Skip to main content
Top

29-01-2025 | Metastasis | Ultrasound

A radiopathomics model for predicting large-number cervical lymph node metastasis in clinical N0 papillary thyroid carcinoma

Authors: Weihan Xiao, Wang Zhou, Hongmei Yuan, Xiaoling Liu, Fanding He, Xiaomin Hu, Xianjun Ye, Xiachuan Qin

Published in: European Radiology

Login to get access

Abstract

Objectives

This study aimed to develop a multimodal radiopathomics model utilising preoperative ultrasound (US) and fine-needle aspiration cytology (FNAC) to predict large-number cervical lymph node metastasis (CLNM) in patients with clinically lymph node-negative (cN0) papillary thyroid carcinoma (PTC).

Materials and methods

This multicentre retrospective study included patients with PTC between October 2017 and June 2024 across seven institutions. Patients were categorised based on the presence or absence of large-number CLNM in training, validation, and external testing cohorts. A clinical model was developed based on the maximum diameter of thyroid nodules. Radiomics features were extracted from US images and pathomics features were extracted from FNAC images. Feature selection was performed using univariate analysis, correlation analysis, and least absolute shrinkage and selection operator regression. Six machine learning (ML) algorithms were employed to construct radiomics, pathomics, and radiopathomics models. Predictive performance was assessed using the area under the curve (AUC), and decision curve analysis (DCA).

Results

A total of 426 patients with PTC (41.65 ± 12.47 years; 124 men) were included in this study, with 213 (50%) exhibiting large-number CLNM. The multimodal radiopathomics model demonstrated excellent predictive capabilities with AUCs 0.921, 0.873, 0.903; accuracies (ACCs) 0.852, 0.800, 0.833; sensitivities (SENs) 0.876, 0.867, 0.857; specificities (SPEs) 0.829, 0.733, 0.810, for the training, validation, and testing cohorts, respectively. It significantly outperformed the clinical model (AUCs 0.730, 0.698, 0.630; ACCs 0.690, 0.656, 0.627; SENs 0.686, 0.378, 0.556; SPEs 0.695, 0.933, 0.698), the radiomics model (AUCs 0.819, 0.762, 0.783; ACCs 0.752, 0.722, 0.738; SENs 0.657, 0.844, 0.937; SPEs 0.848, 0.600, 0.540), and the pathomics model (AUCs 0.882, 0.786, 0.800; ACCs 0.829, 0.756, 0.786; SENs 0.819, 0.889, 0.857; SPEs 0.838, 0.633, 0.714).

Conclusion

The multimodal radiopathomics model demonstrated significant advantages in the preoperative prediction of large-number CLNM in patients with cN0 PTC.

