CoChat
Sign Up
Cited by 73Thyroid Cancer Diagnosis and TreatmentAI in cancer detectionRadiomics and Machine Learning in Medical Imaging

Artificial intelligence defines protein-based classification of thyroid nodules

Open access
Sun, Yaoting, Selvarajan, Sathiyamoorthy, Zang, Zelin, Liu, Wei, Zhu, Yi, Zhang, Hao, Chen, Wanyuan, Chen, Hao +44 more·2022·Cell Discovery
DOI 10.1038/s41421-022-00442-xPMC PMC9448820
Open this paper in CoChat — free accountOpen PDF

Abstract

Determination of malignancy in thyroid nodules remains a major diagnostic challenge. Here we report the feasibility and clinical utility of developing an AI-defined protein-based biomarker panel for diagnostic classification of thyroid nodules: based initially on formalin-fixed paraffin-embedded (FFPE), and further refined for fine-needle aspiration (FNA) tissue specimens of minute amounts which pose technical challenges for other methods. We first developed a neural network model of 19 protein biomarkers based on the proteomes of 1724 FFPE thyroid tissue samples from a retrospective cohort. This classifier achieved over 91% accuracy in the discovery set for classifying malignant thyroid nodules. The classifier was externally validated by blinded analyses in a retrospective cohort of 288 nodules (89% accuracy; FFPE) and a prospective cohort of 294 FNA biopsies (85% accuracy) from twelve independent clinical centers. This study shows that integrating high-throughput proteomics and AI technology in multi-center retrospective and prospective clinical cohorts facilitates precise disease diagnosis which is otherwise difficult to achieve by other methods.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41421-022-00442-x

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • In thyroid carcinoma proteomics data from iProX, USP15 protein level positively correlates with TBX3 among samples with both factors detectable.

    “Our findings were further supported by available thyroid carcinoma proteomics data from iProX, where USP15 protein level positively correlated with that of TBX3 among samples with both factors detectable45 (Fig. 5m, n = 52).”

    From Proteostatic reactivation of the developmental transcription factor TBX3 drives BRAF/MAPK-mediated tumorigenesis (2024) · cites this paper as [45]

    The Results (Global proteomic profiling of thyroid nodules; page unavailable) describe a quantified thyroid-tissue proteomics dataset, supporting the citation as a source for such data. The citing authors present the USP15–TBX3 correlation as their own analysis, but our copy does not establish the claimed positive correlation, the 52-sample subset, or the iProX location (searched: USP15, TBX3, iProX, and data availability). (LLM, conf=0.78)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 50

