Gastric cancer diagnosis using hyperspectral imaging with principal component analysis and spectral angle mapper
Open Access
- 27 June 2020
- journal article
- research article
- Published by SPIE-Intl Soc Optical Eng in Journal of Biomedical Optics
- Vol. 25 (06) , 066005-9
Abstract
Gastric cancer is one of the most serious illnesses in the world because of its high morbidity and mortality.1 Currently, early detection and localization of gastric cancer sites are critical to decrease the mortality. However, it is a big challenge for clinicians who routinely utilize conventional white-light reflectance endoscope to accurately identify and localize early dysplasia, carcinoma in situ, and flat mucosal cancers in the stomach.2 The serum markers fail to diagnose or screen gastric cancer with sufficient sensitivity and specificity despite being helpful for monitoring response to therapy and detecting cancer recurrence. Although the radiological diagnostic tests, ionizing or nonionizing radiology, are proved to be effective for gastric cancer diagnosis, a positive result requires further histopathology examination [hematoxylin–eosin (H&E)], which could finally decide when and how to operate on the tumor. The result with H&E approach is invasive, time-consuming, and impractical as a routine screening tool for high-risk patients, and is also subjective based on the pathologist’s expertise.3 Yet accurate identification of the tumor margins is of remarkable clinical importance, in particular for the diffuse type of gastric cancer where the boundaries of the lesion can be indistinct and nests of cancerous cells may be found at a distance from the visible tumor margin. As an emerging spectroscopy and imaging modality for medical applications, hyperspectral imaging (HSI) offers great potential for noninvasive disease diagnosis and surgical guidance.4,5Keywords
This publication has 29 references indexed in Scilit:
- Gastric cancer differentiation using Fourier transform near-infrared spectroscopy with unsupervised pattern recognitionSpectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2013
- Cancer detection using infrared hyperspectral imagingCancer Science, 2011
- A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area MappingSensors, 2010
- Vibrational spectroscopy: a clinical tool for cancer diagnosticsThe Analyst, 2009
- Ability of near infrared reflectance spectroscopy (NIRS) to estimate physical parameters of adult steers (oxen) and young cattle meat samplesMeat Science, 2008
- Screening for gastric cancer in Asia: current evidence and practiceThe Lancet Oncology, 2008
- The use of visible and near infrared reflectance spectroscopy to predict beef M. longissimus thoracis et lumborum quality attributesMeat Science, 2008
- Diagnostic potential of near-infrared Raman spectroscopy in the stomach: differentiating dysplasia from normal tissueBritish Journal of Cancer, 2008
- Application of near-infrared spectroscopy for the diagnosis of colorectal cancer in resected human tissue specimensVibrational Spectroscopy, 2007
- Spectral imaging: Principles and applicationsCytometry Part A, 2006