利用张量建模的光谱-空间分类用于基于高光谱成像的癌症检测
Spectral-Spatial Classification Using Tensor Modeling for Cancer Detection with Hyperspectral Imaging.
作者信息
Lu Guolan, Halig Luma, Wang Dongsheng, Chen Zhuo Georgia, Fei Baowei
机构信息
The Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA.
Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA.
出版信息
Proc SPIE Int Soc Opt Eng. 2014 Mar 21;9034:903413. doi: 10.1117/12.2043796.
Abstract
As an emerging technology, hyperspectral imaging (HSI) combines both the chemical specificity of spectroscopy and the spatial resolution of imaging, which may provide a non-invasive tool for cancer detection and diagnosis. Early detection of malignant lesions could improve both survival and quality of life of cancer patients. In this paper, we introduce a tensor-based computation and modeling framework for the analysis of hyperspectral images to detect head and neck cancer. The proposed classification method can distinguish between malignant tissue and healthy tissue with an average sensitivity of 96.97% and an average specificity of 91.42% in tumor-bearing mice. The hyperspectral imaging and classification technology has been demonstrated in animal models and can have many potential applications in cancer research and management.
摘要
作为一种新兴技术，高光谱成像（HSI）结合了光谱学的化学特异性和成像的空间分辨率，这可能为癌症检测和诊断提供一种非侵入性工具。恶性病变的早期检测可以提高癌症患者的生存率和生活质量。在本文中，我们介绍了一种基于张量的计算和建模框架，用于分析高光谱图像以检测头颈癌。所提出的分类方法在荷瘤小鼠中区分恶性组织和健康组织的平均灵敏度为96.97%，平均特异性为91.42%。高光谱成像和分类技术已在动物模型中得到验证，并且在癌症研究和管理中可能有许多潜在应用。
相似文献
1
Spectral-Spatial Classification Using Tensor Modeling for Cancer Detection with Hyperspectral Imaging.利用张量建模的光谱-空间分类用于基于高光谱成像的癌症检测
Proc SPIE Int Soc Opt Eng. 2014 Mar 21;9034:903413. doi: 10.1117/12.2043796.
2
Superpixel-based spectral classification for the detection of head and neck cancer with hyperspectral imaging.基于超像素的光谱分类用于通过高光谱成像检测头颈癌。
Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9788. doi: 10.1117/12.2216559. Epub 2016 Mar 29.
3
Deep Learning based Classification for Head and Neck Cancer Detection with Hyperspectral Imaging in an Animal Model.基于深度学习的动物模型高光谱成像对头颈部癌症的检测分类
Proc SPIE Int Soc Opt Eng. 2017 Feb;10137. doi: 10.1117/12.2255562. Epub 2017 Mar 13.
4
Spectral-spatial classification for noninvasive cancer detection using hyperspectral imaging.使用高光谱成像进行非侵入性癌症检测的光谱-空间分类
J Biomed Opt. 2014;19(10):106004. doi: 10.1117/1.JBO.19.10.106004.
5
Hyperspectral Imaging of Neoplastic Progression in a Mouse Model of Oral Carcinogenesis.口腔癌发生小鼠模型中肿瘤进展的高光谱成像
Proc SPIE Int Soc Opt Eng. 2016 Feb 27;9788. doi: 10.1117/12.2216553. Epub 2016 Mar 29.
6
Cancer Detection in Animal Model Using Hyperspectral Image Classification with Wavelet Feature Extraction.基于小波特征提取的高光谱图像分类在动物模型中的癌症检测
Proc SPIE Int Soc Opt Eng. 2020 Feb;11317. doi: 10.1117/12.2549397. Epub 2020 Feb 28.
7
Tumor margin assessment of surgical tissue specimen of cancer patients using label-free hyperspectral imaging.使用无标记高光谱成像技术对癌症患者手术组织标本进行肿瘤边缘评估。
Proc SPIE Int Soc Opt Eng. 2017 Jan-Feb;10054. doi: 10.1117/12.2249803. Epub 2017 Feb 14.
8
Label-free reflectance hyperspectral imaging for tumor margin assessment: a pilot study on surgical specimens of cancer patients.用于肿瘤边缘评估的无标记反射率高光谱成像：癌症患者手术标本的初步研究
J Biomed Opt. 2017 Aug;22(8):1-7. doi: 10.1117/1.JBO.22.8.086009.
9
Prior-Based Tensor Approximation for Anomaly Detection in Hyperspectral Imagery.基于先验的张量逼近用于高光谱图像中的异常检测
IEEE Trans Neural Netw Learn Syst. 2022 Mar;33(3):1037-1050. doi: 10.1109/TNNLS.2020.3038659. Epub 2022 Feb 28.
10
Hyperspectral Imaging for Cancer Surgical Margin Delineation: Registration of Hyperspectral and Histological Images.用于癌症手术切缘描绘的高光谱成像：高光谱图像与组织学图像的配准
Proc SPIE Int Soc Opt Eng. 2014 Mar 12;9036:90360S. doi: 10.1117/12.2043805.
引用本文的文献
1
Polarized Hyperspectral Microscopic Imaging for Zebrafish.用于斑马鱼的偏振高光谱显微成像
Proc SPIE Int Soc Opt Eng. 2024 Jan-Feb;12834. doi: 10.1117/12.3007294. Epub 2024 Mar 12.
2
An Ensemble Learning Method for Detection of Head and Neck Squamous Cell Carcinoma Using Polarized Hyperspectral Microscopic Imaging.一种使用偏振高光谱显微成像检测头颈鳞状细胞癌的集成学习方法。
Proc SPIE Int Soc Opt Eng. 2024 Feb;12933. doi: 10.1117/12.3007869. Epub 2024 Apr 3.
