6 February 2013 New method for detection of gastric cancer by hyperspectral imaging: a pilot study
Author Affiliations +
J. of Biomedical Optics, 18(2), 026010 (2013). doi:10.1117/1.JBO.18.2.026010
Abstract
We developed a new, easy, and objective method to detect gastric cancer using hyperspectral imaging (HSI) technology combining spectroscopy and imaging A total of 16 gastroduodenal tumors removed by endoscopic resection or surgery from 14 patients at Yamaguchi University Hospital, Japan, were recorded using a hyperspectral camera (HSC) equipped with HSI technology Corrected spectral reflectance was obtained from 10 samples of normal mucosa and 10 samples of tumors for each case The 16 cases were divided into eight training cases (160 training samples) and eight test cases (160 test samples) We established a diagnostic algorithm with training samples and evaluated it with test samples Diagnostic capability of the algorithm for each tumor was validated, and enhancement of tumors by image processing using the HSC was evaluated The diagnostic algorithm used the 726-nm wavelength, with a cutoff point established from training samples The sensitivity, specificity, and accuracy rates of the algorithm’s diagnostic capability in the test samples were 78.8% (63/80), 92.5% (74/80), and 85.6% (137/160), respectively Tumors in HSC images of 13 (81.3%) cases were well enhanced by image processing Differences in spectral reflectance between tumors and normal mucosa suggested that tumors can be clearly distinguished from background mucosa with HSI technology.
Kiyotoki, Nishikawa, Okamoto, Hamabe, Saito, Goto, Fujita, Hamamoto, Takeuchi, Satori, and Sakaida: New method for detection of gastric cancer by hyperspectral imaging: a pilot study

1.

Introduction

Gastric cancer is the second most frequent cause of cancer-related death worldwide,1 and the number of deaths due to gastric cancer is about 15% of the total cancer deaths in Japan.2 Esophagogastroduodenoscopy (EGD) is widely used for the screening of gastric cancer in Japan;3 however, skill is required to detect small gastric cancers by this method. Such cancers are often missed by EGD; the reported miss rate for gastric cancers is approximately 20%.4 Although image-enhanced endoscopic technologies such as narrow-band imaging (NBI)5 and flexible spectral imaging color enhancement (FICE)6 have been developed, they are not sufficient to improve the detection rate of gastric cancers.

Hyperspectral imaging (HSI) represents a hybrid modality of optical diagnostics that obtains spectroscopic information and renders it in image form.7 This technology has been used in the field of remote sensing. The HSC1700 hyperspectral camera (HSC; EBA JAPAN Co., Ltd., Tokyo, Japan) is equipped with HSI technology, and the images recorded by the HSC1700 include spectral reflectance (SR) at 72 spectral bands in the wavelength range from 400 to 800 nm, at wavelength intervals of approximately 5.6 nm. Satori et al. reported that at these intervals, it was possible to distinguish slight changes of color with a high degree of accuracy.8

We recorded gastroduodenal tumors removed by endoscopic resection or surgery using HSC and found a difference of SR between tumors and normal mucosa in resected specimens ex vivo. The goal of the present study was to develop a new method for detecting gastric cancers based on differences in SR between tumors and normal mucosa.

2.

Methods

2.1.

Patients

A total of 16 lesions from 14 patients who were treated in Yamaguchi University Hospital in Japan were examined. The clinicopathological characteristics of the lesions are shown in Table 1. In the study, 10 early gastric carcinomas and 4 gastric adenomas were endoscopically resected, and 1 advanced gastric carcinoma and 1 carcinoma of the duodenum were surgically resected. These resected specimens were used for evaluation of SR by HSC.

Table 1

Characteristics of the cases recorded by HSC.

GroupCase no.SexAge (y)Treatment methodLocationHistopathologic diagnosisDepthMacroscopic typeColorTumor size (mm)
Training1F76ERMAdenomamProtrudingDiscolored20
2F76ERMAdenomamProtrudingDiscolored10
3M71ERMTub1mProtrudingReddish20
4F79ERLPapmDepressedReddish6
5M76ERLTub1mProtrudingDiscolored22
6F67ERLAdenomamProtrudingSame12
7M86ERMTub1mProtrudingSame18
8M84ERMTub1mDepressedReddish10
Test9M81ERLAdenomamProtrudingSame10
10M70ERLTub1mDepressedReddish12
11M64ERLTub1smProtrudingDiscolored38
12M68ERLTub1mDepressedReddish8
13M68ERLTub1mDepressedReddish8
14F65ERUTub2mDepressedReddish28
15M59SurgeryDTub1mProtrudingDiscolored20
16M78SurgeryMPapssProtrudingReddish20

Note: ER, endoscopic resection; U, upper third of the stomach; M, middle third of the stomach; L, lower third of the stomach; D, duodenum; Tub1, well-differentiated adenocarcinoma; Tub2, moderately differentiated adenocarcinoma; Pap, papillary adenocarcinoma; m, mucosa; sm, submucosa; ss, subserosa; Same, same color as normal mucosa.

