PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The rapid and accurate identification and classification of cell types is of great significance in scientific research and clinical diagnosis. We proposed the wide-field hyperspectral interferometry rapid label-free (WHIRL)imaging method. Hyperspectral imaging collects and processes information from across the electromagnetic spectrum. In machine learning, support-vector machine (SVM) is one of most commonly used supervised learning models. We cultured a variety of cells and performed hyperspectral imaging by spot scanning with a spectrometer. Then use the SVM method for classification. The accuracy of distinguishing benign from malignant is >99%, and the accuracy of distinguishing different lung cancer subtypes is >90%,which indicates a promising prospect for cell identification and classification based on WHIRL imaging method.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Wenqi Lyu, Rongxin Fu, Xiangyu Jin, Han Yang, Hao Zhong, Guoliang Huang, "From molecular and cellular level to whole body: cross-scale application of label-free optical detection methods," Proc. SPIE 12320, Optics in Health Care and Biomedical Optics XII, 123200I (19 December 2022); https://doi.org/10.1117/12.2644136