高光谱成像在头颈部肿瘤诊疗中的应用现状

doi:10.3760/cma.j.cn371439-20231026-00050

摘要/Abstract

摘要：

头颈部肿瘤是一种常见的恶性肿瘤，其发病率和死亡率在全球范围内均呈上升趋势。传统的头颈部肿瘤诊断方法受制于缺乏特异性的生物标志物和侵入性检测方法的局限性，存在时间成本和误诊率偏高等问题，因此需要开展基于新技术的头颈部肿瘤诊断研究。高光谱成像（HSI）是一种非接触式光学成像方式，通过在数个光谱波段获取一系列图像，从而产生一个高光谱图像立方体。HSI在头颈部肿瘤早期诊断、癌缘识别、临床研究等方面展现了其相应的潜力。

关键词: 头颈部肿瘤, 高光谱成像, 临床诊断, 机器学习, 深度学习

Abstract:

Head and neck tumor is a common malignant tumor with increasing incidence and mortality worldwide. Traditional diagnostic methods for head and neck tumor are limited by the lack of specific biomarkers and the limitation of invasive detection methods， as well as high time cost and a high rate of misdiagnosis. Therefore， research on head and neck tumor diagnosis based on new technologies is needed. Hyperspectral imaging （HSI） is a non-contact optical imaging technique that captures a series of images in multiple spectral bands to generate a hyperspectral image cube. HSI has shown its corresponding potential in the early diagnosis， tumor margin identification and clinical research of head and neck cancer.

Key words: Head and neck neoplasms, Hyperspectral imaging, Clinical diagnosis, Machine learning, Deep learning

陈琦, 徐晨阳, 王寅, 雷大鹏. 高光谱成像在头颈部肿瘤诊疗中的应用现状[J]. 国际肿瘤学杂志, 2024, 51(5): 298-302.

Chen Qi, Xu Chenyang, Wang Yin, Lei Dapeng. Current application status of hyperspectral imaging in the diagnosis and treatment of head and neck tumor[J]. Journal of International Oncology, 2024, 51(5): 298-302.