We obtained institutional review board approval from our university. The patients received complete information on this study before providing their consent for participation, and research was carried out in accordance with the Declaration of Helsinki.

2.2.

Characteristics of the HSC1700

The HSC1700 can obtain SR for 72 spectral bands in the wavelength range from 400 to 800 nm in an image with a size of 640×480 pixels. A representative HSC image and SR data for each wavelength in tumorous and normal mucosae from Case 1 are shown in Fig. 1. The SR at all pixels in the image can be evaluated with HSC analysis software (HSD Analysiser; EBA JAPAN Co.). The obtained SR is normalized to one on the basis of white reference data.

Fig. 1

Image from Case 1 obtained with the HSC and SR. Each individual pixel in the image recorded with the HSC has an SR in the wavelength range from 400 to 800 nm. By selecting any pixel, the SR of the spot can be extracted.

JBO_18_2_026010_f001.png

2.3.

Recording Procedure with the HSC

The 16 resected specimens were washed with buffered saline and as much of the mucus as possible was removed; then the specimens were pinned on blackboards and immediately recorded with the HSC. All specimens were illuminated equally using the diffused light of three 250-W halogen lamps. The distance between the HSC and the specimen was 50 cm (Fig. 2). Images of the tumors and surrounding normal mucosa could be obtained for all specimens.

Fig. 2

Schematic of the recording procedure using the HSC. All specimens are illuminated equally using the diffused light of three 250-W halogen lamps. The distance between the HSC and the specimen is 50 cm.

JBO_18_2_026010_f002.png

2.4.

Pathological Evaluation of the Resected Specimens

After being recorded by HSC, the resected specimens were fixed in 10% buffered formalin. We followed the 14th edition of the Japanese Classification of Gastric Carcinoma with regard to the handling of resected specimens.9 The fixed specimens were sectioned at 2-mm intervals and stained with hematoxylin and eosin. The border between the tumor and normal mucosa was diagnosed by histopathological examination. All lesions were curatively resected with a sufficient margin.

2.5.

Analysis of the SRs of Tumors and Normal Mucosae

The method of supervised learning was used to establish a diagnostic algorithm and evaluate its diagnostic capability.10 The 16 cases were divided into eight training cases and eight test cases. The training cases were used to determine the optimal wavelength and cutoff point to discriminate between normal and tumorous mucosae. The test cases, which were independent of the training cases, were used to evaluate the diagnostic capability for tumors.

The SRs were obtained from 15 samples (pixels) of normal mucosae and 10 samples (pixels) of tumors from each case. Artifacts of electric cauterization and surgical margins were omitted from the measured samples. Because the SR varied in each case, the mean SR from five normal samples was used as a control for normalization. For each case, corrected spectral reflectance (cSR) was defined as follows:

Corrected spectral reflectance (cSR)=SR-mean SR of 5 normal samples

Then the cSRs from 10 normal mucosa samples and 10 tumor samples of each case were obtained. A flowchart of the SR analysis is shown in Fig. 3.

Fig. 3

Flowchart of the analysis of SR. The SR is obtained from 15 samples (pixels) of normal mucosae and 10 samples (pixels) of tumors from each case. The mean SR from 5 normal samples is used as a control for normalization, and then the cSR from 10 normal mucosa samples and 10 tumor samples of each case are obtained. The 16 cases are divided into eight training cases and eight test cases. The training cases are used to determine the optimal wavelength and cutoff point to discriminate between normal and tumorous mucosae. The test cases are used to evaluate the diagnostic capability for tumors.

JBO_18_2_026010_f003.png

2.6.

Image Enhancement of Tumors by Image Processing

By using the HSD Analysiser, we processed the images of all lesions with 20 levels of color gradation on the basis of the SR of the optimal wavelength. Each pixel of the image was displayed in blue if the SR of the pixel was low and red if it was high. The enhanced images were classified by two endoscopists (J. Nishikawa and T. Okamoto) into the following three grades: A, the entire tumor was enhanced; B, the tumor was partially enhanced; and C, the tumor was not enhanced at all. The cases classified as A or B were defined as “enhanced,” and we examined the cases of enhancement.

3.

