Wooster Community Hospital Adopts ProFound AI for Digital
Breast Tomosynthesis to Optimize Breast Cancer Screening and Improve Workflow
iCAD’s educational webinar series recently featured Gabriele
Pedicelli, MD, Radiologist at Wooster Community Hospital, who shared how
ProFound AI™ not only improved workflow at his facility, it also resulted in a
positive impact on his practice’s bottom line. Learn how this leading-edge AI
tool empowered Dr. Pedicelli and his team to increase the number of cases seen
per day and boost revenues, without increasing expenses.
Listen to the recording of this webinar here.
“Adopting ProFound AI was straightforward. It increases
our comfort level knowing that the technology is reading every image, or slice,
and it’s reassuring knowing that this technology will help us not miss a
Pedicelli, MD, Radiologist at Wooster Community Hospital
The Story of Wooster Community Hospital
Wooster Community Hospital is a 175-bed, full service and
acute-care facility serving residents of Wayne County, Ohio. The hospital
offers a comprehensive range of inpatient and outpatient services, including
radiology examinations. Of the 85,000 radiology exams performed each year,
about 4,900 are mammography related. Gabriele Pedicelli, MD, a radiologist at
Wooster Community Hospital, reviews the majority of breast screening cases at
the facility, an average of 75-90 relative value units (RVUs) per day.
Wooster Community Hospital became one of the first
facilities in Ohio to adopt ProFound AI for Digital Breast Tomosynthesis (DBT)
in 2019, after first upgrading to 3D mammography in 2016 and later adopting the
technology to move to synthesized views.
ProFound AI for DBT is the first FDA-cleared software with
artificial intelligence for DBT. Its algorithm was trained with the latest in
deep-learning artificial intelligence (AI) to detect malignant soft tissue densities
and calcifications with unrivaled accuracy. Designed to be used concurrently by
radiologists reading 3D mammography, the software 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. The study showed 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
“Adopting ProFound AI was a seamless process that offered
immediate benefits to our radiologists and patients, and we have gained
additional efficiencies since then.”
– David Harrison, MBT, RT (R) (N), Director of Imaging
Services, Wooster Community Hospital
Adjusting to New Technology
After ProFound AI was installed, the team at Wooster was
able to quickly incorporate it into daily practice, with little to no learning
“Adopting ProFound AI was straightforward. It increases our
comfort level knowing that the technology is reading every image, or slice, and
it’s reassuring knowing that this technology will help us not miss a cancer,”
explains Dr. Pedicelli. “I typically will read the images without ProFound AI
first, just to get a gut impression of the case, but when I turn ProFound AI on,
it gives me added peace of mind knowing that the technology will alert me to
look at certain images more closely.”
“Since we were doing DBT already, implementing ProFound AI
just made sense,” adds Harrison. “Adopting ProFound AI was a seamless process
that offered immediate benefits to our radiologists and patients, and we have
gained additional efficiencies since then.”
Benefits for Clinicians and Patients
Upon implementation, ProFound AI began to offer benefits to
both clinicians and patients at Wooster Community Hospital.
“ProFound AI significantly reduces the time it takes to
review 3D tomo datasets, thus reducing the amount of time needed between
patients,” according to Harrison. “The technology allows us to fully harness
the advantages our 3D mammography system offers and improves our overall
efficiency, which allows us to see more patients throughout the day within the
Since adopting the technology (synthesized views and
ProFound AI), the team at Wooster found the average number of patients seen per
day increased from 19 to 24; this increase in patient volume has also increased
revenues by more than $79K per year.
“We’ve also had fewer callbacks,” adds Dr. Pedicelli.
“Because we’re doing less diagnostics, we’re now free to do more screenings.”
Additionally, Dr. Pedicelli notes that ProFound AI is
especially helpful in reviewing cases with dense breasts, which can be more
challenging to read.
“Currently, dense breasts are considered a risk factor
because dense breast tissue masks cancerous tissue on mammography images.
ProFound AI not only helps us to review cases with fatty tissue, we see an even
greater benefit for those women with dense breasts,” according to Dr.
Pedicelli. “Before ProFound AI, I might have read a case with dense breasts and
thought ‘Let’s call them back in 6 months or a year,’ but with ProFound AI, we
can more easily tell whether we should be doing another examination or biopsy.
In fact, there have been two recent cases with dense breasts in a short period
of time where ProFound AI helped us make the decision for a follow up, and they
both turned out to be cancers.”
Overall the team at Wooster found the technology enhanced
breast cancer screening and improved sensitivity and specificity, allowing them
to more quickly and confidently detect cancers sooner, with fewer callbacks and
“I would certainly recommend ProFound AI to other
radiologists and imaging centers,” said Dr. Pedicelli. “Based on my experience
reading mammography, I typically feel comfortable making the call of whether it
is negative or positive, but the added confidence of calling something negative
is the most significant advantage this technology offers to patients.”
- 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
Contributed to by:
Gabriele Pedicelli, MD, Radiologist, Wooster Community Hospital
David Harrison, MBT, RT (R) (N), Director of Imaging Services, Wooster
Danelle Jordan, RT (R), (M), Lead Mammography Technologist, Wooster Community