
Delayed callbacks may be a reasonable option for likely benign breast findings on mammography when immediate callback is not an option -- such as during a pandemic, a study published March 21 in Clinical Imaging suggests.
A team led by Dr. Juliana Chamadoira from the University of Toronto found that most mammography findings labeled as "possibly benign" that had workup delayed were indeed benign, with no in-situ cancers found on follow-up.
"The results of this study may be helpful for a future situation when delaying a call back from screening mammography is again required," Chamadoira and co-authors wrote.
During the COVID-19 pandemic, healthcare facilities around the world postponed nonurgent medical care to patients, including breast cancer screening. During the pandemic, if findings on the screening mammography were deemed to be not suspicious for malignancy, workup was postponed, the team noted, writing that this was an institutional decision in response to the pandemic in an attempt to minimize the spread the disease, "even understanding that a hidden malignancy mimicking a benign lesion could be overlooked."
Chamadoira's group sought to assess the frequency and distinguishing imaging characteristics of breast cancers detected on screening mammography that were initially evaluated as a probably benign lesion and workup was delayed due to COVID-19. The team conducted a study that included 1,816 screening mammograms taken between February and March 2020. Of these, 99 had possibly benign findings and delayed workup.
Out of the study cohort, two women, ages 49 and 56, had cancers misinterpreted as benign findings (2%); both these cases were focal asymmetries, with pathology of invasive ductal carcinoma, and were 12 mm and 9 mm in size, respectively. No in-situ cancers were detected.
Based on the study findings, delayed callback can be considered reasonable, Chamadoira and colleagues concluded, although they did call for larger studies to support their findings.



![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=100&q=70&w=100)







![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)







