Hyperspectral imaging and quantitative analysis for prostate cancer detection

Hamed Akbari, Luma V Halig, David M Schuster, Adeboye Osunkoya, Viraj Master, Peter T Nieh, Georgia Z Chen, Baowei Fei, Hamed Akbari, Luma V Halig, David M Schuster, Adeboye Osunkoya, Viraj Master, Peter T Nieh, Georgia Z Chen, Baowei Fei

Abstract

Hyperspectral imaging (HSI) is an emerging modality for various medical applications. Its spectroscopic data might be able to be used to noninvasively detect cancer. Quantitative analysis is often necessary in order to differentiate healthy from diseased tissue. We propose the use of an advanced image processing and classification method in order to analyze hyperspectral image data for prostate cancer detection. The spectral signatures were extracted and evaluated in both cancerous and normal tissue. Least squares support vector machines were developed and evaluated for classifying hyperspectral data in order to enhance the detection of cancer tissue. This method was used to detect prostate cancer in tumor-bearing mice and on pathology slides. Spatially resolved images were created to highlight the differences of the reflectance properties of cancer versus those of normal tissue. Preliminary results with 11 mice showed that the sensitivity and specificity of the hyperspectral image classification method are 92.8% to 2.0% and 96.9% to 1.3%, respectively. Therefore, this imaging method may be able to help physicians to dissect malignant regions with a safe margin and to evaluate the tumor bed after resection. This pilot study may lead to advances in the optical diagnosis of prostate cancer using HSI technology.

Figures

Fig. 1
Fig. 1
Schematic view of the hyperspectral images of a nude mouse. Right: the spectral graphs of two, sample pixels from cancer (dashed line) and normal (continuous line) tissue. The graph depicts the normalized reflectance for each wavelength in that pixel. The horizontal axis shows different wavelengths in nanometers. The vertical axis shows the normalized reflectance.
Fig. 2
Fig. 2
A nude mouse with the initiated prostate tumor (arrow).
Fig. 3
Fig. 3
The flowchart of the tissue classification method for hyperspectral images.
Fig. 4
Fig. 4
Spetral images of a tumor-bearing mouse at different wavelengths. The tumor (arrow) and the pellet (arrow head) are visible on the images at various wavelengths.
Fig. 5
Fig. 5
In vivo spectral signature of 12 pixels of cancer tissue (dot-dashed line) and additional 12 pixels of normal tissue (continuous line) in a nude mouse. The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the relative reflectance.
Fig. 6
Fig. 6
The mean of the spectral signatures of the cancer tissue (dashed line) and normal tissue (continuous line) in a typical mouse. The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the relative reflectance.
Fig. 7
Fig. 7
Detection of cancer tissue (green) in a nude mouse using the proposed classification method. Most of the tumor tissue (arrow) was automatically detected while some false-positive areas are also shown on the image at locations other than the tumor.
Fig. 8
Fig. 8
In vitro spectral signature of 10 pixels of cancer tissue (dashed line) and additional 12 pixels of normal tissue (continuous line) seen on pathology slides of a human prostate. The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the relative reflectance.
Fig. 9
Fig. 9
The mean of spectral signatures of the cancer tissue (dot-dashed line) and normal tissue (continuous line) seen on pathology slides of a human prostate. The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the relative reflectance.
Fig. 10
Fig. 10
Automatic detection of cancer tissue on pathology slides using hyperspectral image classification. (a) The original histological slide shows the cancer as outlined by the black line. (b) Most of the cancer tissue (arrows) was detected using the automatic method, while false-postive areas are also shown on the image (arrow head).
Fig. 11
Fig. 11
An RGB image of the hyperspectral microscopic images seen on a pathology slide. The blue line outlining the tumor region was made by a pathologist.
Fig. 12
Fig. 12
The spectral diagrams of the normal tubuloalveolar glands (square continuous line), the cancerous tubuloalveolar glands (square dashed line), the normal fibromuscular stroma (continuous line), and the cancerous fibromuscular stroma (star dot-dashed line) seen in prostate inflammation. The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the intensity of the hyperspectral images.
Fig. 13
Fig. 13
The spectral diagrams of the normal tubuloalveolar glands (square continuous line), cancerous tubuloalveolar glands (square dashed line), the normal fibromuscular stroma (continuous line), and the cancerous fibromuscular stroma (star dot-dashed line) seen in prostatic intraepithelial neoplasia (PIN). The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the intensity of the hyperspectral images.
Fig. 14
Fig. 14
The spectral diagrams of the normal tubuloalveolar glands (square continuous line), the cancerous tubuloalveolar glands (square dashed line), the normal fibromuscular stroma (continuous line), and the cancerous fibromuscular stroma (star dot-dashed line) seen in prostatic cancer (Gleason 3). The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the intensity of the hyperspectral images.
Fig. 15
Fig. 15
The spectral diagrams of the normal tubuloalveolar glands (square continuous line), the cancerous tubuloalveolar glands (square dashed line), the normal fibromuscular stroma (continuous line), and the cancerous fibromuscular stroma (star dot-dashed line) seen in prostatic cancer (Gleason 4). The horizontal axis shows the different wavelengths in nanometers. The vertical axis shows the intensity of the hyperspectral images.

