A Minimum Spanning Forest-Based Method for Noninvasive Cancer Detection With Hyperspectral Imaging

Goal: The purpose of this paper is to develop a classification method that combines both spectral and spatial information for distinguishing cancer from healthy tissue on hyperspectral images in an animal model. Methods: An automated algorithm based on a minimum spanning forest (MSF) and optimal band selection has been proposed to classify healthy and cancerous tissue on hyperspectral images. A support vector machine classifier is trained to create a pixel-wise classification probability map of cancerous and healthy tissue. This map is then used to identify markers that are used to compute mutual information for a range of bands in the hyperspectral image and thus select the optimal bands. An MSF is finally grown to segment the image using spatial and spectral information. Conclusion: The MSF based method with automatically selected bands proved to be accurate in determining the tumor boundary on hyperspectral images. Significance: Hyperspectral imaging combined with the proposed classification technique has the potential to provide a noninvasive tool for cancer detection.

[1]  R. Prim.  Shortest connection networks and some generalizations , 1957 .

[2]  Guolan Lu,et al.  Estimation of tissue optical parameters with hyperspectral imaging and spectral unmixing , 2015, Medical Imaging.

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

[4]  Nicholas Stone,et al.  Correlation mapping: rapid method for identification of histological features and pathological classification in mid infrared spectroscopic images of lymph nodes. , 2010, Journal of biomedical optics.

[5]  D. Ferris,et al.  Multimodal Hyperspectral Imaging for the Noninvasive Diagnosis of Cervical Neoplasia , 2001, Journal of lower genital tract disease.

[6]  Jon Atli Benediktsson,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on a Stochastic Minimum Spanning Forest Approach , 2012, IEEE Transactions on Image Processing.

[7]  Chein-I Chang,et al.  An information-theoretic approach to spectral variability, similarity, and discrimination for hyperspectral image analysis , 2000, IEEE Trans. Inf. Theory.

[8]  Richard J. Duro,et al.  Hyperspectral image segmentation through evolved cellular automata , 2013, Pattern Recognit. Lett..

[9]  David J. Foran,et al.  A comparative performance study characterizing breast tissue microarrays using standard RGB and multispectral imaging , 2010, BiOS.

[10]  J. Stawiaski.  Mathematical morphology and graphs: application to interactive medical image segmentation , 2008 .

[11]  A. Fischer,et al.  Detection of malignancy in cytology specimens using spectral–spatial analysis , 2005, Laboratory Investigation.

[12]  Chin-Teng Lin,et al.  A Spatial–Contextual Support Vector Machine for Remotely Sensed Image Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Dongsheng Wang,et al.  Spectral-spatial classification for noninvasive cancer detection using hyperspectral imaging , 2014, Journal of biomedical optics.

[14]  Jon Atli Benediktsson,et al.  Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  D. Faller,et al.  Medical hyperspectral imaging to facilitate residual tumor identification during surgery , 2007, Cancer biology & therapy.

[16]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[17]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[18]  Dongsheng Wang,et al.  A minimum spanning forest based hyperspectral image classification method for cancerous tissue detection , 2014, Medical Imaging.

[19]  R. Richards-Kortum,et al.  Multispectral optical imaging device for in vivo detection of oral neoplasia. , 2008, Journal of biomedical optics.

[20]  Ioannis Sechopoulos,et al.  Breast tissue classification in digital tomosynthesis images based on global gradient minimization and texture features , 2014, Medical Imaging.

[21]  Xin-She Yang,et al.  Introduction to Algorithms , 2021, Nature-Inspired Optimization Algorithms.

[22]  Ahmed M. Elgammal,et al.  Face detection in complex environments from color images , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[23]  May D. Wang,et al.  Semantic interpretation of robust imaging features for Fuhrman grading of renal carcinoma , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  Ying Xu,et al.  2D image segmentation using minimum spanning trees , 1997, Image Vis. Comput..

[25]  Ioanna Kakoulli,et al.  Multispectral and hyperspectral imaging technologies in conservation: current research and potential applications , 2006 .

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

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

[28]  Yuliya Tarabalka,et al.  Spectral-spatial classification of hyperspectral images using hierarchical optimization , 2011, 2011 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[29]  Guolan Lu,et al.  Spectral-spatial classification using tensor modeling for cancer detection with hyperspectral imaging , 2014, Medical Imaging.

[30]  Anita Mahadevan-Jansen,et al.  Liquid-crystal tunable filter spectral imaging for brain tumor demarcation. , 2007, Applied optics.

[31]  Zhao Liao-ying.  Hyperspectral image classification based on compsite kernels support vector machine , 2013 .

[32]  D. Elder,et al.  Differentiation of normal skin and melanoma using high resolution hyperspectral imaging , 2006, Cancer biology & therapy.

[33]  Robert E. Tarjan,et al.  Efficient algorithms for finding minimum spanning trees in undirected and directed graphs , 1986, Comb..

[34]  Nasir M. Rajpoot,et al.  Spatial Analysis for Colon Biopsy Classification from Hyperspectral Imagery , 2008 .

[35]  Noah Bedard,et al.  Emerging Roles for Multimodal Optical Imaging in Early Cancer Detection: A Global Challenge , 2010, Technology in cancer research & treatment.

[36]  Dongsheng Wang,et al.  Hyperspectral imaging for cancer surgical margin delineation: registration of hyperspectral and histological images , 2014, Medical Imaging.

[37]  Zhuo Georgia Chen,et al.  Detection of cancer metastasis using a novel macroscopic hyperspectral method , 2012, Medical Imaging.

[38]  R. Richards-Kortum,et al.  Optical spectroscopy for detection of neoplasia. , 2002, Current opinion in chemical biology.

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

[40]  C. Mathers,et al.  Estimates of worldwide burden of cancer in 2008: GLOBOCAN 2008 , 2010, International journal of cancer.

[41]  Guozheng Yan,et al.  Bleeding detection in wireless capsule endoscopy images based on color invariants and spatial pyramids using support vector machines , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[42]  Hongjun Wang,et al.  Tongue Tumor Detection in Medical Hyperspectral Images , 2011, Sensors.

[43]  J. Kruskal.  On the shortest spanning subtree of a graph and the traveling salesman problem , 1956 .

[44]  B Fei,et al.  WE-D-9A-05: Medical Hyperspectral Imaging for the Detection of Head and Neck Cancer in Animal Models. , 2014, Medical physics.

[45]  Mourad Tighiouart,et al.  The Pivotal Role of Integrin β1 in Metastasis of Head and Neck Squamous Cell Carcinoma , 2012, Clinical Cancer Research.

[46]  Fernand Meyer,et al.  Minimum Spanning Forests for Morphological Segmentation , 1994, ISMM.

[47]  Baowei Fei,et al.  Hyperspectral imaging and spectral-spatial classification for cancer detection , 2012, 2012 5th International Conference on BioMedical Engineering and Informatics.

[48]  Dongsheng Wang,et al.  Quantitative wavelength analysis and image classification for intraoperative cancer diagnosis with hyperspectral imaging , 2015, Medical Imaging.