Results

3.1.

Establishment of the Diagnostic Algorithm with Training Cases

The mean cSR of each wavelength from the 10 tumor samples and 10 normal samples of Case 1 is shown in Fig. 4. In the range of 600 to 800 nm, the mean cSR in the tumors tended to be higher than that in normal mucosae in the training cases. Consequently, the cutoff point was set at the intermediate value between the mean cSR of 80 tumor samples and the mean cSR of 80 normal mucosal samples from the eight training cases. We hypothesized that a cSR higher than the cutoff point indicated a tumor, and a cSR lower than the cutoff point indicated normal mucosa. To determine the optimal wavelength and cutoff point, we set a cutoff point for each wavelength and compared the sensitivity, specificity, and diagnostic accuracy. The accuracy rate using the cutoff point of 726 nm was the highest for the 72 wavelengths, and its cutoff point was 0.05084. The sensitivity, specificity, and accuracy rates were 76.2% (61/80 samples), 78.8% (63/80), and 77.5% (124/160), respectively (Fig. 5).

Fig. 4

Example of the cSR from the training cases. The mean cSR of the tumor and the normal mucosa from Case 1 are shown. Solid line: tumor; dashed line: normal mucosa.

JBO_18_2_026010_f004.png

Fig. 5

Sensitivity, specificity, and diagnostic accuracy of each wavelength in the training cases. The cutoff point is set at the intermediate value between the mean cSR of 80 tumor samples and the mean cSR of 80 normal mucosal samples from the eight training cases. The accuracy rate using the cutoff point of 726 nm is the highest for the 72 wavelengths.

JBO_18_2_026010_f005.png

3.2.

Validation of the Diagnostic Algorithm with Test Cases

To evaluate the diagnostic capability using the cutoff point of the optimal wavelength (726 nm) determined in training cases, we used 160 blind samples (80 tumor samples and 80 normal mucosa samples) from the test cases, independent of the training cases. The sensitivity, specificity, and accuracy rates were 78.8% (63/80 samples), 92.5% (74/80), and 85.6% (137/160), respectively, in the test cases (Fig. 6).

Fig. 6

Diagnostic accuracy of the cSR at the 726-nm wavelength in the test cases. Using the cutoff point (0.05084) determined for the training cases, 160 test case samples were diagnosed as tumors or normal mucosae. The sensitivity, specificity, and accuracy rates are 78.8% (63/80 samples), 92.5% (74/80), and 85.6% (137/160), respectively.

JBO_18_2_026010_f006.png

3.3.

Evaluation of Images Enhanced by SR Data at 726 nm

HSC images of the 16 cases were processed on the basis of the SR of the wavelength of 726 nm. An image from Case 1 is shown in Fig. 7. Endoscopist J. Nishikawa classified them as follows: A, 8 cases; B, 6 cases; and C, 2 cases, whereas T. Okamoto considered the classifications to be as follows: A, 3 cases; B, 11 cases; and C, 2 cases. The number of cases evaluated as enhanced (A or B) by both endoscopists was 13 (81.3%).

Fig. 7

Image processing on the basis of the SR at the 726-nm wavelength. A resected specimen from Case 1 is shown. (a) Digital camera image before recording with the HSC. (b) Image of the resected specimen fixed in 10% buffered formalin. The fixed specimen is sectioned at 2-mm intervals, and the tumorous areas are diagnosed by histopathological examination. We indicated the cut lines made at 2-mm intervals as white lines on the specimens and the tumorous areas compared with the histopathological results with red lines. (c) HSC image before image processing. (d) Image processed on the basis of the SR at the 726-nm wavelength by using HSD Analysiser. Each pixel of the image is displayed in blue if the SR of the pixel is low and in red if it is high. The tumor-emphasized areas and the histopathologically determined tumorous areas are almost identical.

JBO_18_2_026010_f007.png

4.

Discussion

Previous applications of optical spectroscopy to detect gastrointestinal cancer have been attempted. Sambongi et al. measured the spectral intensities of tumors and normal mucosae of the stomach and the colon using a fiber probe through an endoscope.11 They analyzed the SR in the range of 400 to 600 nm normalized to an SR of 640 nm, but the difference in SR between tumors and normal mucosae was not clearly identified. The usefulness of autofluorescence for cancer detection has been reported. Mayinger et al. measured the fluorescence spectra of gastric cancer by illumination with violet-blue light through a fiber probe, and a sensitivity of 84% and specificity of 87% were obtained for the diagnosis of gastric adenocarcinoma.12 Because both systems could obtain the spectral data of only a single spot, it was impossible to evaluate the spectrum over a large area of observation. By contrast, the advantage of HSI technology is that it can obtain spectral data for each pixel in an image with a large area of observation.7,8 This enables the comparison of spectral data between the tumor and normal mucosa and visualization of the difference by image processing.

