In vivo use of hyperspectral imaging to develop a noncontact endoscopic diagnosis support system for malignant colorectal tumors

Abstract. The early detection and diagnosis of malignant colorectal tumors enables the initiation of early-stage therapy and can significantly increase the survival rate and post-treatment quality of life among cancer patients. Hyperspectral imaging (HSI) is recognized as a powerful tool for noninvasive cancer detection. In the gastrointestinal field, most of the studies on HSI have involved ex vivo biopsies or resected tissues. In the present study, we aimed to assess the difference in the in vivo spectral reflectance of malignant colorectal tumors and normal mucosa. A total of 21 colorectal tumors or adenomatous polyps from 12 patients at Shanghai Zhongshan Hospital were examined using a flexible hyperspectral (HS) colonoscopy system that can obtain in vivo HS images of the colorectal mucosa. We determined the optimal wavelengths for differentiating tumors from normal tissue based on these recorded images. The application of the determined wavelengths in spectral imaging in clinical trials indicated that such a clinical support system comprising a flexible HS colonoscopy unit and band selection unit is useful for outlining the tumor region and enhancing the display of the mucosa microvascular pattern in vivo.

[1]  Subhransu Maji,et al.  Efficient Classification for Additive Kernel SVMs , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Holger Lange,et al.  Reflectance and fluorescence hyperspectral elastic image registration , 2004, SPIE Medical Imaging.

[3]  Masahiro Yamaguchi,et al.  Endoscopic Observation of Tissue by Narrowband Illumination , 2003 .

[4]  V. Tuchin.  Tissue Optics: Light Scattering Methods and Instruments for Medical Diagnosis , 2000 .

[5]  T. Lehnert,et al.  Sequential hepatic and pulmonary resections for metastatic colorectal cancer , 1999, The British journal of surgery.

[6]  Boris Thies,et al.  Hyperspectral hybrid method classification for detecting altered mucosa of the human larynx , 2012, International Journal of Health Geographics.

[7]  N. Rajpoot,et al.  Hyperspectral Colon Tissue Classification using Morphological Analysis , 2006, 2006 International Conference on Emerging Technologies.

[8]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[9]  Ying Lu,et al.  Detection of hepatic metastases from cancers of the gastrointestinal tract by using noninvasive imaging methods (US, CT, MR imaging, PET): a meta-analysis. , 2002, Radiology.

[10]  Zhimin Han,et al.  New real-time endoscopy image processing technology of hemoglobin color enhancement , 2011, Other Conferences.

[11]  David A. Boas,et al.  "Handbook of biomedical optics", edited by David A. Boas, Constantinos Pitris, and Nimmi Ramanujam , 2012, BioMedical Engineering OnLine.

[12]  N. N. Murthy,et al.  Elastic, maximal matching , 1991, Pattern Recognit..

[13]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[14]  Daniel L. Farkas,et al.  The hyperspectral imaging endoscope: a new tool for in vivo cancer detection , 2004, SPIE BiOS.

[15]  谢天宇,et al.  Hyperspectral high-dynamic-range endoscopic mucosal imaging , 2015 .

[16]  A. Jemal,et al.  Cancer statistics, 2012 , 2012, CA: a cancer journal for clinicians.

[17]  Philip Sloan,et al.  Why oral histopathology suffers inter-observer variability on grading oral epithelial dysplasia: an attempt to understand the sources of variation. , 2007, Oral oncology.

[18]  Lihong V. Wang.  Photoacoustic imaging and spectroscopy , 2009 .

[19]  Guolan Lu,et al.  Medical hyperspectral imaging: a review , 2014, Journal of biomedical optics.

[20]  D. Hill,et al.  Non-rigid image registration: theory and practice. , 2004, The British journal of radiology.

[21]  Luma V. Halig,et al.  Hyperspectral imaging and quantitative analysis for prostate cancer detection. , 2012, Journal of biomedical optics.

[22]  J. Rey,et al.  Narrow band imaging: a wide field of possibilities. , 2007, Saudi journal of gastroenterology : official journal of the Saudi Gastroenterology Association.

[23]  I. Shimoyama,et al.  The micro Fabry-Perot interferometer for the spectral endoscope , 2005, 18th IEEE International Conference on Micro Electro Mechanical Systems, 2005. MEMS 2005..

[24]  Seong G. Kong,et al.  Band Selection of Hyperspectral Images for Automatic Detection of Poultry Skin Tumors , 2007, IEEE Transactions on Automation Science and Engineering.

[25]  W. Wolfe.  Introduction to Imaging Spectrometers , 1997 .

[26]  Tuan Vo-Dinh,et al.  Development of an Advanced Hyperspectral Imaging (HSI) System with Applications for Cancer Detection , 2006, Annals of Biomedical Engineering.

[27]  Y. Kosugi,et al.  Blood vessel detection and artery-vein differentiation using hyperspectral imaging , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[28]  J. Kybic.  ELASTIC IMAGE REGISTRATION USING PARAMETRIC DEFORMATION MODELS , 2001 .

[29]  V. Livolsi,et al.  Can we agree to disagree? , 2003, Human pathology.

[30]  S. Cramer,et al.  International variation in histologic grading is large and persistent feedback does not improve reproducibility. , 2004, The American journal of surgical pathology.

[31]  Vijayashree S. Bhattar,et al.  Accuracy of In Vivo Multimodal Optical Imaging for Detection of Oral Neoplasia , 2012, Cancer Prevention Research.

[32]  Yoshihiko Hamamoto,et al.  New method for detection of gastric cancer by hyperspectral imaging: a pilot study , 2013, Journal of biomedical optics.

[33]  Guang-Zhong Yang,et al.  Multispectral image alignment using a three channel endoscope in vivo during minimally invasive surgery , 2012, Biomedical optics express.

[34]  Jörg Bendix,et al.  Hyperspectral imaging of mucosal surfaces in patients , 2012, Journal of biophotonics.

[35]  Robert P. W. Duin,et al.  Multi-spectral video endoscopy system for the detection of cancerous tissue , 2013, Pattern Recognit. Lett..