3
Polarized Hyperspectral Microscopic Imaging for White Blood Cells on Wright-Stained Blood Smear Slides.用于瑞氏染色血涂片玻片上白细胞的偏振高光谱显微成像
Proc SPIE Int Soc Opt Eng. 2023 Jan-Feb;12382. doi: 10.1117/12.2655708. Epub 2023 Mar 15.
4
Polarized hyperspectral microscopic imaging for collagen visualization on pathologic slides of head and neck squamous cell carcinoma.用于在头颈部鳞状细胞癌病理切片上进行胶原蛋白可视化的偏振高光谱显微成像。
Proc SPIE Int Soc Opt Eng. 2023 Jan-Feb;12382. doi: 10.1117/12.2655831. Epub 2023 Mar 15.
5
Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and deep learning.利用偏振高光谱成像和深度学习在病理切片上自动检测头颈部鳞状细胞癌。
Proc SPIE Int Soc Opt Eng. 2022 Feb-Mar;12039. doi: 10.1117/12.2614624. Epub 2022 Apr 4.
6
Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging.运用高光谱成像技术对食管腺癌标本中的肿瘤细胞进行鉴定和分类。
Sci Rep. 2022 Mar 16;12(1):4508. doi: 10.1038/s41598-022-07524-6.
7
Automatic detection of head and neck squamous cell carcinoma on pathologic slides using polarized hyperspectral imaging and machine learning.使用偏振高光谱成像和机器学习在病理切片上自动检测头颈部鳞状细胞癌。
Proc SPIE Int Soc Opt Eng. 2021 Feb;11603. doi: 10.1117/12.2582330. Epub 2021 Feb 15.
8
Development of a new polarized hyperspectral imaging microscope.一种新型偏振高光谱成像显微镜的研发。
Proc SPIE Int Soc Opt Eng. 2020 Feb;11213. doi: 10.1117/12.2549676. Epub 2020 Feb 19.
9
Cancer Detection in Animal Model Using Hyperspectral Image Classification with Wavelet Feature Extraction.基于小波特征提取的高光谱图像分类在动物模型中的癌症检测
Proc SPIE Int Soc Opt Eng. 2020 Feb;11317. doi: 10.1117/12.2549397. Epub 2020 Feb 28.
10
Adaptive deep learning for head and neck cancer detection using hyperspectral imaging.使用高光谱成像的自适应深度学习用于头颈癌检测。
Vis Comput Ind Biomed Art. 2019;2(1):18. doi: 10.1186/s42492-019-0023-8. Epub 2019 Nov 21.
本文引用的文献
1
Breast Tissue Classification in Digital Tomosynthesis Images Based on Global Gradient Minimization and Texture Features.基于全局梯度最小化和纹理特征的数字断层合成图像中的乳腺组织分类
Proc SPIE Int Soc Opt Eng. 2014 Mar 21;9034:90341V. doi: 10.1117/12.2043828.
2
Mapping Cardiac Fiber Orientations from High-Resolution DTI to High-Frequency 3D Ultrasound.将高分辨率扩散张量成像的心脏纤维方向映射到高频三维超声
Proc SPIE Int Soc Opt Eng. 2014 Mar 12;9036:90361O. doi: 10.1117/12.2043821.
3
Hyperspectral Imaging for Cancer Surgical Margin Delineation: Registration of Hyperspectral and Histological Images.用于癌症手术切缘描绘的高光谱成像：高光谱图像与组织学图像的配准
Proc SPIE Int Soc Opt Eng. 2014 Mar 12;9036:90360S. doi: 10.1117/12.2043805.
4
Medical hyperspectral imaging: a review.医学高光谱成像：综述
J Biomed Opt. 2014 Jan;19(1):10901. doi: 10.1117/1.JBO.19.1.010901.
5
Extracting Cardiac Myofiber Orientations from High Frequency Ultrasound Images.从高频超声图像中提取心肌纤维方向
Proc SPIE Int Soc Opt Eng. 2013 Mar 29;8675. doi: 10.1117/12.2006494.
6
Automatic Segmentation of Right Ventricle on Ultrasound Images Using Sparse Matrix Transform and Level Set.基于稀疏矩阵变换和水平集的超声图像右心室自动分割
Proc SPIE Int Soc Opt Eng. 2013 Mar 13;8669. doi: 10.1117/12.2006490.
7
Automatic segmentation of right ventricular ultrasound images using sparse matrix transform and a level set.基于稀疏矩阵变换和水平集的右心室超声图像自动分割。
Phys Med Biol. 2013 Nov 7;58(21):7609-24. doi: 10.1088/0031-9155/58/21/7609. Epub 2013 Oct 10.
8
Detection of Cancer Metastasis Using a Novel Macroscopic Hyperspectral Method.使用新型宏观高光谱方法检测癌症转移
Proc SPIE Int Soc Opt Eng. 2012;8317:831711. doi: 10.1117/12.912026. Epub 2012 Mar 23.
9
Head and neck cancer.头颈癌
Semin Roentgenol. 2013 Jan;48(1):75-86. doi: 10.1053/j.ro.2012.09.002.
10
Tongue tumor detection in medical hyperspectral images.医学高光谱图像中的舌肿瘤检测。
Sensors (Basel). 2012;12(1):162-74. doi: 10.3390/s120100162. Epub 2011 Dec 23.
Zotero 插件