An AI-based, automated workflow for identification and scoring of invasive tumors in Ki-67 stained breast cancer specimens.

• DOI: 10.1200/jco.2022.40.16_suppl.e15108
• Publication Date: 2022-06-06T16:13:01Z
• Authors: Bhavika Patel; Stephanie Allen; Sameer S. Talwalkar; Navi Mehra; Jeppe Thagaard; Thomas W. Ramsing; Agnete Overgaard; Jeni Caldara
• Keywords: Ki-67; Stain; Proliferation index

e15108 Background: Understanding the rate of tumor cell growth in breast cancer specimens may be indicative disease aggressiveness, a characteristic which can used to make an informed treatment decision. The nuclear protein Ki-67 is increased cells as they prepare divide or proliferate and therefore widely proliferation marker for progression. This degree proliferation, proliferative index, commonly detailed pathology reports shared with patient care team. Methods: In this study, we utilized [K2] immunohistochemistry (IHC) assay stain 10 specimens. Stained slides were imaged using AT2 scanner (Leica Biosystems, Buffalo Grove, IL) analyzed Visiopharm Image Analysis platform. Results: Previous efforts assess positivity utilizing image analysis have relied on use secondary manual effort by pathologist exclude non-invasive regions. These antiquated methods are costly lab require additional materials valuable time. Our novel approach utilizes artificial intelligence (AI) automatically denote verses invasive regions, then quantify index. Conclusions: tool will allow greater accuracy, cost-savings, time efficiency when analyzing samples compared traditional methods.