Abstract
Thyroid cancer, a common endocrine malignancy, is one of the leading death causes among endocrine tumors. The diagnosis of pathological section analysis suffers from diagnostic delay and cumbersome operating procedures. Therefore, we intend to construct the models based on spectral data that can be potentially used for rapid intraoperative papillary thyroid carcinoma (PTC) diagnosis and characterize PTC characteristics. To alleviate any concerns pathologists may have about using the model, we conducted an analysis of the used bands that can be interpreted pathologically. A spectra acquisition system was first built to acquire spectra of pathological section images from 91 patients. The obtained spectral dataset contains 217 spectra of normal thyroid tissue and 217 spectra of PTC tissue. Clinical data of the corresponding patients were collected for subsequent model interpretability analysis. The experiment has been approved by the Ethics Review Committee of the Wuhu Hospital of East China Normal University. The spectral preprocessing method was used to process the spectra, and the preprocessed signal respectively optimized by the first and secondary informative wavelengths selection was used to develop the PTC detection models. The PTC detection model using mean centering (MC) and multiple scattering correction (MSC) has optimal performance, and the reasons for the good performance were analyzed in combination with the spectral acquisition process and composition of the test slide. For model interpretable analysis, the near-ultraviolet band selected for modeling corresponds to the location of amino acid absorption peak, and this is consistent with the clinical phenomenon of significantly lower amino acid concentrations in PTC patients. Moreover, the absorption peak of hemoglobin selected for modeling is consistent with the low hemoglobin index in PTC patients. In addition, the correlation analysis was performed between the selected wavelengths and the clinical data, and the results show: the reflection intensity of selected wavelengths in normal cells has a moderate correlation with cell arrangement structure, nucleus size and free thyroxine (FT4), and has a strong correlation with triiodothyronine (T3); the reflection intensity of selected bands in PTC cells has a moderate correlation with free triiodothyronine (FT3).
Similar content being viewed by others
Data Availability Statement
The relevant thyroid spectrum dataset has been deposited in figshare (https://figshare.com). The project DOI is https://doi.org/10.6084/m9.figshare.21579546.
Abbreviations
- PTC:
-
Papillary thyroid carcinoma
- NIR:
-
Near infrared
- HE:
-
Hematoxylin-eosin
- SVM:
-
Support vector machines
- CARS:
-
Competitive adaptive reweighted sampling
- FD:
-
First derivative
- SD:
-
Second derivative
- SG:
-
Savitzky–Golay
- MC:
-
Mean centering
- SNV:
-
Standard normal variate
- MSC:
-
Multiplicative scatter correction
- PLS:
-
Partial least squares
- RMSECV:
-
Root mean square error of cross validation
- T3:
-
Triiodothyronine
- T4:
-
Tetraiodothyronine
- FT3:
-
Free triiodothyronine
- FT4:
-
Free thyroxine
References
Abooshahab R, Hooshmand K, Razavi SA, Gholami M, Hedayati M (2020) Plasma metabolic profiling of human thyroid nodules by Gas Chromatography-Mass Spectrometry (GC-MS)-Based untargeted metabolomics. Front Cell Dev Biol 8:385. https://doi.org/10.3389/fcell.2020.00385
Avital H, Rasnik KS (2016) Increased rates of advanced thyroid cancer in California. J Surg Res 201(1):244–252. https://doi.org/10.1016/j.jss.2015.10.037