  1. [1]Burman KD Wartofsky L Clinical practice. Thyroid nodules N. Engl. J. Med. 2015 373 2347 2356 26650154
  2. [2]Jameson JL Minimizing unnecessary surgery for thyroid nodules N. Engl. J. Med. 2012 367 765 767 22731671
  3. [3]Faquin WC Bongiovanni M Sadow PM Update in thyroid fine needle aspiration Endocr. Pathol. 2011 22 178 183 21997833
  4. [4]Alexander EK Preoperative diagnosis of benign thyroid nodules with indeterminate cytology N. Engl. J. Med. 2012 367 705 715 22731672
  5. [5]Ahn HS Kim HJ Welch HG Korea’s thyroid-cancer “epidemic”—screening and overdiagnosis N. Engl. J. Med. 2014 371 1765 1767 25372084
  6. [6]Vaccarella S Worldwide thyroid-cancer epidemic? The increasing impact of overdiagnosis N. Engl. J. Med. 2016 375 614 617 27532827
  7. [7]Nikiforova MN Wald AI Roy S Durso MB Nikiforov YE Targeted next-generation sequencing panel (ThyroSeq) for detection of mutations in thyroid cancer J. Clin. Endocrinol. Metab. 2013 98 E1852 E1860 23979959 PMC3816258
  8. [8]Livhits MJ Effectiveness of molecular testing techniques for diagnosis of indeterminate thyroid nodules: a randomized clinical trial JAMA Oncol. 2020 7 70 77 PMC7729582 33300952
  9. [9]KN P Performance of a genomic sequencing classifier for the preoperative dagnosis of cytologically indeterminate thyroid nodules JAMA Surg. 2018 153 817 824 29799911 PMC6583881
  10. [10]Wang TS Sosa JA Thyroid surgery for differentiated thyroid cancer - recent advances and future directions Nat. Rev. Endocrinol. 2018 14 670 683 30131586
  11. [12]Shao S Minimal sample requirement for highly multiplexed protein quantification in cell lines and tissues by PCT-SWATH mass spectrometry Proteomics 2015 15 3711 3721 26287124
  12. [13]Shao S Reproducible tissue homogenization and protein extraction for quantitative proteomics using microPestle-assisted pressure-cycling technology J. Proteome Res 2016 15 1821 1829 27098501
  13. [14]Zhu Y High-throughput proteomic analysis of FFPE tissue samples facilitates tumor stratification Mol. Oncol. 2019 13 2305 2328 31495056 PMC6822243
  14. [15]Gillet LC Targeted data extraction of the MS/MS spectra generated by data-independent acquisition: a new concept for consistent and accurate proteome analysis Mol. Cell Proteom. 2012 11 O111.016717 PMC3433915 22261725
  15. [16]Zhang F Ge W Ruan G Cai X Guo T Data-independent acquisition mass spectrometry-based proteomics and software tools: a glimpse in 2020 Proteomics 2020 20 e1900276 32275110
  16. [17]Shao W Comparative analysis of mRNA and protein degradation in prostate tissues indicates high stability of proteins Nat. Commun. 2019 10 2524 31175306 PMC6555818
  17. [19]Sun Y Stratification of follicular thyroid tumours using data-independent acquisition proteomics and a comprehensive thyroid tissue spectral library Mol. Oncol. 2022 16 1611 1624 35194950 PMC9019893
  18. [20]Mitchell, M. (ed.) An Introduction to Generic Algorithms (The MIT Press: London, 1998).
  19. [21]Shapley, L. S. (ed.) Notes on the n-Person Game–II: The Value of an n-Person Game (The RAND Corporation: Santa Monica, 1951).
  20. [22]Roth, A. E. (ed.) The Shapley value: essays in honor of Lloyd S. Shapley (Cambridge University Press: Cambridge, 1988).
  21. [23]Farrokhi Yekta R Arefi Oskouie A Rezaei Tavirani M Mohajeri-Tehrani MR Soroush AR Decreased apolipoprotein A4 and increased complement component 3 as potential markers for papillary thyroid carcinoma: a proteomic study Int. J. Biol. Markers 2018 33 455 462 30058426
  22. [24]Ciregia F Proteomic analysis of fine-needle aspiration in differential diagnosis of thyroid nodules Transl. Res.: J. Lab. Clin. Med. 2016 176 81 94 27172385
  23. [25]Kashat L Secretome-based identification and characterization of potential biomarkers in thyroid cancer J. Proteome Res. 2010 9 5757 5769 20873772
  24. [26]Bartolazzi A Sciacchitano S D’Alessandria C Galectin-3: The impact on the clinical management of patients with thyroid nodules and future perspectives Int. J. Mol. Sci. 2018 19 445 PMC5855667 29393868
  25. [27]Schürch CM Targeting CD47 in anaplastic thyroid carcinoma enhances tumor phagocytosis by macrophages and is a promising therapeutic strategy Thyroid 2019 29 979 992 30938231 PMC6648226
  26. [28]Kim H-S Kim GY Lim S-J Kim YW Raf-1 kinase inhibitory protein expression in thyroid carcinomas Endocr. Pathol. 2010 21 253 257 20734161
