Cone-beam breast CT radiomics predicts Ki-67 and prognosis in two-centre study

Preoperative cone-beam breast CT (CE-CBBCT) radiomics predicted high Ki-67 in breast cancer (AUC 0.885 at 14% cut-off; 0.831 at 30% cut-off, external test cohort). Adding deep learning did not significantly improve performance. The radiomics score for Ki-67 ≥30% independently pr…

• Two-centre retrospective study (n=636) with internal (n=77) and external (n=78) validation cohorts.
• At 30% Ki-67 cut-off, the combined radiomics+DL+clinical model achieved an external test AUC of 0.869, not statistically superior to radiomics alone.
• Preliminary survival finding; DFS analysis was limited to a single prognostic cohort (n=171) without external validation of the outcome.

RadPigeon summaries are original and for information only. They are not clinical advice.