Key Points

Question Accurate preoperative prediction of large-number CLNM in PTC patients can guide treatment plans, but single-modality diagnostic performance remains limited.
Findings The radiopathomics model utilising preoperative US and FNAC images effectively predicted large-number CLNM in both validation and testing cohorts, outperforming single predictive models.
Clinical relevance Our study proposes a multimodal radiopathomics model based on preoperative US and FNAC images, which can effectively predict large-number CLNM in PTC preoperatively and guide clinicians in treatment planning.
Appendix
Available only for authorised users
Literature
1.
go back to reference Miranda-Filho A, Lortet-Tieulent J, Bray F et al (2021) Thyroid cancer incidence trends by histology in 25 countries: a population-based study. Lancet Diabetes Endocrinol 9:225–234CrossRefPubMed Miranda-Filho A, Lortet-Tieulent J, Bray F et al (2021) Thyroid cancer incidence trends by histology in 25 countries: a population-based study. Lancet Diabetes Endocrinol 9:225–234CrossRefPubMed
2.
go back to reference Chen AY, Jemal A, Ward EM (2009) Increasing incidence of differentiated thyroid cancer in the United States, 1988–2005. Cancer 115:3801–3807CrossRefPubMed Chen AY, Jemal A, Ward EM (2009) Increasing incidence of differentiated thyroid cancer in the United States, 1988–2005. Cancer 115:3801–3807CrossRefPubMed
4.
go back to reference Haugen BR, Alexander EK, Bible KC et al (2016) 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: the American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer. Thyroid 26:1–133CrossRefPubMedPubMedCentral Haugen BR, Alexander EK, Bible KC et al (2016) 2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: the American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer. Thyroid 26:1–133CrossRefPubMedPubMedCentral
5.
go back to reference Yan B, Hou Y, Chen D, He J, Jiang Y (2018) Risk factors for contralateral central lymph node metastasis in unilateral cN0 papillary thyroid carcinoma: a meta-analysis. Int J Surg 59:90–98CrossRefPubMed Yan B, Hou Y, Chen D, He J, Jiang Y (2018) Risk factors for contralateral central lymph node metastasis in unilateral cN0 papillary thyroid carcinoma: a meta-analysis. Int J Surg 59:90–98CrossRefPubMed
6.
go back to reference Chen BD, Zhang Z, Wang KK et al (2019) A multivariable model of BRAF(V600E) and ultrasonographic features for predicting the risk of central lymph node metastasis in cN0 papillary thyroid microcarcinoma. Cancer Manag Res 11:7211–7217CrossRefPubMedPubMedCentral Chen BD, Zhang Z, Wang KK et al (2019) A multivariable model of BRAF(V600E) and ultrasonographic features for predicting the risk of central lymph node metastasis in cN0 papillary thyroid microcarcinoma. Cancer Manag Res 11:7211–7217CrossRefPubMedPubMedCentral
7.
go back to reference Liu LS, Liang J, Li JH et al (2017) The incidence and risk factors for central lymph node metastasis in cN0 papillary thyroid microcarcinoma: a meta-analysis. Eur Arch Otorhinolaryngol 274:1327–1338CrossRefPubMed Liu LS, Liang J, Li JH et al (2017) The incidence and risk factors for central lymph node metastasis in cN0 papillary thyroid microcarcinoma: a meta-analysis. Eur Arch Otorhinolaryngol 274:1327–1338CrossRefPubMed
8.
go back to reference Wang TS, Dubner S, Sznyter LA, Heller KS (2004) Incidence of metastatic well-differentiated thyroid cancer in cervical lymph nodes. Arch Otolaryngol Head Neck Surg 130:110–113CrossRefPubMed Wang TS, Dubner S, Sznyter LA, Heller KS (2004) Incidence of metastatic well-differentiated thyroid cancer in cervical lymph nodes. Arch Otolaryngol Head Neck Surg 130:110–113CrossRefPubMed
9.
go back to reference Adam MA, Pura J, Goffredo P et al (2015) Presence and number of lymph node metastases are associated with compromised survival for patients younger than age 45 years with papillary thyroid cancer. J Clin Oncol 33:2370–2375CrossRefPubMed Adam MA, Pura J, Goffredo P et al (2015) Presence and number of lymph node metastases are associated with compromised survival for patients younger than age 45 years with papillary thyroid cancer. J Clin Oncol 33:2370–2375CrossRefPubMed
10.
go back to reference Zaydfudim V, Feurer ID, Griffin MR, Phay JE (2008) The impact of lymph node involvement on survival in patients with papillary and follicular thyroid carcinoma. Surgery 144:1070–1077CrossRefPubMed Zaydfudim V, Feurer ID, Griffin MR, Phay JE (2008) The impact of lymph node involvement on survival in patients with papillary and follicular thyroid carcinoma. Surgery 144:1070–1077CrossRefPubMed