  27. [29]Li Y ZNF677 suppresses Akt phosphorylation and tumorigenesis in thyroid cancer Cancer Res 2018 78 5216 5228 29997231
  28. [30]Stein L Copy number and gene expression alterations in radiation-induced papillary thyroid carcinoma from chernobyl pediatric patients Thyroid 2010 20 475 487 19725780
  29. [31]Kimura HJ Influence of signal transducer and activator of transcription-1 signaling on thyroid morphology and function Endocrinology 2009 150 3409 3416 19325004 PMC2703527
  30. [32]Gomez-Rueda H Palacios-Corona R Gutierrez-Hermosillo H Trevino V A robust biomarker of differential correlations improves the diagnosis of cytologically indeterminate thyroid cancers Int. J. Mol. Med 2016 37 1355 1362 27035928
  31. [33]Ihara M Ashizawa K Shichijo K Kudo T Expression of the DNA-dependent protein kinase catalytic subunit is associated with the radiosensitivity of human thyroid cancer cell lines J. Radiat. Res. 2019 60 171 177 30476230 PMC6430255
  32. [34]Zhan S Li J Wang T Ge W Quantitative proteomics analysis of sporadic medullary thyroid cancer reveals FN1 as a potential novel candidate prognostic biomarker Oncologist 2018 23 1415 1425 29739896 PMC6292558
  33. [35]Figliozzi RW Chen F Hsia SV New insights on thyroid hormone mediated regulation of herpesvirus infections Cell Biosci. 2017 7 13 28344765 PMC5360088
  34. [36]Khoo TK Coenen MJ Schiefer AR Kumar S Bahn RS Evidence for enhanced Thy-1 (CD90) expression in orbital fibroblasts of patients with Graves’ ophthalmopathy Thyroid 2008 18 1291 1296 18976167 PMC2857447
  35. [37]Fagin, J. A. & Wells, S. A. Jr. Biologic and clinical perspectives on thyroid cancer. N. Engl. J. Med.375, 1054–1067 (2016). PMC5512163 27626519
  36. [38]Dom G Thyroid follicular adenomas and carcinomas: molecular profiling provides evidence for a continuous evolution Oncotarget 2018 9 10343 10359 29535811 PMC5828225
  37. [39]Ganly I Integrated genomic analysis of hurthle cell cancer reveals oncogenic drivers, recurrent mitochondrial mutations, and unique chromosomal landscapes Cancer Cell 2018 34 256 270.e5 30107176 PMC6247912
  38. [40]Gopal RK Widespread chromosomal losses and mitochondrial DNA alterations as genetic drivers in hurthle cell carcinoma Cancer Cell 2018 34 242 255.e5 30107175 PMC6121811
  39. [41]Grani G Lamartina L Durante C Filetti S Cooper DS Follicular thyroid cancer and Hürthle cell carcinoma: challenges in diagnosis, treatment, and clinical management Lancet Diabetes Endocrinol. 2018 6 500 514 29102432
  40. [42]Agrawal N Integrated genomic characterization of papillary thyroid carcinoma Cell 2014 159 676 690 25417114 PMC4243044
  41. [43]Vogel C Marcotte EM Insights into the regulation of protein abundance from proteomic and transcriptomic analyses Nat. Rev. Genet 2012 13 227 232 22411467 PMC3654667
  42. [44]Liu Y Beyer A Aebersold R On the dependency of cellular protein levels on mRNA abundance Cell 2016 165 535 550 27104977
  43. [45]Martínez-Aguilar J Clifton-Bligh R Molloy MP Proteomics of thyroid tumours provides new insights into their molecular composition and changes associated with malignancy Sci. Rep. 2016 6 23660 27025787 PMC4812243
  44. [46]Ucal Y Proteomic analysis reveals differential protein expression in variants of papillary thyroid carcinoma EuPA Open Proteom. 2017 17 1 6 29900122 PMC5988514
  45. [47]Lai X Chen S Identification of novel biomarker and therapeutic target candidates for diagnosis and treatment of follicular adenoma Cancer Genomics Proteom. 2015 12 271 281 26543076
  46. [48]Zhang F Phenotype classification using proteome data in a data-independent acquisition tensor format J. Am. Soc. Mass Spectrom. 2020 31 2296 2304 33104352
  47. [49]Rost HL OpenSWATH enables automated, targeted analysis of data-independent acquisition MS data Nat. Biotechnol. 2014 32 219 223 24727770
  48. [50]Kohavi R A Study of cross-validation and bootstrap for accuracy estimation and model selection Int. Jt. Conf. Artif. Intell. 1995 2 1137 1143
  49. [51]Li, S. Z., Zang, Z. & Wu, L. Deep manifold transformation for dimension reduction. arXiv10.48550/arXiv.2010.14831 (2020).
  50. [53]Steward DL Performance of a multigene genomic classifier in thyroid nodules with indeterminate cytology: a prospective blinded multicenter study JAMA Oncol. 2019 5 204 212 30419129 PMC6439562

