Automated Intraoperative Lumpectomy Margin Detection using SAM-Incorporated Forward-Forward Contrastive Learning

Tyler Ward, Braxton McFarland, Sahar Nozad, Talal Arshad, Hafsa Nebbache, Jin Chen, Xiaoqin Wang, Abdullah-Al-Zubaer Imran

Keywords: Breast, Lumpectomy, Specimen radiography, Cancer margin, Forward-Forward, Contrastive learning, SAM

Abstract: Complete removal of cancerous tumors with a negative specimen margin during lumpectomy is essential to reduce breast cancer recurrence. However, interpretation of 2D specimen radiography (SR) by radiologists, the current method used to assess intraoperative margin status, has limited accuracy. This study aims to improve positive margin detection performance on SRs by leveraging cutting-edge deep learning models. We propose a novel lumpectomy margin assessment method using an innovative integration of a contrastive pre-training strategy (Forward-Forward Contrastive Learning) and a segmentation foundation model (Segment Anything Model). Experimental results on an independently annotated breast SRs demonstrate the effectiveness of the proposed method in accurately detecting positive margins on SRs.

Submission Number: 115