NEWPORT NEWS, Va. — When Virginia Beach mother Tasha Cade shared her story with me this summer — exposing the terrifying moment she was diagnosed with breast cancer while she was pregnant — it struck a chord with people in our community.
“I started hyperventilating [when I was diagnosed with breast cancer],” Cade told me. “I was beyond angry. I had been doing my due diligence by going to see specialists, by getting my routine mammograms. And yet, my concerns were ultimately dismissed.”
“This happened to me. I was 13 weeks pregnant,” wrote a News 3 viewer under my Instagram post about Cade’s story.
“I was told my mammogram was all good in January, and was diagnosed with breast cancer in November with a palpable lump,” wrote another News 3 viewer in response to my reporting on Cade’s story.
@coastalcurr3nts
We’re hearing from a woman who learned she had breast cancer while pregnant and had to go through major surgery during her third trimester. She tells jessica Latché about the test that finally confirmed her fears.
While doing research about mammograms and their ability to detect breast cancer, I learned screening mammograms can miss one in eight breast cancers, according to the American Cancer Society. The research also revealed that mammograms are more likely to miss cancer in people with dense breast tissue, like Cade.
“That tissue density can affect the ability for the mammogram to see [cancer],” said Dr. Benjamin Pettus, a radiologist within the Riverside Health System.
Pettus told me artificial intelligence programs can help radiologists detect signs of cancer in mammograms that screening by a radiologist may miss, and studies I reviewed support Dr. Pettus’ findings. He’s been using the technology to help screen mammograms this year, and last month, Riverside Health System announced that all their patients’ mammograms will be analyzed by the Transpara Breast Care artificial intelligence portal at no additional cost.
“[The artificial intelligence] basically looks for the shapes and features associated with cancer, and it can find it very small, sometimes even smaller potentially than we [radiologists] can,” Pettus told me. “We're finding more and more people when it's basically a curable situation.”
Pettus said the technology — which flags suspicious areas in mammograms as low, intermediate or elevated risk of breast cancer — is a computer algorithm trained on over a million mammogram screenings. He said radiologists are still tasked with making the final decision on a cancer diagnosis.
“Having that secondary safety measure of another set of eyes looking over [mammograms] reduces the chance for any human error or any fatigue,” said Pettus. “It definitely is nice for us to have that secondary evaluation occurring automatically for everybody.”
Riverside Health System’s announcement joins a list of other health systems and hospitals nationwide using artificial intelligence to aid radiologists in mammogram screenings. The artificial intelligence system, they said, serves as a “second set of eyes for providers to identify patterns of cancerous breast tissue and aims to detect cancer early, when it may be easier to treat.”
Investigations
VB woman diagnosed with breast cancer while pregnant voiced concerns for years
An early-stage study published in The Lancet Oncology found that artificial intelligence “cut doctors' mammogram reading workload almost in half."
Another study I reviewed in the Journal of Breast Cancer said artificial intelligence programs provide results “equivalent or superior to those of radiologists alone."
However, a study I read by the Radiological Society of North America found that automation bias “impaired the performance of radiologists with varying levels of expertise."
I asked Dr. Pettus, “[Do] you want to caution other doctors not to just use [artificial intelligence] as a default?”
“I don’t think we should ever do that,” he replied. “I personally think it’s best to have it as a secondary safety measure after we’ve done all of our work.”
Pettus said the technology will likely benefit women with dense breast tissue the most.
Data reveals Black women are more likely to fall into this group, and Pettus is hopeful the use of artificial intelligence will help bridge disparity gaps in early diagnosis and treatment.
“I definitely hope that each of these advances help bridge that gap because we don’t want any disparities,” said Pettus.
I told Tasha Cade about the new artificial intelligence tool at Riverside Health System, and she said she’s hopeful it will help prevent the missed or delayed diagnoses of other people.
“It can mean the difference between life and death, that one extra test,” Cade told me.
I reached out to other regional health systems. Representatives from Sentara and Bon Secours said they are not using artificial intelligence to aid radiologists in screening mammograms.
