While radiologists herald breast tomosynthesis as the hope for the future of breast imaging, several barriers hinder its widespread use. Its very ability to detect benign lesions dilutes the value of such detection, according to a keynote speech at the RSNA meeting.
While radiologists herald breast tomosynthesis as the hope for the future of breast imaging, several barriers hinder its widespread use. Its very ability to detect benign lesions dilutes the value of such detection, according to a keynote speech at the RSNA meeting.
Radiologists hope breast tomosynthesis will improve sensitivity in detection of breast cancer by removing overlapping structures and improving the conspicuity of breast lesions, said Dr. Jay Baker, director of breast imaging at Duke University, during his keynote speech on Tuesday.
"Tomosynthesis may also improve the specificity by allowing better evaluation of lesion morphology and the ability to recognize benign lesions for what they are," he said.
While detecting lesions is the strength of tomosynthesis, however, it may also be the modality's biggest weakness.
"We end up seeing every fibroid adenoma and every cyst when we markedly increase our detection of otherwise benign lesions," he said.
Increasing the number of detected benign lesions becomes problematic because, ultimately, the detection does not aid the patient. The hope that tomosynthesis will reduce the overall number of recalls depends on clarifying architectural distortion, which on diagnostic examination turns out to be nothing more than overlapping but normal breast tissue, Baker said.
"It's also possible that tomosynthesis may allow us to reduce the number of benign biopsies by allowing better evaluation of lesion morphology. But in order to do this, it would require an entirely new imaging paradigm than what we're presently used to," he said.
Tomosynthesis may move to a point at which, if a radiologist identifies a round, oval, or lobulated mass that is 100% circumscribed, the radiologist may simply declare the lesion benign.
This may, however, ultimately lead to a delay in diagnosis, he said.
"Obviously, we're not there yet. We don't have the data to suggest this. We may need to get to this point in order for breast tomosynthesis to live up to its ultimate promise," he said.
Two more pressing challenges to tomosynthesis' introduction are lack of FDA-approved systems in the U.S. and a dearth of published data, according to Baker.
Study: Mammography AI Leads to 29 Percent Increase in Breast Cancer Detection
February 5th 2025Use of the mammography AI software had a nearly equivalent false positive rate as unassisted radiologist interpretation and resulted in a 44 percent reduction in screen reading workload, according to findings from a randomized controlled trial involving over 105,000 women.
Can AI Bolster Breast Cancer Detection in DBT Screening?
January 16th 2025In sequential breast cancer screening with digital breast tomosynthesis (DBT), true positive examinations had more than double the AI case score of true negative examinations and the highest positive AI score changes from previous exams, according to new research.
Mammography Study Suggests DBT-Based AI May Help Reduce Disparities with Breast Cancer Screening
December 13th 2024New research suggests that AI-powered assessment of digital breast tomosynthesis (DBT) for short-term breast cancer risk may help address racial disparities with detection and shortcomings of traditional mammography in women with dense breasts.
Can MRI-Based AI Bolster Biopsy Decision-Making in PI-RADS 3 Cases?
December 9th 2024In patients with PI-RADS 3 lesion assessments, the combination of AI and prostate-specific antigen density (PSAD) level achieved a 78 percent sensitivity and 93 percent negative predictive value for clinically significant prostate cancer (csPCa), according to research presented at the Radiological Society of North American (RSNA) conference.