Highly accurate diagnosis of lung adenocarcinoma and squamous cell carcinoma tissues by deep learning.

Journal: Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
Published Date:

Abstract

Intraoperative detection of the marginal tissues is the last and most important step to complete the resection of adenocarcinoma and squamous cell carcinoma. However, the current intraoperative diagnosis is time-consuming and requires numerous steps including staining. In this paper, we present the use of Raman spectroscopy with deep learning to achieve accurate diagnosis with stain-free process. To make the spectrum more suitable for deep learning, we utilize an unusual way of thinking which regards Raman spectral signal as a sequence and then converts it into two-dimensional Raman spectrogram by short-time Fourier transform as input. The normal-adenocarcinoma deep learning model and normal-squamous carcinoma deep learning model both achieve more than 96% accuracy, 95% sensitivity and 98% specificity when test, which higher than the conventional principal components analysis-linear discriminant analysis method with normal-adenocarcinoma model (0.896 accuracy, 0.867 sensitivity, 0.926 specificity) and normal-squamous carcinoma model (0.821 accuracy, 0.776 sensitivity, 1.000 specificity). The high performance of deep learning models provides a reliable way for intraoperative detection of marginal tissue, and is expected to reduce the detection time and save human lives.

Authors

  • Yafeng Qi
    State Key Laboratory of Tribology, Tsinghua University, Beijing 100084, China.
  • Lin Yang
    National Clinical Research Center for Metabolic Diseases, Key Laboratory of Diabetes Immunology (Central South University), Ministry of Education, and Department of Metabolism and Endocrinology, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Bangxu Liu
    State Key Laboratory of Tribology, Tsinghua University, Beijing 100084, China.
  • Li Liu
    Metanotitia Inc., Shenzhen, China.
  • Yuhong Liu
    State Key Laboratory of Tribology, Tsinghua University, Beijing 100084, China. Electronic address: liuyuhong@tsinghua.edu.cn.
  • Qingfeng Zheng
    Department of Thoracic Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China. Electronic address: qfzhengpku@163.com.
  • Dameng Liu
    State Key Laboratory of Tribology, Tsinghua University, Beijing 100084, China. Electronic address: ldm@tsinghua.edu.cn.
  • Jianbin Luo
    State Key Laboratory of Tribology, Tsinghua University, Beijing 100084, China.