Barberio M, Maktabi M, Gockel I, Rayes N, Jansen-Winkeln B, Köhler H, Rabe SM, Seidemann L, Takoh JP, Diana M, Neumuth T, Chalopin C (2018) Hyperspectral based discrimination of thyroid and parathyroid during surgery. Curr Dir Biomed Eng 4(1):399–402. https://doi.org/10.1515/cdbme-2018-0095
Cui H, Zhou L, Li Y, Kang B (2022) Belief entropy-of-entropy and its application in the cardiac interbeat interval time series analysis. Chaos Solitons Fractals 155:111736. https://doi.org/10.1016/j.chaos.2021.111736
Chowdhury SR, Sharma G, Arora Y (2020) Cerebral oxygenation studies through near infrared spectroscopy: a review. Adv Mater Lett 11(3):1–10. https://doi.org/10.5185/amlett.2020.031482
Chen C, Du G, Tong D, Lv G, Lv X, Si R, Tang J, Li H, Ma H, Mo J (2019) Exploration research on the fusion of multimodal spectrum technology to improve performance of rapid diagnosis scheme for thyroid dysfunction. J Biophotonics 13(2):e201900099. https://doi.org/10.1002/jbio.201900099
Cheng Q, Li X, Acharya CR, Hyslop T, Sosa JA (2017) A novel integrative risk index of papillary thyroid cancer progression combining genomic alterations and clinical factors. Oncotarget 8(10):16690–16703. https://doi.org/10.18632/oncotarget.15128
Cosimo D, Teresa M, Massimo T, Marco A, Fabio M, Salvatore T, Giuseppe C, Domenico M, Rocco B, Fabiana T, Michela M, Adele M, Rosaria D, Laura G, Giuseppe R, Sebastiano F (2013) Papillary thyroid cancer: time course of recurrences during postsurgery surveillance. J Clin Endocrinol Metab 98(2):636–642. https://doi.org/10.1210/jc.2012-340
Cooper G, Gordon M, Tulumello D, Turci C, Kaznatcheev K, Hitchcock AP (2004) Inner shell excitation of glycine, glycyl-glycine, alanine and phenylalanine. J Electron Spectrosc Relat Phenom 137:795–799. https://doi.org/10.1016/j.elspec.2004.02.102
Dervieux E, Bodinier Q, Uhring W, Théron M (2021) Measuring hemoglobin spectra:searching for carbamino-hemoglobin. J Biomed Opt 25(10):105001. https://doi.org/10.1117/1.JBO.25.10.105001
Dicker DT, Lerner J, Van-Belle P, Barth SF, Guerry D IV, Herlyn M, Elder DE, El-Deiry WS (2006) Differentiation of normal skin and melanoma using high resolution hyperspectral imaging. Cancer Biol Ther 5(8):1033–1038
Fu J, Yu H, Chen Z, Yun Y (2022) A review on hybrid strategy-based wavelength selection methods in analysis of near-infrared spectral data. Infrared Phys Technol 125:104231. https://doi.org/10.1016/j.infrared.2022.104231
Fontenelle LC, Feitosa MM, Severo JS, Freitas TEC, Morais JBS, Torres-Leal FL, Henriques GS, Marreiro DDN (2016) Thyroid function in human obesity: underlying mechanisms. Horm Metab Res 48(12):787–794. https://doi.org/10.1055/S-0042-121421
Fan W, Shan Y, Li G, Lv H, Li H, Liang Y (2012) Application of competitive adaptive reweighted sampling method to determine effective wavelengths for prediction of total acid of vinegar. Food Anal Methods 5(3):585–590. https://doi.org/10.1007/s12161-011-9285-2
Giacomelli MG, Husvogt L, Vardeh H, Faulknerjones BE, Hornegger J, Connolly JL, Fujimoto JG (2016) Virtual hematoxylin and eosin transillumination microscopy using epi-fluorescence imaging. PLoS One 11(8):e0159337. https://doi.org/10.1371/journal.pone.0159337
Hu M, Chen X, Ye P, Chen X, Shi Y, Zhai G, Yang X (2016) Combination of multiple model population analysis and mid-infrared technology for the estimation of copper content in Tegillarca granosa. Infrared Phys Technol 79:198–204. https://doi.org/10.1016/j.infrared.2016.10.009
Issa MM, Nejem RM, Stefan RI, Aboul-Enein HY (2015) New approach application of data transformation in mean centering of ratio spectra method. Spectrochim Acta Part A Mol Biomol Spectrosc 142:204–209. https://doi.org/10.1016/j.saa.2015.01.064