Cited by

Sorted by citations

Authors
Sun, Y., Selvarajan, S., Zang, Z., Liu, W., Zhu, Y., Zhang, H., Chen, W., Chen, H., Li, L., Cai, X., Gao, H., Wu, Z., Zhao, Y., Chen, L., Teng, X., Mantoo, S., Lim, T. K.-H., Hariraman, B., Yeow, S., Alkaff, S. M. F., Lee, S. S., Ruan, G., Zhang, Q., Zhu, T., Hu, Y., Dong, Z., Ge, W., Xiao, Q., Wang, W., Wang, G., Xiao, J., He, Y., Wang, Z., Sun, W., Qin, Y., Zhu, J., Zheng, X., Wang, L., Zheng, X., Xu, K., Shao, Y., Zheng, S., Liu, K., Aebersold, R., Guan, H., Wu, X., Luo, D., Tian, W., Li, S. Z., Kon, O. L., Iyer, N. G., & Guo, T.
Affiliations
  • Westlake University (CN)
  • Singapore General Hospital (SG)
  • First Hospital of China Medical University (CN)
  • Zhejiang Provincial People's Hospital (CN)
  • Dalian Medical University (CN)
  • Second Affiliated Hospital of Zhejiang University (CN)
  • First Affiliated Hospital Zhejiang University (CN)
  • National Cancer Centre Singapore (SG)
  • Sir Run Run Shaw Hospital (CN)
  • University of Zurich (CH)
  • Guangdong Academy of Medical Sciences (CN)
  • Zhejiang University (CN)
  • Chinese PLA General Hospital (CN)
Corresponding author
  • Li, Stan Ziqing
  • Kon, Oi Lian
  • Iyer, Narayanan Gopalakrishna
  • Guo, Tiannan
ORCID
Venue
Cell Discovery
Publisher
Springer Science and Business Media LLC
Published
2022-09-06
Volume
8
Issue
1
Pages
85-85
ISSN
2056-5968 (ISSN-L)
DOI
10.1038/s41421-022-00442-x
PMC
PMC9448820
OpenAlex
W4294771218
Cited by
73
References
1
Citations by year
2026: 14 · 2025: 21 · 2024: 26 · 2023: 11 · 2022: 1
FWCI
11.49
Type
journal article
Language
en
Update notices
correction (2022-09-30)
Open access
Licence
Locations
  • Cell Discovery (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Repository for Publications and Research Data (ETH Zurich) (submittedVersion, cc-by)
  • ETH Zürich Research Collection
Funders
National Natural Science Foundation of China (81972492)
Topics
  • Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Thyroid Cancer Diagnosis and Treatment
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
Keywords
thyroid nodules, thyroid cancer diagnosis, protein biomarkers, artificial intelligence, neural network classifier, fine-needle aspiration, formalin-fixed paraffin-embedded tissue, proteomics, malignancy classification

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review