society of North America (RSNA) meeting. Getty Images

Feature | RSNA | January 20, 2021 | By Melinda Taschetta-Millane and Dave Fornell
AI Metrics, LLC, a medical imaging startup focused on augmented intelligence to improve patient care, announced today that the U.S. Food and Drug Administration (FDA) has granted 510(k) clearance for the company’s flagship image analysis platform.
News | Artificial Intelligence | January 18, 2021
January 18, 2021 — AI Metrics, LLC, a medical imaging startup focused on augmented intelligence to improve patient ca
A, Contrast-enhanced axial T1-weighted fat-saturated image from baseline MRI before initiation of neoadjuvant therapy shows irregular mass (arrow) in upper inner right breast corresponding to biopsy-proven carcinoma. B, Contrast-enhanced axial T1-weighted fat-saturated image from follow-up MRI performed 3 months after initiation of neoadjuvant therapy shows decrease in size of right breast cancer (arrow). C, Contrast-enhanced axial T1-weighted fat-saturated image 3 months after initiation of neoadjuvant the

A, Contrast-enhanced axial T1-weighted fat-saturated image from baseline MRI before initiation of neoadjuvant therapy shows irregular mass (arrow) in upper inner right breast corresponding to biopsy-proven carcinoma. B, Contrast-enhanced axial T1-weighted fat-saturated image from follow-up MRI performed 3 months after initiation of neoadjuvant therapy shows decrease in size of right breast cancer (arrow). C, Contrast-enhanced axial T1-weighted fat-saturated image 3 months after initiation of neoadjuvant therapy shows new mass (arrow) in upper outer left breast that was assessed as BI-RADS 4. Pathologic examination from MRI-guided core biopsy of new suspicious mass revealed benign usual ductal hyperplasia. No atypia or malignancy was identified. Image courtesy of American Roentgen Ray Society (ARRS), American Journal of Roentgenology (AJR)

News | MRI Breast | January 15, 2021
January 15, 2021 — According to ARRS' ...
A targeted intervention providing mammograms to hospitalized Medicaid patients can help patients complete overdue breast cancer screening

Getty Images

News | Mammography | January 14, 2021
January 14, 2021 — Completing cancer screening tests, such as...
DB-I website features new educational tools and streamlined user experience to improve access to medically sourced breast density content
News | Breast Density | January 13, 2021
January 13, 2021 — DenseBreast-info.org (DB-I) invites he
This cutting-edge technology assists radiologists in the interpretation of screening mammograms and allows them to diagnose breast cancer earlier and more accurately
News | Mammography | January 12, 2021
January 12, 2021 — Therapixel announced that...
The U.S. Food and Drug Administration released the agency's first Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) Action Plan. This action plan describes a multi-pronged approach to advance the Agency's oversight of AI/ML-based medical software.
News | Artificial Intelligence | January 12, 2021
January 12, 2021 — The U.S.