11.
go back to reference Ito Y, Fukushima M, Tomoda C et al (2009) Prognosis of patients with papillary thyroid carcinoma having clinically apparent metastasis to the lateral compartment. Endocr J 56:759–766CrossRefPubMed Ito Y, Fukushima M, Tomoda C et al (2009) Prognosis of patients with papillary thyroid carcinoma having clinically apparent metastasis to the lateral compartment. Endocr J 56:759–766CrossRefPubMed
13.
go back to reference Randolph GW, Duh QY, Heller KS et al (2012) The prognostic significance of nodal metastases from papillary thyroid carcinoma can be stratified based on the size and number of metastatic lymph nodes, as well as the presence of extranodal extension. Thyroid 22:1144–1152CrossRefPubMed Randolph GW, Duh QY, Heller KS et al (2012) The prognostic significance of nodal metastases from papillary thyroid carcinoma can be stratified based on the size and number of metastatic lymph nodes, as well as the presence of extranodal extension. Thyroid 22:1144–1152CrossRefPubMed
14.
go back to reference Londero SC, Krogdahl A, Bastholt L et al (2015) Papillary thyroid carcinoma in Denmark, 1996-2008: outcome and evaluation of established prognostic scoring systems in a prospective national cohort. Thyroid 25:78–84CrossRefPubMed Londero SC, Krogdahl A, Bastholt L et al (2015) Papillary thyroid carcinoma in Denmark, 1996-2008: outcome and evaluation of established prognostic scoring systems in a prospective national cohort. Thyroid 25:78–84CrossRefPubMed
15.
go back to reference Hay ID, Grant CS, van Heerden JA, Goellner JR, Ebersold JR, Bergstralh EJ (1992) Papillary thyroid microcarcinoma: a study of 535 cases observed in a 50-year period. Surgery 112:1139–1146PubMed Hay ID, Grant CS, van Heerden JA, Goellner JR, Ebersold JR, Bergstralh EJ (1992) Papillary thyroid microcarcinoma: a study of 535 cases observed in a 50-year period. Surgery 112:1139–1146PubMed
16.
go back to reference Raffaelli M, De Crea C, Sessa L et al (2021) Modulating the extension of thyroidectomy in patients with papillary thyroid carcinoma pre-operatively eligible for lobectomy: reliability of ipsilateral central neck dissection. Endocrine 72:437–444CrossRefPubMed Raffaelli M, De Crea C, Sessa L et al (2021) Modulating the extension of thyroidectomy in patients with papillary thyroid carcinoma pre-operatively eligible for lobectomy: reliability of ipsilateral central neck dissection. Endocrine 72:437–444CrossRefPubMed
17.
go back to reference Raffaelli M, Sessa L, De Crea C et al (2021) Is it possible to intraoperatively modulate the extent of thyroidectomy in small papillary thyroid carcinoma? Surgery 169:77–81CrossRefPubMed Raffaelli M, Sessa L, De Crea C et al (2021) Is it possible to intraoperatively modulate the extent of thyroidectomy in small papillary thyroid carcinoma? Surgery 169:77–81CrossRefPubMed
18.
go back to reference Albuck AL, Issa PP, Hussein M et al (2023) A combination of computed tomography scan and ultrasound provides optimal detection of cervical lymph node metastasis in papillary thyroid carcinomas: a systematic review and meta-analysis. Head Neck 45:2173–2184CrossRefPubMed Albuck AL, Issa PP, Hussein M et al (2023) A combination of computed tomography scan and ultrasound provides optimal detection of cervical lymph node metastasis in papillary thyroid carcinomas: a systematic review and meta-analysis. Head Neck 45:2173–2184CrossRefPubMed
19.
go back to reference Xiao W, Hu X, Zhang C, Qin X (2023) Ultrasonic feature prediction of large-number central lymph node metastasis in clinically node-negative solitary papillary thyroid carcinoma. Endocr Res 48:112–119CrossRefPubMed Xiao W, Hu X, Zhang C, Qin X (2023) Ultrasonic feature prediction of large-number central lymph node metastasis in clinically node-negative solitary papillary thyroid carcinoma. Endocr Res 48:112–119CrossRefPubMed
20.
go back to reference Xing Z, Qiu Y, Yang Q et al (2020) Thyroid cancer neck lymph nodes metastasis: meta-analysis of US and CT diagnosis. Eur J Radiol 129:109103CrossRefPubMed Xing Z, Qiu Y, Yang Q et al (2020) Thyroid cancer neck lymph nodes metastasis: meta-analysis of US and CT diagnosis. Eur J Radiol 129:109103CrossRefPubMed
21.
