Adjunctive AI May Improve DBT Detection of Invasive Lobular Breast Cancer
Diagnostic Imaging reports on research suggesting AI can improve digital breast tomosynthesis detection of invasive lobular cancer. The finding is important because lobular breast cancer is notoriously difficult to see on imaging and is often missed or detected late. If validated, adjunctive AI could help close one of the most persistent blind spots in breast imaging.
Invasive lobular carcinoma has long been one of the harder breast cancers to detect because it often grows in a diffuse pattern rather than forming a dense, obvious mass. That makes it a natural candidate for AI assistance, especially in digital breast tomosynthesis, where subtle patterns can be difficult to interpret consistently.
The significance of adjunctive AI here is less about replacing radiologists than about widening perception. In hard-to-see cancers, the clinical value of AI often lies in identifying patterns that are too faint, too scattered, or too time-consuming for human readers to catch reliably at scale.
But this is also exactly where caution is needed. Lesion detection studies can look strong in controlled settings and still fail in real-world practice if they are not tested across different scanners, patient populations, and reading environments. Breast imaging is also an area where false positives carry meaningful downstream costs.
If the findings hold up, the practical impact could be substantial. Lobular cancer is a diagnostic challenge, and tools that improve detection without overwhelming clinicians could become especially valuable in screening programs that are already under pressure from rising volume and limited specialist capacity.