Levy Yanir, Rempel David, Nguyen Mark, Yassine Ali, Sanati-Burns Maggie, Salgia Payal, Lim Bryant, Butler Sarah L, Berkeley Andrew, Bayram Ersin
Perimeter Medical Imaging AI Inc., 555 Richmond St W #511, Toronto, ON M5V 3B1, Canada.
Perimeter Medical Imaging AI Inc., 8585 N Stemmons Fwy Suite 106N, Dallas, TX 75247, USA.
Life (Basel). 2023 Dec 14;13(12):2340. doi: 10.3390/life13122340.
This study explores the integration of Wide Field Optical Coherence Tomography (WF-OCT) with an AI-driven clinical decision support system, with the goal of enhancing productivity and decision making in breast cancer surgery margin assessment. A computationally efficient convolutional neural network (CNN)-based binary classifier is developed using 585 WF-OCT margin scans from 151 subjects. The CNN model swiftly identifies suspicious areas within margins with an on-device inference time of approximately 10 ms for a 420 × 2400 image. In independent testing on 155 pathology-confirmed margins, including 31 positive margins from 29 patients, the classifier achieved an AUROC of 0.976, a sensitivity of 0.93, and a specificity of 0.98. At the margin level, the deep learning model accurately identified 96.8% of pathology-positive margins. These results highlight the clinical viability of AI-enhanced margin visualization using WF-OCT in breast cancer surgery and its potential to decrease reoperation rates due to residual tumors.
本研究探索了宽视野光学相干断层扫描（WF-OCT）与人工智能驱动的临床决策支持系统的整合，目的是提高乳腺癌手术切缘评估的效率和决策水平。使用来自151名受试者的585次WF-OCT切缘扫描，开发了一种计算效率高的基于卷积神经网络（CNN）的二元分类器。对于420×2400的图像，该CNN模型在设备上的推理时间约为10毫秒，能够迅速识别切缘内的可疑区域。在对155个病理确诊切缘的独立测试中，包括来自29名患者的31个阳性切缘，该分类器的曲线下面积（AUROC）为0.976，灵敏度为0.93，特异性为0.98。在切缘水平上，深度学习模型准确识别了96.8%的病理阳性切缘。这些结果凸显了在乳腺癌手术中使用WF-OCT进行人工智能增强切缘可视化的临床可行性及其降低因残留肿瘤导致的再次手术率的潜力。
