OpenLB
Open Library of Bioscience
Advanced Search
Reviews in endocrine & metabolic disorders
02, 2024;25 (1): 175-186.

Application of radiomics and machine learning to thyroid diseases in nuclear medicine: a systematic review.

Francesco Dondi, Roberto Gatta, Giorgio Treglia, Arnoldo Piccardo, Domenico Albano, Luca Camoni, Elisa Gatta, Maria Cavadini, Carlo Cappelli, Francesco Bertagna
Author Information
  1. Francesco Dondi: Nuclear Medicine, ASST Spedali Civili di Brescia, P.le Spedali Civili, 1, Brescia, 25123, Italy.
  2. Roberto Gatta: Dipartimento di Scienze Cliniche e Sperimentali, Università degli Studi di Brescia, Brescia, Italy.
  3. Giorgio Treglia: Clinic of Nuclear Medicine, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, Bellinzona, Switzerland.
  4. Arnoldo Piccardo: Department of Nuclear Medicine, Ospedali Galliera, Genoa, Italy.
  5. Domenico Albano: Nuclear Medicine, ASST Spedali Civili di Brescia and Università degli Studi di Brescia, Brescia, Italy.
  6. Luca Camoni: Nuclear Medicine, ASST Spedali Civili di Brescia, P.le Spedali Civili, 1, Brescia, 25123, Italy.
  7. Elisa Gatta: Unit of Endocrinology and Metabolism, ASST Spedali Civili di Brescia and Università degli Studi di Brescia, Brescia, Italy.
  8. Maria Cavadini: Unit of Endocrinology and Metabolism, ASST Spedali Civili di Brescia and Università degli Studi di Brescia, Brescia, Italy.
  9. Carlo Cappelli: Unit of Endocrinology and Metabolism, ASST Spedali Civili di Brescia and Università degli Studi di Brescia, Brescia, Italy.
  10. Francesco Bertagna: Nuclear Medicine, ASST Spedali Civili di Brescia, P.le Spedali Civili, 1, Brescia, 25123, Italy. francesco.bertagna@unibs.it. ORCID
PMID: 37434097 DOI: 10.1007/s11154-023-09822-4

Abstract

BACKGROUND: In the last years growing evidences on the role of radiomics and machine learning (ML) applied to different nuclear medicine imaging modalities for the assessment of thyroid diseases are starting to emerge. The aim of this systematic review was therefore to analyze the diagnostic performances of these technologies in this setting.
METHODS: A wide literature search of the PubMed/MEDLINE, Scopus and Web of Science databases was made in order to find relevant published articles about the role of radiomics or ML on nuclear medicine imaging for the evaluation of different thyroid diseases.
RESULTS: Seventeen studies were included in the systematic review. Radiomics and ML were applied for assessment of thyroid incidentalomas at  F-FDG PET, evaluation of cytologically indeterminate thyroid nodules, assessment of thyroid cancer and classification of thyroid diseases using nuclear medicine techniques.
CONCLUSION: Despite some intrinsic limitations of radiomics and ML may have affect the results of this review, these technologies seem to have a promising role in the assessment of thyroid diseases. Validation of preliminary findings in multicentric studies is needed to translate radiomics and ML approaches in the clinical setting.