References

    1. Panasyuk S. V., et al. , “Medical hyperspectral imaging to facilitate residual tumor identification during surgery,” Canc. Biol. Ther. 6(3), 439–446 (2007).CBTAAO10.4161/cbt
    1. Goetz A. F. H., “Three decades of hyperspectral remote sensing of the earth: a personal view,” Remote Sens. Environ. 113(Suppl. 1), S5–S16 (2009).RSEEA710.1016/j.rse.2007.12.014
    1. Akbari H., et al. , “Hyperspectral image segmentation and its application in abdominal surgery,” Int. J. Funct. Inform. Personal. Med. 2(2), 201–216 (2009).10.1504/IJFIPM.2009.027592
    1. Kellicut D. C., et al. , “Emerging technology: hyperspectral imaging,” Perspect. Vasc. Surg. Endovasc. Ther. 16(1), 53–57 (2004).10.1177/153100350401600114
    1. Akbari H., et al. , “Detection and analysis of the intestinal ischemia using visible and invisible hyperspectral imaging,” IEEE Trans. Biomed. Eng. 57(8), 2011–2017 (2010).IEBEAX10.1109/TBME.2010.2049110
    1. Khaodhiar L., et al. , “The use of medical hyperspectral technology to evaluate microcirculatory chaves in diabetic foot ulcers and to predict clinical outcomes,” Diabetes Care 30(4), 903–910 (2007).DICAD210.2337/dc06-2209
    1. Cancio L. C., et al. , “Hyperspectral imaging: a new approach to the diagnosis of hemorrhagic shock,” J. Trauma 60(5), 1087–1095 (2006).JOTRA510.1097/01.ta.0000217357.10617.3d
    1. Jemal A., et al. , “Cancer statistics, 2010,” CA Cancer J. Clin. 60(5), 277–300 (2010).CAMCAM10.3322/caac.20073
    1. Martin M. E., et al. , “Development of an advanced hyperspectral imaging (HSI) system with applications for cancer detection,” Ann. Biomed. Eng. 34(6), 1061–1068 (2006).ABMECF10.1007/s10439-006-9121-9
    1. Siddiqi A. M., et al. , “Use of hyperspectral imaging to distinguish normal, precancerous, and cancerous cells,” Cancer 114(1), 13–21 (2008).10.1002/cncr.23286
    1. Dicker D. T., et al. , “Differentiation of normal skin and melanoma using high resolution hyperspectral imaging,” Cancer Biol. Ther. 5(8), 1033–1038 (2006).CBTAAO10.4161/cbt
    1. Akbari H., et al. , “Cancer detection using infrared hyperspectral imaging,” Cancer Sci. 102(4), 852–857 (2011).CSACCM10.1111/cas.2011.102.issue-4
    1. Camps-Valls G., Bruzzone L., “Kernel-based methods for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens. 43(6), 1351–1362 (2005).IGRSD210.1109/TGRS.2005.846154
    1. Camps-Valls G., et al. , “Robust support vector method for hyperspectral data classification and knowledge discovery,” IEEE Trans. Geosci. Remote Sens. 42(7), 1530–1542 (2004).IGRSD210.1109/TGRS.2004.827262
    1. Brown M., Lewis H. G., Gunn S. R., “Linear spectral mixture models and support vector machines for remote sensing,” IEEE Trans. Geosci. Remote Sens. 38(5), 2346–2360 (2000).IGRSD210.1109/36.868891
    1. Brown M., Gunn S. R., Lewis H. G., “Support vector machines for optimal classification and spectral unmixing,” Ecol. Model. 120(2–3), 167–179 (1999).ECMODT10.1016/S0304-3800(99)00100-3
    1. Melgani F., Bruzzone L., “Classification of hyperspectral remote sensing images with support vector machines,” IEEE Trans. Geosci. Remote Sens. 42(8), 1778–1790 (2004).IGRSD210.1109/TGRS.2004.831865
    1. Wang H., Fei B. W., “Diffusion-weighted MRI for monitoring tumor response to photodynamic therapy,” J. Magn. Reson. Imaging 32(2), 409–417 (2010).10.1002/jmri.v32:2
    1. Fei B. W., et al. , “Choline PET for monitoring early tumor response to photodynamic therapy,” J. Nucl. Med. 51(1), 130–138 (2010).