Kamal AM, Pal UM, Nayak A, Medisetti T, Arjun BS, Pandya HJ (2021) Towards development of LED-Based time-domain Near-IR spectroscopy system for delineating breast cancer from adjacent normal tissue. IEEE Sens J 21(16):17758–17765. https://doi.org/10.1109/JSEN.2021.3082850
Kuipers BJH, Gruppen H (2007) Prediction of molar extinction coefficients of proteins and peptides using uv absorption of the constituent amino acids at 214 nm to enable quantitative reverse phase high-performance liquid chromatography- mass spectrometry analysis. J Agric Food Chem 55(14):5445–5451. https://doi.org/10.1021/jf070337l
Lao C, Chen J, Zhang Z, Chen Y, Ma Y, Chen H, Gu X, Ning J, Jin J, Li X (2021) Predicting the contents of soil salt and major water-soluble ions with fractional-order derivative spectral indices and variable selection. Comput Electron Agric 182:106031. https://doi.org/10.1016/j.compag.2021.106031
Luisa A, Miresan V, Coroian A, Pop I, Raducu C, Rotaru A, Cocan D, Pânzaru SC, Domsa I, Coroian CO (2015) Raman spectroscopy of the hematoxylin - eosin stained tissue. ProEnvironmen 8(24):590–600
Mill J, Li L (2022) Recent advances in understanding of Alzheimer’s disease progression through mass spectrometry-based metabolomics. Phenomics 2:1–17. https://doi.org/10.1007/s43657-021-00036-9
Ma L, Tan G, Luo H, Liao Q, Li S, Li K (2022) A novel deep learning framework for automatic recognition of thyroid gland and tissues of neck in ultrasound image. IEEE Trans Circ Syst Video Technol 32(9):6113–6124. https://doi.org/10.1109/TCSVT.2022.3157828
Miia, HURSKAINEN (2019) Attempt to reliably identify oral cancer salivary biomarkers using near-infrared spectroscopy and Savitzky-Golay algorithm. 2019 International Conference on Informatics, Control and Robotics, pp 234–237. https://doi.org/10.12783/dtetr/icicr2019/30575
Medeiros-Neto LP, Soto CAT, Chagas MJ, Carvalho LFC, Rajasekaran R, Martin AA (2019) In vivo Raman spectroscopic characterization of papillary thyroid carcinoma. Vib Spectrosc 101:1–9. https://doi.org/10.1016/j.vibspec.2018.12.008
Mehnati P, Tirtash MJ, Zakerhamidi MS, Mehnati P (2016) Assessing absorption coefficient of hemoglobin in the breast phantom using near-infrared spectroscopy. Iran J Radiol 13(4):e31581. https://doi.org/10.5812/iranjradiol.31581
Marín NM, Milbourne A, Rhodes H, Ehlen T, Miller D, Benedet L, Richards-Kortum R, Follen M (2005) Diffuse reflectance patterns in cervical spectroscopy. Gynecolog Oncol 99(3–supp):S116–S120. https://doi.org/10.1016/j.ygyno.2005.07.054
Rinschen MM, Ivanisevic J, Giera M, Siuzdak G (2019) Identification of bioactive metabolites using activity metabolomics. Nat Rev Mol Cell Biol 20(6):353–367. https://doi.org/10.1038/s41580-019-0108-4
Roll W, Markwardt NA, Masthoff M, Helfen A, Claussen J, Eisenblaetter M, Hasenbach A, Hermann S, Karlas A, Wildgruber M, Ntziachristos V, Schaefers M (2019) Multispectral optoacoustic tomography of benign and malignant thyroid disorders: a pilot study. J Nucl Med 60(10):1461–1466. https://doi.org/10.2967/jnumed.118.222174
Santana FB, Daly K (2022) A comparative study of MIR and NIR spectral models using ball-milled and sieved soil for the prediction of a range soil physical and chemical parameters. Spectrochim Acta Part A Mol Biomol Spectrosc 279:121441. https://doi.org/10.1016/j.saa.2022.121441
Stenman S, Bychkov D, Kücükel H, Linder N, Haglund C, Arola J, Lundin J (2021) Antibody supervised training of a deep learning based algorithm for leukocyte segmentation in papillary thyroid carcinoma. IEEE J Biomed Health Inform 25(2):422–428. https://doi.org/10.1109/JBHI.2020.2994970
