Gastric cancer diagnosis using hyperspectral imaging with principal component analysis and spectral angle mapper

Significance: Hyperspectral imaging (HSI) is an emerging optical technique that has a double function of spectroscopy and imaging. Aim: Near-infrared hyperspectral imaging (NIR-HSI) (900 to 1700 nm) with the help of chemometrics was investigated for gastric cancer diagnosis. Approach: Mean spectra and standard deviation of normal and cancerous pixels were extracted. Principal component analysis (PCA) was used to compress the dimension of hypercube data and select the optimal wavelengths. Moreover, spectral angle mapper (SAM) was utilized as chemometrics to discriminate gastric cancer from normal. Results: Major spectral difference of cancerous and normal gastric tissue was observed around 975, 1215, and 1450 nm by comparison. A total of six wavelengths (i.e., 975, 1075, 1215, 1275, 1390, and 1450 nm) were then selected as optimal wavelengths by PCA. The accuracy using SAM is up to 90% according to hematoxylin–eosin results. Conclusions: These results suggest that NIR-HSI has the potential as a cutting-edge optical diagnostic technique for gastric cancer diagnosis with suitable chemometrics.