Keywords

Machine learning Positron emission tomography Radiomics Texture analysis Thyroid

References

  1. Eur J Nucl Med Mol Imaging. 2022 Jun;49(7):2174-2188 [PMID: 35138444]
  2. Radiology. 2022 Aug;304(2):397-405 [PMID: 35536131]
  3. Nucl Med Biol. 2015 Apr;42(4):349-54 [PMID: 25595135]
  4. Cancers (Basel). 2021 May 18;13(10): [PMID: 34069887]
  5. Br J Radiol. 2019 Feb;92(1094):20180620 [PMID: 30273012]
  6. Am Fam Physician. 2020 Sep 1;102(5):298-304 [PMID: 32866364]
  7. Diagnostics (Basel). 2022 May 27;12(6): [PMID: 35741138]
  8. Eur J Radiol. 2018 Feb;99:1-8 [PMID: 29362138]
  9. Semin Nucl Med. 2023 Jul;53(4):481-489 [PMID: 36702731]
  10. Ann Nucl Med. 2021 Oct;35(10):1089-1099 [PMID: 34152569]
  11. Endocrine. 2022 Jan;75(1):202-210 [PMID: 34468949]
  12. Endocrine. 2015 Dec;50(3):681-8 [PMID: 25948075]
  13. J Clin Med. 2022 Jan 26;11(3): [PMID: 35160067]
  14. Diagnostics (Basel). 2023 Feb 03;13(3): [PMID: 36766670]
  15. Nucl Med Mol Imaging. 2020 Oct;54(5):241-248 [PMID: 33088353]
  16. Eur J Nucl Med Mol Imaging. 2019 Nov;46(12):2514-2525 [PMID: 31392371]
  17. Eur J Nucl Med Mol Imaging. 2020 Oct;47(11):2639-2646 [PMID: 32248325]
  18. Transl Vis Sci Technol. 2020 Feb 27;9(2):14 [PMID: 32704420]
  19. Circulation. 2015 Nov 17;132(20):1920-30 [PMID: 26572668]
  20. Cancers (Basel). 2023 Feb 16;15(4): [PMID: 36831612]
  21. Eur J Hybrid Imaging. 2017;1(1):3 [PMID: 29782578]
  22. J Clin Med. 2021 Oct 29;10(21): [PMID: 34768584]
  23. Endocrinol Metab Clin North Am. 2000 Mar;29(1):187-203 [PMID: 10732271]
  24. Ann Intern Med. 2011 Oct 18;155(8):529-36 [PMID: 22007046]
  25. J Int Med Res. 2021 Jan;49(1):300060520982842 [PMID: 33445994]
  26. Med Phys. 2023 Jan;50(1):152-162 [PMID: 35925871]
  27. Pathol Res Pract. 2020 Sep;216(9):153098 [PMID: 32825964]
  28. Endocrine. 2021 Nov;74(2):332-339 [PMID: 34014437]
  29. Endocrine. 2019 Feb;63(2):293-300 [PMID: 30206772]
  30. Nucl Med Mol Imaging. 2018 Jun;52(3):170-189 [PMID: 29942396]
  31. Comput Intell Neurosci. 2019 Jan 15;2019:6212759 [PMID: 30766599]
  32. Eur J Nucl Med Mol Imaging. 2021 Feb;48(2):461-468 [PMID: 32794104]
  33. Eur J Nucl Med Mol Imaging. 2022 Mar;49(4):1374-1385 [PMID: 34664092]
  34. Sci Rep. 2020 May 8;10(1):7738 [PMID: 32385375]
  35. Adv Anat Pathol. 2019 Mar;26(2):114-123 [PMID: 30664001]
  36. Diagnostics (Basel). 2021 Nov 25;11(12): [PMID: 34943426]
  37. Curr Med Imaging. 2020;16(3):199-205 [PMID: 32133949]
  38. Rev Endocr Metab Disord. 2019 Mar;20(1):47-64 [PMID: 30900067]
  39. HNO. 2022 May;70(5):333-344 [PMID: 35364686]
  40. Thyroid. 2016 Jan;26(1):1-133 [PMID: 26462967]
  41. Front Oncol. 2021 Jul 07;11:639326 [PMID: 34307123]
  42. J Nucl Med Technol. 2021 Dec 7;: [PMID: 34876477]
  43. Thyroid. 2021 Jan;31(1):88-95 [PMID: 32517585]
  44. J Clin Med. 2022 Dec 29;12(1): [PMID: 36615053]
  45. Cancer. 2018 Mar 1;124(5):888-898 [PMID: 29278433]
  46. JAMA Oncol. 2021 Jan 01;7(1):70-77 [PMID: 33300952]
  47. Am Fam Physician. 2016 Mar 1;93(5):363-70 [PMID: 26926973]
  48. Diagnostics (Basel). 2022 Feb 12;12(2): [PMID: 35204561]
  49. Front Oncol. 2021 Oct 28;11:762643 [PMID: 34778083]

MeSH Term

Humans
Fluorodeoxyglucose F18
Machine Learning
Nuclear Medicine
Radiomics
Thyroid Neoplasms
Thyroid Nodule
Thyroid Diseases

Chemicals

Fluorodeoxyglucose F18
Systematic Review Journal Article Review

Word Cloud

Created with Highcharts 10.0.0thyroidradiomicsMLdiseasesnuclearassessmentreviewrolelearningmedicinesystematicmachineapplieddifferentimagingtechnologiessettingevaluationstudiesRadiomicsBACKGROUND:lastyearsgrowingevidencesmodalitiesstartingemergeaimthereforeanalyzediagnosticperformancesMETHODS:wideliteraturesearchPubMed/MEDLINEScopusWebSciencedatabasesmadeorderfindrelevantpublishedarticlesRESULTS:Seventeenincludedincidentalomas F-FDGPETcytologicallyindeterminatenodulescancerclassificationusingtechniquesCONCLUSION:DespiteintrinsiclimitationsmayaffectresultsseempromisingValidationpreliminaryfindingsmulticentricneededtranslateapproachesclinicalApplicationmedicine:MachinePositronemissiontomographyTextureanalysisThyroid

Similar Articles

Cited By