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

Shuwei Zhang ¹Bin Yang ²Houpu Yang ¹Jin Zhao ¹Yuanyuan Zhang ³Yuanxu Gao ⁴Olivia Monteiro ⁴Kang Zhang ⁵Bo Liu ⁶Shu Wang¹

扫码查看

作者信息

1. Breast Center,Peking University People's Hospital,Beijing 100044,China
2. China ESG Institute,Capital University of Economics and Business,Beijing 100070,China;Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China
3. Department of Pathology,Peking University People's Hospital,Beijing 100044,China
4. Center for Biomedicine and Innovations,Faculty of Medicine,Macau University of Science and Technology,Macao 999078,China
5. Center for Biomedicine and Innovations,Faculty of Medicine,Macau University of Science and Technology,Macao 999078,China;College of Future Technology,Peking University,Beijing 100091,China
6. School of Mathematical and Computational Sciences,Massey University,Auckland 0745,New Zealand
折叠

Abstract

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,indepen-dent 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 intraop-erative 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 intraop-erative cancer diagnosis independently of traditional pathology laboratory procedures.

Key words

Cancer diagnosis/Breast neoplasms/Dynamic full-field optical coherence tomography/Deep learning/Image classification

引用本文复制引用

基金项目

Capital's Funds for Health Improvement and Research(CHF 2020-2Z-40812)

Beijing Natural Science Foundation(7242281)

Beijing Municipal Science and Technology Project(Z201100005520081)

National Key Research and Development Program of China(2016YFC0901300)

National Natural Science Foundation of China(62076015)

Macau Science and Technology Development Fund,Macao,China(0070/2020/A2)

Macau Science and Technology Development Fund,Macao,China(0003/2021/AKP)

Macao Young Scholars Program(AM2023024)

出版年

2024

科学通报(英文版)

中国科学院

科学通报(英文版)

CSTPCD

ISSN：1001-6538

段落导航