We measured the SR of resected specimens of gastric cancers using the HSC1700; however, SR varied in each case. It is thought that SR is reflected mainly by surface color. Gastric cancers have various colors (ranging from reddish to discolored) in each patient. In addition, the color of the background mucosa also varies with gastritis and the grade of mucosal atrophy, and these changes may also provide variations in the SR. Therefore, the mean SR in normal mucosa was used as a control for normalization, making it possible to effectively reduce variation and determine the optimal wavelength and cutoff point to discriminate between normal and tumorous mucosae. The accuracy rate using the optimal wavelength of 726 nm was the highest among the 72 wavelengths examined in the training cases. The diagnostic algorithm based on the analysis of the training cases was applied to test cases and led to highly accurate diagnoses.

With regard to the clinical setting, we are considering that an endoscope and an HSC are connected to measure reflectance spectra of gastric cancer in vivo. When we develop such a prototype, SR of normal mucosa will be measured first, and images of cancerous areas with SR very different from the normal will be enhanced during endoscopic examination. We believe that application of HSI to endoscopic examination could decrease the incidence of missed gastric cancer.

We believe that higher specificity and fewer false negatives are preferable for cancer screening. In the present study, what resulted in a false negative was very low-grade malignant gastric cancer such as that in Case 13, which suggests that differences in SR in such cases may be small.

It is not known why the SR at 726 nm is generally higher in cancerous mucosae. We first speculated that this particular SR could be affected by the hemoglobin concentration because microvessel density correlated positively with the SR at the wavelength of 726 nm in the lesions (data not shown in this article). Oxyhemoglobin is normally the most abundant form of hemoglobin and has three peaks of absorption (418, 542, and 577 nm).13 Image-enhanced endoscopic techniques such as NBI and FICE have mainly utilized light wavelengths of 400 to 600 nm.5,6 These are suitable for the detection of capillary-rich tumors and observation of irregular microvessels on tumors with a magnifying endoscope.14,15 The 726-nm wavelength of light has a tendency to be absorbed more easily by deoxyhemoglobin.16,17 Therefore, the difference of SR at 726 nm might be associated with the deoxyhemoglobin content. We also considered other factors influencing the absorption and scattering of light. The 726-nm wavelength is near-infrared light, and it can penetrate the mucosal layer to the submucosal layer,18 so interstitial collagen in this layer might affect the SR at 726 nm.19

The limitations of this study include the small sample size and the fact that all the results obtained with the HSC were from ex vivo SR data. It is not known if the same results would be obtained with in vivo data. There is a high possibility that hemoglobin density and oxygen saturation having an effect on SR are considered to change with in vivo and ex vivo tissue. Therefore, in order to determine whether the ex vivo results of this study can be applied in vivo, we are planning to measure SR of gastric cancer in vivo.

In conclusion, we found a difference in the SR between tumors and normal mucosae ex vivo, indicating that it is possible to discriminate tumors from normal mucosae with this HSI system. Thus, HSI technology can be used in a computer-aided detection system that could potentially improve the detection rate of gastric cancers.

References

1. 

K. D. CrewA. I. Neugut, “Epidemiology of gastric cancer,” World J. Gastroenterol. 12(3), 354–362 (2006).WJGAF21007-9327Google Scholar

2. 

S. Hirobashi, Ed., Cancer Statistics in Japan, p. 12, Foundation for Promotion of Cancer Research, Tokyo (2009).Google Scholar

3. 

C. Hamashimaet al., “The Japanese guidelines for gastric cancer screening,” Jpn. J. Clin. Oncol. 38(4), 259–267 (2008).JJCOAC0368-2811http://dx.doi.org/10.1093/jjco/hyn017Google Scholar

4. 

K. Aidaet al., “Clinicopathological features of gastric cancer detected by endoscopy as part of annual health checkup,” J. Gastroenterol. Hepatol. 23(4), 632–637 (2008).JGHEEO1440-1746http://dx.doi.org/10.1111/j.1440-1746.2008.05346.xGoogle Scholar

5. 

K. Gonoet al., “Appearance of enhanced tissue features in narrow-band endoscopic imaging,” J. Biomed. Opt. 9(3), 568–577 (2004).JBOPFO1083-3668http://dx.doi.org/10.1117/1.1695563Google Scholar

6. 

