基于从高光谱显微图像中提取的共同特征识别胃癌细胞。
Identification of cancerous gastric cells based on common features extracted from hyperspectral microscopic images.
作者信息
Zhu Siqi, Su Kang, Liu Yumeng, Yin Hao, Li Zhen, Huang Furong, Chen Zhenqiang, Chen Weidong, Zhang Ge, Chen Yihong
机构信息
Key Laboratory of Optoelectronic Information and Sensing Technologies of Guangdong Higher Education Institutes, Jinan University, Guangzhou, Guangdong 510632, China ; Department of Optoelectronic Engineering, Jinan University, Guangzhou, Guangdong 510632, China.
Key Laboratory of Optoelectronic Materials Chemistry and Physics, Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou, Fujian 350002, China.
出版信息
Biomed Opt Express. 2015 Mar 4;6(4):1135-45. doi: 10.1364/BOE.6.001135. eCollection 2015 Apr 1.
Abstract
We construct a microscopic hyperspectral imaging system to distinguish between normal and cancerous gastric cells. We study common transmission-spectra features that only emerge when the samples are dyed with hematoxylin and eosin (H&E) stain. Subsequently, we classify the obtained visible-range transmission spectra of the samples into three zones. Distinct features are observed in the spectral responses between the normal and cancerous cell nuclei in each zone, which depend on the pH level of the cell nucleus. Cancerous gastric cells are precisely identified according to these features. The average cancer-cell identification accuracy obtained with a backpropagation algorithm program trained with these features is 95%.
摘要
我们构建了一个微观高光谱成像系统，用于区分正常和癌变的胃细胞。我们研究了仅在样本用苏木精和伊红（H&E）染色时才会出现的常见透射光谱特征。随后，我们将获得的样本可见光谱分为三个区域。在每个区域中，正常和癌细胞核的光谱响应呈现出明显特征，这些特征取决于细胞核的pH值。根据这些特征可精确识别出癌变的胃细胞。使用基于这些特征训练的反向传播算法程序获得的癌细胞识别平均准确率为95%。
相似文献
1
Identification of cancerous gastric cells based on common features extracted from hyperspectral microscopic images.基于从高光谱显微图像中提取的共同特征识别胃癌细胞。
Biomed Opt Express. 2015 Mar 4;6(4):1135-45. doi: 10.1364/BOE.6.001135. eCollection 2015 Apr 1.
2
Using cell nuclei features to detect colon cancer tissue in hematoxylin and eosin stained slides.利用细胞核特征在苏木精和伊红染色切片中检测结肠癌组织。
Cytometry A. 2017 Aug;91(8):785-793. doi: 10.1002/cyto.a.23175. Epub 2017 Jul 20.
3
Tumor tissue classification based on micro-hyperspectral technology and deep learning.基于显微高光谱技术和深度学习的肿瘤组织分类
Biomed Opt Express. 2019 Nov 19;10(12):6370-6389. doi: 10.1364/BOE.10.006370. eCollection 2019 Dec 1.
4
Hyperspectral Microscopic Imaging for Automatic Detection of Head and Neck Squamous Cell Carcinoma Using Histologic Image and Machine Learning.使用组织学图像和机器学习的高光谱显微成像技术对头颈部鳞状细胞癌进行自动检测
Proc SPIE Int Soc Opt Eng. 2020 Feb;11320. doi: 10.1117/12.2549369. Epub 2020 Mar 16.
5
Identification of the Citrus Greening Disease Using Spectral and Textural Features Based on Hyperspectral Imaging.基于高光谱成像技术利用光谱和纹理特征识别柑橘黄龙病
Guang Pu Xue Yu Guang Pu Fen Xi. 2016 Jul;36(7):2344-50.
6
Discriminating normal regions within cancerous hen ovarian tissue using multivariate hyperspectral image analysis.使用多变量高光谱图像分析鉴别癌性母鸡卵巢组织中的正常区域。
Rapid Commun Mass Spectrom. 2019 Feb 28;33(4):381-391. doi: 10.1002/rcm.8362.
7
Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi.用于肠道真菌鉴定与分析的双模式高光谱显微成像
Biomed Opt Express. 2018 Aug 27;9(9):4496-4508. doi: 10.1364/BOE.9.004496. eCollection 2018 Sep 1.
8
Fast Detection of Striped Stem-Borer (Chilo suppressalis Walker) Infested Rice Seedling Based on Visible/Near-Infrared Hyperspectral Imaging System.基于可见/近红外高光谱成像系统的水稻潜叶蝇快速检测。
Sensors (Basel). 2017 Oct 27;17(11):2470. doi: 10.3390/s17112470.
9
Hyperspectral Imaging and K-Means Classification for Histologic Evaluation of Ductal Carcinoma .用于导管癌组织学评估的高光谱成像与K均值分类
Front Oncol. 2018 Feb 7;8:17. doi: 10.3389/fonc.2018.00017. eCollection 2018.
10
Hyperspectral Imaging and Spectrometry-Derived Spectral Features for Bitter Pit Detection in Storage Apples.高光谱成像和光谱法衍生光谱特征在贮藏苹果苦痘病检测中的应用。
Sensors (Basel). 2018 May 15;18(5):1561. doi: 10.3390/s18051561.
引用本文的文献
1
Improving lung cancer pathological hyperspectral diagnosis through cell-level annotation refinement.通过细胞水平注释优化提高肺癌病理高光谱诊断
Sci Rep. 2025 Mar 8;15(1):8086. doi: 10.1038/s41598-025-85678-9.