参考文献 43

[1]	Bhat GR, Hyole RG, Li J. Head and neck cancer: current challenges and future perspectives[J]. Adv Cancer Res, 2021, 152: 67-102. DOI: 10.1016/bs.acr.2021.05.002. pmid: 34353444
[2]	Xia C, Dong X, Li H, et al. Cancer statistics in China and United States, 2022: profiles, trends, and determinants[J]. Chin Med J (Engl), 2022, 135(5): 584-590. DOI: 10.1097/CM9.0000000000002108.
[3]	Jiang S, Ma D, Tan X, et al. Bibliometric analysis of the current status and trends on medical hyperspectral imaging[J]. Front Med (Lausanne), 2023, 10: 1235955. DOI: 10.3389/fmed.2023.1235955.
[4]	Lin S, Ke Z, Liu K, et al. Identification of DAPI-stained normal, inflammatory, and carcinoma hepatic cells based on hyperspectral microscopy[J]. Biomed Opt Express, 2022, 13(4): 2082-2090. DOI: 10.1364/BOE.451006. pmid: 35519237
[5]	Brouwer de Koning SG, Weijtmans P, Karakullukcu MB, et al. Toward assessment of resection margins using hyperspectral diffuse reflection imaging (400-1, 700 nm) during tongue cancer surgery[J]. Lasers Surg Med, 2020, 52(6): 496-502. DOI: 10.1002/lsm.23161.
[6]	Barberio M, Felli E, Seyller E, et al. Quantitative fluorescence angiography versus hyperspectral imaging to assess bowel ischemia: a comparative study in enhanced reality[J]. Surgery, 2020, 168(1): 178-184. DOI: 10.1016/j.surg.2020.02.008.
[7]	Trajanovski S, Shan C, Weijtmans PJC, et al. Tongue tumor detection in hyperspectral images using deep learning semantic segmentation[J]. IEEE Trans Biomed Eng, 2021, 68(4): 1330-1340. DOI: 10.1109/TBME.2020.3026683.
[8]	Schimunek L, Schöpp K, Wagner M, et al. Hyperspectral imaging as a new diagnostic tool for cervical intraepithelial neoplasia[J]. Arch Gynecol Obstet, 2023, 308(5): 1525-1530. DOI: 10.1007/s00404-023-07171-w. pmid: 37574506
[9]	张冬, 张俊华, 孟昭鹏, 等. 基于高光谱图像技术的中医舌诊客观化研究展望[J]. 中国中医基础医学杂志, 2019, 25(9): 1324-1326. DOI: 10.19945/j.cnki.issn.1006-3250.2019.09.033.
[10]	Campbell JM, Mahbub SB, Habibalahi A, et al. Clinical applications of non-invasive multi and hyperspectral imaging of cell and tissue autofluorescence beyond oncology[J]. J Biophotonics, 2023, 16(4): e202200264. DOI: 10.1002/jbio.202200264.
[11]	Edwards K, Halicek M, Little JV, et al. Multiparametric radiomics for predicting the aggressiveness of papillary thyroid carcinoma using hyperspectral images[J]. Proc SPIE Int Soc Opt Eng, 2021, 11597: 1159728. DOI: 10.1117/12.2582147.
[12]	Halicek M, Fabelo H, Ortega S, et al. Cancer detection using hyperspectral imaging and evaluation of the superficial tumor margin variance with depth[J]. Proc SPIE Int Soc Opt Eng, 2019, 10951: 109511A. DOI: 10.1117/12.2512985.
[13]	Halicek M, Fabelo H, Ortega S, et al. Hyperspectral imaging for head and neck cancer detection: specular glare and variance of the tumor margin in surgical specimens[J]. J Med Imaging (Bellingham), 2019, 6(3): 035004. DOI: 10.1117/1.JMI.6.3.035004.
[14]	Maktabi M, Wichmann Y, Köhler H, et al. Tumor cell identification and classification in esophageal adenocarcinoma specimens by hyperspectral imaging[J]. Sci Rep, 2022, 12(1): 4508. DOI: 10.1038/s41598-022-07524-6. pmid: 35296685
[15]	Tran MH, Ma L, Litter JV, et al. Thyroid carcinoma detection on whole histologic slides using hyperspectral imaging and deep learning[J]. Proc SPIE Int Soc Opt Eng, 2022, 12039: 120390H. DOI: 10.1117/12.2612963.
[16]	Halicek M, Dormer JD, Little JV, et al. Hyperspectral imaging of head and neck squamous cell carcinoma for cancer margin detection in surgical specimens from 102 patients using deep learning[J]. Cancers (Basel), 2019, 11(9): 1367. DOI: 10.3390/cancers11091367.
[17]	Ma L, Little JV, Chen AY, et al. Automatic detection of head and neck squamous cell carcinoma on histologic slides using hyperspectral microscopic imaging (Erratum)[J]. J Biomed Opt, 2022, 27(5): 059802. DOI: 10.1117/1.JBO.27.5.059802.
[18]	Halicek M, Fabelo H, Ortega S, et al. In-vivo and ex-vivo tissue analysis through hyperspectral imaging techniques: revealing the invisible features of cancer[J]. Cancers (Basel), 2019, 11(6): 756. DOI: 10.3390/cancers11060756.
[19]	李伟, 吕蒙, 陈天虹, 等. 高光谱图像在生物医学中的应用[J]. 中国图象图形学报, 2021, 26(8): 1764-1785. DOI: 10.11834/jig.210191.
[20]	Chu YW, Chen F, Tang Y, et al. Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method[J]. Opt Express, 2018, 26(22): 28661-28671. DOI: 10.1364/OE.26.028661. pmid: 30470039
[21]	Halicek M, Dormer JD, Little JV, et al. Tumor detection of the thyroid and salivary glands using hyperspectral imaging and deep learning[J]. Biomed Opt Express, 2020, 11(3): 1383-1400. DOI: 10.1364/BOE.381257. pmid: 32206417