Sbroscia M, Gioacchino MD, Ascenzi P, Crucitti P, Masi AD, Giovannoni I, Longo F, Mariotti D, Naciu AM, Palermo A, Taffon C, Verri M, Sodo A, Crescenzi A, Ricci MA (2020) Thyroid cancer diagnosis by Raman spectroscopy. Sci Rep 10(1):13342. https://doi.org/10.1038/s41598-020-70165-0
Shurrab K, Kochaji N, Bachir W (2020) Elastic scattering spectroscopy for monitoring skin cancer transformation and therapy in the near infrared window. Lasers Med Sci 35(3):701–708. https://doi.org/10.1007/s10103-019-02894-2
Siegel RL, Miller KD (2019) Jemal A (2019) Cancer statistics. CA Cancer J Clin 69(1):7–34. https://doi.org/10.3322/caac.21551
Silalahi DD, Midi H, Arasan J, Mustafa MS, Caliman JP (2018) Robust generalized multiplicative scatter correction algorithm on pretreatment of near infrared spectral data. Vib Spectrosc 97:55–65. https://doi.org/10.1016/j.vibspec.2018.05.002
Shen C, Zhang Y, Liu Y, Yin S, Zhang X, Wei W, Sun Z, Song H, Qiu Z, Wang C, Luo Q (2017) A distinct serum metabolic signature of distant metastatic papillary thyroid carcinoma. Clin Endocrinol 87(6):844–852. https://doi.org/10.1111/cen.13437
Sprague BL, Trentham-Dietz A, Remington PL (2011) The contribution of postmenopausal hormone use cessation to the declining incidence of breast cancer. Cancer Causes Control 22(1):125–134. https://doi.org/10.1007/s10552-010-9682-7
Trajanovski S, Shan C, Weijtmans PJC, Koning SGBD, Ruers TJM (2021) Tongue tumor detection in hyperspectral images using deep learning semantic segmentation. IEEE Trans Biomed Eng 68(4):1330–1340. https://doi.org/10.1109/TBME.2020.3026683
Veld DCGD, Skurichina M, Witjes MJH, Duin RPW, Sterenborg HJCM, Roodenburg JLN (2005) Autofluorescence and diffuse reflectance spectroscopy for oral oncology. Lasers Surg Med 36(5):356–364. https://doi.org/10.1002/lsm.20122
Zhao X, Shen X, Wan W, Lu Y, Hu S, Xiao R, Du X, Li J (2022) Automatic thyroid ultrasound image classification using feature fusion network. IEEE Access 10:27917–27924. https://doi.org/10.1109/ACCESS.2022.3156096
Zhang G, Hao H, Wang Y, Jiang Y, Shi J, Yu J, Cui X, Li J, Zhou S, Yu B (2021) Optimized adaptive Savitzky-Golay filtering algorithm based on deep learning network for absorption spectroscopy. Spectrochim Acta Part A Mol Biomol Spectrosc 263:120187. https://doi.org/10.1016/j.saa.2021.120187
Funding
This work was supported by the grant awarded by the National Natural Science Foundation of China (No. 62225112; No. 61831015), and the key research and development project of Anhui Province (No. 202104j07020059).
Author information
Authors and Affiliations
Contributions
BLZ contributed to literature searching and wrote the manuscript. BLZ, Y Wang, and MHH designed the experiments and interpreted the results of the manuscript. BLZ, Y Wang, MHH, Y Wu, JNL, QLL, MD, WQS, and GTZ supervised the study and revised the manuscript. All authors read and approved the final manuscript.
Corresponding authors
Ethics declarations
Conflict of Interest
The authors declare that they have no competing interests.
Ethical Approval
The study had passed the Ethical Review of the Medical Ethics Committee of the Second People's Hospital of Wuhu, which agreed to the implementation of the study.
Consent to Participate
Written informed consent was obtained from all the participants.
Consent for Publication
All the participants approved to publish.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhao, B., Wang, Y., Hu, M. et al. Auxiliary Diagnosis of Papillary Thyroid Carcinoma Based on Spectral Phenotype. Phenomics 3, 469–484 (2023). https://doi.org/10.1007/s43657-023-00113-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s43657-023-00113-1