J. Pohlet al., “Computed virtual chromoendoscopy: a new tool for enhancing tissue surface structures,” Endoscopy 39(1), 80–83 (2007).ENDCAMhttp://dx.doi.org/10.1055/s-2006-945045Google Scholar

7. 

T. Vo-Dinhet al., “A hyperspectral imaging system for in vivo optical diagnostics. Hyperspectral imaging basic principles, instrumental systems, and applications of biomedical interest,” IEEE Eng. Med. Biol. Mag. 23(5), 40–49 (2004).IEMBDE0739-5175http://dx.doi.org/10.1109/MEMB.2004.1360407Google Scholar

8. 

S. Satoriet al., “Hyperspectral sensor HSC3000 for Nano-satellite ‘TAIKI’,” Proc. SPIE 7149, 71490M (2008).PSISDG0277-786Xhttp://dx.doi.org/10.1117/12.804898Google Scholar

9. 

Japanese Gastric Cancer Association, Ed., Japanese Classification of Gastric Carcinoma, 14th ed., pp. 21–25, Kanehara, Tokyo (2010).Google Scholar

10. 

A. K. JainR. P. W. DuinJ. Mao, “Statistical pattern recognition: a review,” IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 4–37 (2000).ITPIDJ0162-8828http://dx.doi.org/10.1109/34.824819Google Scholar

11. 

M. Sambongiet al., “Analysis of spectral reflectance using normalization method from endoscopic spectroscopy system,” Opt. Rev. 9(6), 238–243 (2002).1340-6000http://dx.doi.org/10.1007/s10043-002-0238-2Google Scholar

12. 

B. Mayingeret al., “Evaluation of in vivo endoscopic autofluorescence spectroscopy in gastric cancer,” Gastrointest. Endosc. 59(2), 191–198 (2004).GAENBQ0016-5107http://dx.doi.org/10.1016/S0016-5107(03)02687-7Google Scholar

13. 

S. Prahl, “Optical absorption of hemoglobin,” 15 December 1999, http://omlc.ogi.edu/spectra/hemoglobin/index.html (31 January 2012).Google Scholar

14. 

T. Nakayoshiet al., “Magnifying endoscopy combined with narrow band imaging system for early gastric cancer: correlation of vascular pattern with histopathology (including video),” Endoscopy 36(12), 1080–1084 (2000).ENDCAMhttp://dx.doi.org/10.1055/s-2004-825961Google Scholar

15. 

K. Sumiyamaet al., “Combined use of a magnifying endoscope with a narrow band imaging system and a multibending endoscope for en bloc EMR of early-stage gastric cancer,” Gastrointest. Endosc. 60(1), 79–84 (2004).GAENBQ0016-5107http://dx.doi.org/10.1016/S0016-5107(04)01285-4Google Scholar

16. 

P. Taroniet al., “Time-resolved optical spectroscopy and imaging of breast,” Opto-Electron Rev. 12(2), 249–253 (2004).OELREM1230-3402Google Scholar

17. 

W. G. ZijlstraA. BuursmaW. P. Meeuwsen-van der Roest, “Absorption spectra of human fetal and adult oxyhemoglobin, de-oxyhemoglobin, carboxyhemoglobin, and methemoglobin,” Clin. Chem. 37(9), 1633–1638 (1991).CLCHAU0009-9147Google Scholar

18. 

A. N. Bashkatovet al., “Optical properties of human skin, subcutaneous and mucous tissues in the wavelength range from 400 to 2000 nm,” J. Phys. D: Appl. Phys. 38(15), 2543–2555 (2005).JPAPBE0022-3727http://dx.doi.org/10.1088/0022-3727/38/15/004Google Scholar

19. 

I. Georgakoudiet al., “NAD(P)H and collagen as in vivo quantitative fluorescent biomarkers of epithelial precancerous changes,” Cancer Res. 62(3), 682–687 (2002).CNREA80008-5472Google Scholar

Shuu Kiyotoki, Jun Nishikawa, Takeshi Okamoto, Kouichi Hamabe, Mari Saito, Atsushi Goto, Yusuke Fujita, Yoshihiko Hamamoto, Yusuke Takeuchi, Shin Satori, Isao Sakaida, "New method for detection of gastric cancer by hyperspectral imaging: a pilot study," Journal of Biomedical Optics 18(2), 026010 (6 February 2013). http://dx.doi.org/10.1117/1.JBO.18.2.026010
Submission: Received ; Accepted
JOURNAL ARTICLE
7 PAGES


SHARE
KEYWORDS
Tumors

Cancer

Diagnostics

Image processing

Hyperspectral imaging

Image enhancement

Reflectivity

Back to Top