DocumentCode
3065427
Title
Hyperspectral imaging and diagnosis of intestinal ischemia
Author
Akbari, Hamed ; Kosugi, Yukio ; Kojima, Kazuyuki ; Tanaka, Naofumi
Author_Institution
Takyo Institute af Technology, 4259 Nagatsuta, Midmi-ku, Yokohama, Japan
fYear
2008
fDate
20-25 Aug. 2008
Firstpage
1238
Lastpage
1241
Abstract
Intestinal ischemia results from a variety of disorders that cause insufficient blood flow to the intestine. The type and prognosis of ischemic injury depends on the blood vessels involved, the underlying medical condition, and the swiftness with which the problem is brought to medical attention for diagnosis and treatment. Hyperspectral imaging has developed as a compact imaging and spectroscopic tool that can he used for different applications including medical diagnostics. In this paper, the application of hyperspectral imaging as a visual supporting tool to detect the intestinal ischemia during surgeries is evaluated. It will he useful for rapid diagnosing tissue abnormalities. The images are captured using an infrared hyperspectral camera (900–1700m). Using hyperspectral images, the spectral signatures for normal intestine, clamped ischemic intestine and other abdominal organs are created. The high-dimensional data are compressed using wavelet transform and classified using support vector machine (SVM). The performance of this method is evaluated for detection of ischemic intestine in an abdominal surgery on a pig. The criteria to evaluate performance are based on false negative rate (FNR) and false positive rate (FPR). This technique is able to detect ischemic intestine with a small FPR and FNR.
Keywords
Abdomen; Biomedical imaging; Blood flow; Hyperspectral imaging; Injuries; Intestines; Ischemic pain; Support vector machine classification; Support vector machines; Surges; Animals; Imaging, Three-Dimensional; Intestines; Ischemia; Pattern Recognition, Automated; Swine;
fLanguage
English
Publisher
ieee
Conference_Titel
Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE
Conference_Location
Vancouver, BC
ISSN
1557-170X
Print_ISBN
978-1-4244-1814-5
Electronic_ISBN
1557-170X
Type
conf
DOI
10.1109/IEMBS.2008.4649387
Filename
4649387
Link To Document