Sunday, November 25 | 12:30 p.m.-1:00 p.m. | LL-BRS-SU5A | Lakeside Learning Center
How best can doctors assess residual disease in inflammatory breast cancer (IBC) patients who have undergone neoadjuvant chemotherapy? Find out in this Sunday poster presentation.Researchers from the University of Texas MD Anderson Cancer Center will share findings from a study they conducted to evaluate the performance of mammography, ultrasound, and MRI for this task.
Dr. Sarah Martaindale and colleagues used their institution's IBC Registry protocol to identify women with an inflammatory breast cancer diagnosis who had had baseline and mammography, ultrasound, and MRI exams after neoadjuvant chemotherapy. Between January 2006 and December 2009, 94 women were enrolled in the IBC Registry protocol; 64 patients met the team's inclusion criteria.
They found the following:
- Mean baseline tumor size was 63 mm, 48 mm, and 69 mm, respectively, on mammography, ultrasound, and MRI.
- Breast tumor size on MRI before neoadjuvant chemotherapy was larger than on ultrasound and mammography.
- Tumor size on MRI and ultrasound after neoadjuvant chemotherapy were similar.
- There was a strong association between tumor size after neoadjuvant chemotherapy and higher pathologic response for ultrasound and MRI.
What did the team conclude? While ultrasound and MRI measurement of tumor size after neoadjuvant chemotherapy can predict for residual disease, MRI may be better for monitoring larger tumor size before neoadjuvant chemotherapy.











![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)






