Waterhouse DJ, Privitera L, Anderson J, Stoyanov D, Giuliani S. Enhancing intraoperative tumor delineation with multispectral short-wave infrared fluorescence imaging and machine learning.
JOURNAL OF BIOMEDICAL OPTICS 2023;
28:094804. [PMID:
36993142 PMCID:
PMC10042297 DOI:
10.1117/1.jbo.28.9.094804]
[Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/06/2022] [Accepted: 03/06/2023] [Indexed: 06/19/2023]
Abstract
SIGNIFICANCE
Fluorescence-guided surgery (FGS) provides specific real-time visualization of tumors, but intensity-based measurement of fluorescence is prone to errors. Multispectral imaging (MSI) in the short-wave infrared (SWIR) has the potential to improve tumor delineation by enabling machine-learning classification of pixels based on their spectral characteristics.
AIM
Determine whether MSI can be applied to FGS and combined with machine learning to provide a robust method for tumor visualization.
APPROACH
A multispectral SWIR fluorescence imaging device capable of collecting data from six spectral filters was constructed and deployed on neuroblastoma (NB) subcutaneous xenografts ( n = 6 ) after the injection of a NB-specific NIR-I fluorescent probe (Dinutuximab-IRDye800). We constructed image cubes representing fluorescence collected from ∼ 850 to 1450 nm and compared the performance of seven learning-based methods for pixel-by-pixel classification, including linear discriminant analysis, k -nearest neighbor classification, and a neural network.
RESULTS
The spectra of tumor and non-tumor tissue were subtly different and conserved between individuals. In classification, a combine principal component analysis and k -nearest-neighbor approach with area under curve normalization performed best, achieving 97.5% per-pixel classification accuracy (97.1%, 93.5%, and 99.2% for tumor, non-tumor tissue and background, respectively).
CONCLUSIONS
The development of dozens of new imaging agents provides a timely opportunity for multispectral SWIR imaging to revolutionize next-generation FGS.
Collapse