2
Evaluation of Preprocessing Methods on Independent Medical Hyperspectral Databases to Improve Analysis.评价独立医学高光谱数据库预处理方法，以改善分析。
Sensors (Basel). 2022 Nov 18;22(22):8917. doi: 10.3390/s22228917.
3
Aggregation-induced heterogeneities in the emission of upconverting nanoparticles at the submicron scale unfolded by hyperspectral microscopy.通过高光谱显微镜揭示的亚微米尺度上转换纳米粒子发射中的聚集诱导异质性。
Nanoscale Adv. 2019 May 21;1(7):2537-2545. doi: 10.1039/c8na00412a. eCollection 2019 Jul 10.
4
Membranous nephropathy classification using microscopic hyperspectral imaging and tensor patch-based discriminative linear regression.利用微观高光谱成像和基于张量补丁的判别线性回归进行膜性肾病分类
Biomed Opt Express. 2021 Apr 28;12(5):2968-2978. doi: 10.1364/BOE.421345. eCollection 2021 May 1.
5
Transmissive Single-Pixel Microscopic Imaging through Scattering Media.透过散射介质的透射式单像素显微成像。
Sensors (Basel). 2021 Apr 13;21(8):2721. doi: 10.3390/s21082721.
6
Hyperspectral microscopy combined with DAPI staining for the identification of hepatic carcinoma cells.高光谱显微镜结合DAPI染色用于鉴定肝癌细胞。
Biomed Opt Express. 2020 Dec 8;12(1):173-180. doi: 10.1364/BOE.412158. eCollection 2021 Jan 1.
7
Tumor tissue classification based on micro-hyperspectral technology and deep learning.基于显微高光谱技术和深度学习的肿瘤组织分类
Biomed Opt Express. 2019 Nov 19;10(12):6370-6389. doi: 10.1364/BOE.10.006370. eCollection 2019 Dec 1.
8
Most Relevant Spectral Bands Identification for Brain Cancer Detection Using Hyperspectral Imaging.基于高光谱成像的脑癌检测中最相关光谱带的识别
Sensors (Basel). 2019 Dec 12;19(24):5481. doi: 10.3390/s19245481.
9
In-Vivo and Ex-Vivo Tissue Analysis through Hyperspectral Imaging Techniques: Revealing the Invisible Features of Cancer.通过高光谱成像技术进行体内和体外组织分析：揭示癌症的隐形特征
Cancers (Basel). 2019 May 30;11(6):756. doi: 10.3390/cancers11060756.
10
Dual-type hyperspectral microscopic imaging for the identification and analysis of intestinal fungi.用于肠道真菌鉴定与分析的双模式高光谱显微成像
Biomed Opt Express. 2018 Aug 27;9(9):4496-4508. doi: 10.1364/BOE.9.004496. eCollection 2018 Sep 1.
本文引用的文献
1
Raman difference spectroscopy: a non-invasive method for identification of oral squamous cell carcinoma.拉曼差光谱法：一种用于鉴定口腔鳞状细胞癌的非侵入性方法。
Biomed Opt Express. 2014 Aug 28;5(9):3252-65. doi: 10.1364/BOE.5.003252. eCollection 2014 Sep 1.
2
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.
3
Identification of kidney tumor tissue by infrared spectroscopy of extracellular matrix.通过细胞外基质的红外光谱法鉴定肾肿瘤组织
J Biomed Opt. 2014 Aug;19(8):087005. doi: 10.1117/1.JBO.19.8.087005.
4
Widefield optical imaging of changes in uptake of glucose and tissue extracellular pH in head and neck cancer.头颈部癌中葡萄糖摄取和组织细胞外pH值变化的宽视野光学成像
Cancer Prev Res (Phila). 2014 Oct;7(10):1035-44. doi: 10.1158/1940-6207.CAPR-14-0097. Epub 2014 Aug 19.
5
Hyperspectral reflected light microscopy of plasmonic Au/Ag alloy nanoparticles incubated as multiplex chromatic biomarkers with cancer cells.将等离子体金/银合金纳米颗粒作为多重彩色生物标志物与癌细胞一起孵育后的高光谱反射光显微镜检查。
Analyst. 2014 Oct 21;139(20):5247-53. doi: 10.1039/c4an01063a. Epub 2014 Aug 18.
6
Computer-based image studies on tumor nests mathematical features of breast cancer and their clinical prognostic value.基于计算机的图像研究对乳腺癌肿瘤巢的数学特征及其临床预后价值。
PLoS One. 2013 Dec 12;8(12):e82314. doi: 10.1371/journal.pone.0082314. eCollection 2013.
7
New method for detection of gastric cancer by hyperspectral imaging: a pilot study.基于高光谱成像的胃癌检测新方法：一项初步研究。
J Biomed Opt. 2013 Feb;18(2):26010. doi: 10.1117/1.JBO.18.2.026010.
8
Use of hyperspectral imaging to distinguish normal, precancerous, and cancerous cells.使用高光谱成像来区分正常细胞、癌前细胞和癌细胞。
Cancer. 2008 Feb 25;114(1):13-21. doi: 10.1002/cncr.23286.
9
Spectral fluorescence molecular imaging of lung metastases targeting HER2/neu.靶向HER2/neu的肺转移灶的光谱荧光分子成像
Clin Cancer Res. 2007 May 15;13(10):2936-45. doi: 10.1158/1078-0432.CCR-06-2240.
10
The relevance of tumour pH to the treatment of malignant disease.肿瘤酸碱度与恶性疾病治疗的相关性。
Radiother Oncol. 1984 Dec;2(4):343-66. doi: 10.1016/s0167-8140(84)80077-8.
Zotero 插件