    1. Fei B. W., et al. , “High-field magnetic resonance imaging of the response of human prostate cancer to Pc 4-based photodynamic therapy in an animal model,” Lasers Surg. Med. 39(9), 723–730 (2007).LSMEDI10.1002/(ISSN)1096-9101
    1. Vapnik V. N., The Nature of Statistical Learning Theory, Springer-Verlag, Berlin: (1995).
    1. Suykens J. A. K., Vandewalle J., “Least squares support vector machine classifiers,” Neural Processing Lett. 9(3), 293–300 (1999).NPLEFG10.1023/A:1018628609742
    1. Liu Z., et al. , “Automated tongue segmentation in hyperspectral images for medicine,” Appl. Opt. 46(34), 8328–8334 (2007).APOPAI10.1364/AO.46.008328
    1. Gestel T. V., et al. , “Benchmarking least squares support vector machine classifiers,” Mach. Learn. 54(1), 5–32 (2004).MALEEZ10.1023/B:MACH.0000008082.80494.e0
    1. Wang H. S., Fei B. W., “A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme,” Med. Image Anal. 13(2), 193–202 (2009). MIAECY10.1016/j.media.2008.06.014
    1. Yang X. F., Fei B. W., “A multiscale and multiblock fuzzy C-means classification method for brain MR images,” Med. Phys. 38(6), 2879–2891 (2011).MPHYA610.1118/1.3584199
    1. Bogie K., et al. , “New technique for real-time interface pressure analysis: getting more out of large image data sets,” J. Rehabil. Res. Dev. 45(4), 523–535 (2008).JRRDEC10.1682/JRRD.0000.00.0000
    1. Crow P., et al. , “The use of Raman spectroscopy to differentiate between different prostatic adenocarcinoma cell lines,” Br. J. Cancer 92(12), 2166–2170 (2005).
    1. Crow P., et al. , “Assessment of fiberoptic near-infrared Raman spectroscopy for diagnosis of bladder and prostate cancer,” Urology 65(6), 1126–1130 (2005).10.1016/j.urology.2004.12.058
    1. Taleb A., et al. , “Raman microscopy for the chemometric analysis of tumor cells,” J. Phys. Chem. B 110(39), 19625–19631 (2006).JPCBFK10.1021/jp061981q
    1. Crow P., et al. , “The use of Raman spectroscopy to differentiate between different prostatic adenocarcinoma cell lines,” Br. J. Cancer 92(12), 2166–2170 (2005).BJCAAI10.1038/sj.bjc.6602638
    1. Sharma V., et al. , “Optical reflectance spectroscopy for detection of human prostate cancer,” Conf. Proc. IEEE. Eng. Med. Biol. Soc., 118–121 (2009).
    1. Huang C., Davis L. S., Townshend J. R. G., “An assessment of support vector machines for land cover classification,” Int. J. Remote Sens. 23(4), 725–749 (2002).IJSEDK10.1080/01431160110040323
    1. Andersson-Engels S., et al. , “In vivo fluorescence imaging for tissue diagnostics,” Phys. Med. Biol. 42(5), 815–824 (1997).PHMBA710.1088/0031-9155/42/5/006
    1. Dolloff N. G., et al. , “Spectral imaging-based methods for quantifying autophagy and apoptosis,” Canc. Biol. Ther. 12(4), 349–356 (2011).CBTAAO10.4161/cbt
    1. Cheng Y., et al. , “Highly efficient drug delivery with gold nanoparticle vectors for in vivo photodynamic therapy of cancer,” J. Am. Chem. Soc. 130(32), 10643–10647 (2008).
    1. Urano Y., “Sensitive and selective tumor imaging with novel and highly activatable fluorescence probes,” Anal. Sci. 24(1), 51–53 (2008).ANSCEN10.2116/analsci.24.51
    1. Chang S. K., et al. , “Combined reflectance and fluorescence spectroscopy for in vivo detection of cervical pre-cancer,” J. Biomed. Opt. 10(2), 024031 (2005).JBOPFO10.1117/1.1899686
    1. Kester R. T., et al. , “Real-time hyperspectral endoscope for early cancer diagnostics,” Proc. SPIE 7555, 75550A (2010).PSISDG10.1117/12.842726
    1. Crow P., et al. , “The use of Raman spectroscopy to identify and grade prostatic adenocarcinoma in vitro,” Br. J. Cancer 89(1), 106–108 (2003).BJCAAI10.1038/sj.bjc.6601059

Source: PubMed

スポンサーと協力者

医学的状態

薬物療法

3
購読する