动态全场光学相干断层扫描结合深度学习在肿瘤患者术中诊断的应用:一项乳腺癌患者的前瞻性队列研究  

Potential rapid intraoperative cancer diagnosis using dynamic full-field optical coherence tomography and deep learning:A prospective cohort study in breast cancer patients

作　　者：张舒玮 杨滨 杨后圃 赵进 张原媛 高元绪 Olivia Monteiro 张康 刘博 王殊 Shuwei Zhang;Bin Yang;Houpu Yang;Jin Zhao;Yuanyuan Zhang;Yuanxu Gao;Olivia Monteiro;Kang Zhang;Bo Liu;Shu Wang(Breast Center,Peking University People’s Hospital,Beijing 100044,China;China ESG Institute,Capital University of Economics and Business,Beijing 100070,China;Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;Department of Pathology,Peking University People’s Hospital,Beijing 100044,China;Center for Biomedicine and Innovations,Faculty of Medicine,Macao University of Science and Technology,Macao 999078,China;College of Future Technology,Peking University,Beijing 100091,China;School of Mathematical and Computational Sciences,Massey University,Auckland 0745,New Zealand)

机构地区：[1]Breast Center,Peking University People’s Hospital,Beijing 100044,China [2]China ESG Institute,Capital University of Economics and Business,Beijing 100070,China [3]Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China [4]Department of Pathology,Peking University People’s Hospital,Beijing 100044,China [5]Center for Biomedicine and Innovations,Faculty of Medicine,Macao University of Science and Technology,Macao 999078,China [6]College of Future Technology,Peking University,Beijing 100091,China [7]School of Mathematical and Computational Sciences,Massey University,Auckland 0745,New Zealand

出　　处：《Science Bulletin》2024年第11期1748-1756,共9页科学通报（英文版）

基　　金：supported by the Capital’s Funds for Health Improvement and Research (CHF 2020-2Z-40812);Beijing Natural Science Foundation (7242281);Beijing Municipal Science and Technology Project (Z201100005520081);the National Key Research and Development Program of China (2016YFC0901300);the National Natural Science Foundation of China (62076015);Macao Science and Technology Development Fund,Macao,China (0070/2020/A2,0003/2021/AKP);Macao Young Scholars Program (AM2023024)。

摘　　要：An intraoperative diagnosis is critical for precise cancer surgery. However, traditional intraoperative assessments based on hematoxylin and eosin(H&E) histology, such as frozen section, are time-,resource-, and labor-intensive, and involve specimen-consuming concerns. Here, we report a near-real-time automated cancer diagnosis workflow for breast cancer that combines dynamic full-field optical coherence tomography(D-FFOCT), a label-free optical imaging method, and deep learning for bedside tumor diagnosis during surgery. To classify the benign and malignant breast tissues, we conducted a prospective cohort trial. In the modeling group(n = 182), D-FFOCT images were captured from April 26 to June 20, 2018, encompassing 48 benign lesions, 114 invasive ductal carcinoma(IDC), 10 invasive lobular carcinoma, 4 ductal carcinoma in situ(DCIS), and 6 rare tumors. Deep learning model was built up and fine-tuned in 10,357 D-FFOCT patches. Subsequently, from June 22 to August 17, 2018, independent tests(n = 42) were conducted on 10 benign lesions, 29 IDC, 1 DCIS, and 2 rare tumors. The model yielded excellent performance, with an accuracy of 97.62%, sensitivity of 96.88% and specificity of 100%;only one IDC was misclassified. Meanwhile, the acquisition of the D-FFOCT images was non-destructive and did not require any tissue preparation or staining procedures. In the simulated intraoperative margin evaluation procedure, the time required for our novel workflow(approximately 3 min)was significantly shorter than that required for traditional procedures(approximately 30 min). These findings indicate that the combination of D-FFOCT and deep learning algorithms can streamline intraoperative cancer diagnosis independently of traditional pathology laboratory procedures.

关 键 词：Cancer diagnosis Breast neoplasms Dynamic full-field optical coherence TOMOGRAPHY Deep learning Image classification 

分 类 号：R737.9[医药卫生—肿瘤]