[22]	Wisotzky EL, Uecker FC, Arens P, et al. Intraoperative hyperspectral determination of human tissue properties[J]. J Biomed Opt, 2018, 23(9): 1-8. DOI: 10.1117/1.JBO.23.9.091409. pmid: 29745130
[23]	Barberio M, Maktabi M, Gockel I, et al. Hyperspectral based discrimination of thyroid and parathyroid during surgery[J]. Curr Dir Biomed Eng, 2018, 4(1): 399-402. DOI: 10.1515/cdbme-2018-0095.
[24]	Maktabi M, Köhler H, Ivanova M, et al. Classification of hyperspectral endocrine tissue images using support vector machines[J]. Int J Med Robot, 2020, 16(5): 1-10. DOI: 10.1002/rcs.2121.
[25]	Thiem DGE, Frick RW, Goetze E, et al. Hyperspectral analysis for perioperative perfusion monitoring—a clinical feasibility study on free and pedicled flaps[J]. Clin Oral Investig, 2021, 25(3): 933-945. DOI: 10.1007/s00784-020-03382-6.
[26]	Chen B, Leung LL, Qu X, et al. Extracellular vesicles as biomar-kers in head and neck squamous cell carcinoma: from diagnosis to disease-free survival[J]. Cancers (Basel), 2023, 15(6): 1826. DOI: 10.3390/cancers15061826.
[27]	Wang Y, Zhang Q, Yuan W, et al. Hyperspectral imaging-based exosome microarray for rapid molecular profiling of extracellular vesicles[J]. Lab Chip, 2021, 21(1): 196-204. DOI: 10.1039/d0lc01006e. pmid: 33289759
[28]	Chandel V, Maru S, Kumar A, et al. Role of monocarboxylate transporters in head and neck squamous cell carcinoma[J]. Life Sci, 2021, 279: 119709. DOI: 10.1016/j.lfs.2021.119709.
[29]	Ippolito L, Morandi A, Giannoni E, et al. Lactate: a metabolic driver in the tumour landscape[J]. Trends Biochem Sci, 2019, 44(2): 153-166. DOI: 10.1016/j.tibs.2018.10.011. pmid: 30473428
[30]	Moharram MA, Sundaram DM. Dimensionality reduction strategies for land use land cover classification based on airborne hyperspectral imagery: a survey[J]. Environ Sci Pollut Res Int, 2023, 30(3): 5580-5602. DOI: 10.1007/s11356-022-24202-2.
[31]	Cruz-Tirado JP, Amigo JM, Barbin DF, et al. Data reduction by randomization subsampling for the study of large hyperspectral datasets[J]. Anal Chim Acta, 2022, 1209: 339793. DOI: 10.1016/j.aca.2022.339793.
[32]	Ma L, Halicek M, Fei B. In vivo cancer detection in animal model using hyperspectral image classification with wavelet feature extraction[J]. Proc SPIE Int Soc Opt Eng, 2020, 11317: 113171C. DOI: 10.1117/12.2549397.
[33]	Dremin V, Marcinkevics Z, Zherebtsov E, et al. Skin complications of diabetes mellitus revealed by polarized hyperspectral imaging and machine learning[J]. IEEE Trans Med Imaging, 2021, 40(4): 1207-1216. DOI: 10.1109/TMI.2021.3049591.
[34]	Liu L, Qi M, Li Y, et al. Staging of skin cancer based on hyperspectral microscopic imaging and machine learning[J]. Biosensors (Basel), 2022, 12(10): 790. DOI: 10.3390/bios12100790.
[35]	Eggert D, Bengs M, Westermann S, et al. In vivo detection of head and neck tumors by hyperspectral imaging combined with deep learning methods[J]. J Biophotonics, 2022, 15(3): e202100167. DOI: 10.1002/jbio.202100167.
[36]	Halicek M, Little JV, Wang X, et al. Tumor margin classification of head and neck cancer using hyperspectral imaging and convolutional neural networks[J]. Proc SPIE Int Soc Opt Eng, 2018, 10576: 1057605. DOI: 10.1117/12.2293167.
[37]	Ma L, Zhou X, Little JV, et al. Hyperspectral microscopic imaging for the detection of head and neck squamous cell carcinoma on histologic slides[J]. Proc SPIE Int Soc Opt Eng, 2021, 11603: 116030P. DOI: 10.1117/12.2581970.
[38]	Ortega S, Halicek M, Fabelo H, et al. Hyperspectral imaging and deep learning for the detection of breast cancer cells in digitized histological images[J]. Proc SPIE Int Soc Opt Eng, 2020, 11320: 113200V. DOI: 10.1117/12.2548609.
[39]	Zeng W, Li W, Zhang M, et al. Microscopic hyperspectral image classification based on fusion transformer with parallel CNN[J]. IEEE J Biomed Health Inform, 2023, 27(6): 2910-2921. DOI: 10.1109/JBHI.2023.3253722.
[40]	Karim S, Qadir A, Farooq U, et al. Hyperspectral imaging: a review and trends towards medical imaging[J]. Curr Med Imaging, 2022, 19(5): 417-427. DOI: 10.2174/157340561866622051914 4358.
[41]	Halicek M, Lu G, Little JV, et al. Deep convolutional neural networks for classifying head and neck cancer using hyperspectral imaging[J]. J Biomed Opt, 2017, 22(6): 60503. DOI: 10.1117/1.JBO.22.6.060503. pmid: 28655055
[42]	Halicek M, Little JV, Wang X, et al. Optical biopsy of head and neck cancer using hyperspectral imaging and convolutional neural networks[J]. Proc SPIE Int Soc Opt Eng, 2018, 10469: 104690X. DOI: 10.1117/12.2289023.
[43]	Selci S. The future of hyperspectral imaging[J]. J Imaging, 2019, 5(11): 84. DOI: 10.3390/jimaging5110084.