go back to reference Zhu Y, Ren W, Song Y et al (2021) Cytomorphologic features as predictors of aggressiveness in patients with pT1 papillary thyroid carcinoma: a retrospective study of associations with clinicopathological parameters in 226 fine-needle aspirates. Gland Surg 10:319–327CrossRefPubMedPubMedCentral Zhu Y, Ren W, Song Y et al (2021) Cytomorphologic features as predictors of aggressiveness in patients with pT1 papillary thyroid carcinoma: a retrospective study of associations with clinicopathological parameters in 226 fine-needle aspirates. Gland Surg 10:319–327CrossRefPubMedPubMedCentral
22.
go back to reference Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A (2019) Artificial intelligence in digital pathology—new tools for diagnosis and precision oncology. Nat Rev Clin Oncol 16:703–715CrossRefPubMedPubMedCentral Bera K, Schalper KA, Rimm DL, Velcheti V, Madabhushi A (2019) Artificial intelligence in digital pathology—new tools for diagnosis and precision oncology. Nat Rev Clin Oncol 16:703–715CrossRefPubMedPubMedCentral
23.
go back to reference Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalised medicine. Nat Rev Clin Oncol 14:749–762CrossRefPubMed Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalised medicine. Nat Rev Clin Oncol 14:749–762CrossRefPubMed
24.
go back to reference Gupta R, Srivastava D, Sahu M, Tiwari S, Ambasta RK, Kumar P (2021) Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Mol Divers 25:1315–1360CrossRefPubMedPubMedCentral Gupta R, Srivastava D, Sahu M, Tiwari S, Ambasta RK, Kumar P (2021) Artificial intelligence to deep learning: machine intelligence approach for drug discovery. Mol Divers 25:1315–1360CrossRefPubMedPubMedCentral
25.
go back to reference Cibas ES, Ali SZ (2017) The 2017 Bethesda system for reporting thyroid cytopathology. Thyroid 27:1341–1346CrossRefPubMed Cibas ES, Ali SZ (2017) The 2017 Bethesda system for reporting thyroid cytopathology. Thyroid 27:1341–1346CrossRefPubMed
26.
go back to reference Tessler FN, Middleton WD, Grant EG et al (2017) ACR thyroid imaging, reporting and data system (TI-RADS): white paper of the ACR TI-RADS Committee. J Am Coll Radiol 14:587–595CrossRefPubMed Tessler FN, Middleton WD, Grant EG et al (2017) ACR thyroid imaging, reporting and data system (TI-RADS): white paper of the ACR TI-RADS Committee. J Am Coll Radiol 14:587–595CrossRefPubMed
27.
go back to reference Cruz Rivera S, Liu X, Chan AW et al (2020) Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nat Med 26:1351–1363CrossRefPubMedPubMedCentral Cruz Rivera S, Liu X, Chan AW et al (2020) Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nat Med 26:1351–1363CrossRefPubMedPubMedCentral
28.
go back to reference Shen G, Ma H, Huang R, Kuang A (2020) Predicting large-volume lymph node metastasis in the clinically node-negative papillary thyroid microcarcinoma: a retrospective study. Nucl Med Commun 41:5–10CrossRefPubMed Shen G, Ma H, Huang R, Kuang A (2020) Predicting large-volume lymph node metastasis in the clinically node-negative papillary thyroid microcarcinoma: a retrospective study. Nucl Med Commun 41:5–10CrossRefPubMed
29.
go back to reference Sugitani I, Kasai N, Fujimoto Y, Yanagisawa A (2004) A novel classification system for patients with PTC: addition of the new variables of large (3 cm or greater) nodal metastases and reclassification during the follow-up period. Surgery 135:139–148CrossRefPubMed Sugitani I, Kasai N, Fujimoto Y, Yanagisawa A (2004) A novel classification system for patients with PTC: addition of the new variables of large (3 cm or greater) nodal metastases and reclassification during the follow-up period. Surgery 135:139–148CrossRefPubMed
30.
go back to reference Leboulleux S, Rubino C, Baudin E et al (2005) Prognostic factors for persistent or recurrent disease of papillary thyroid carcinoma with neck lymph node metastases and/or tumor extension beyond the thyroid capsule at initial diagnosis. J Clin Endocrinol Metab 90:5723–5729CrossRefPubMed Leboulleux S, Rubino C, Baudin E et al (2005) Prognostic factors for persistent or recurrent disease of papillary thyroid carcinoma with neck lymph node metastases and/or tumor extension beyond the thyroid capsule at initial diagnosis. J Clin Endocrinol Metab 90:5723–5729CrossRefPubMed
31.
go back to reference Lechien JR, Maniaci A, Gengler I, Hans S, Chiesa-Estomba CM, Vaira LA (2024) Validity and reliability of an instrument evaluating the performance of intelligent chatbot: the artificial intelligence performance instrument (AIPI). Eur Arch Otorhinolaryngol 281:2063–2079CrossRefPubMed Lechien JR, Maniaci A, Gengler I, Hans S, Chiesa-Estomba CM, Vaira LA (2024) Validity and reliability of an instrument evaluating the performance of intelligent chatbot: the artificial intelligence performance instrument (AIPI). Eur Arch Otorhinolaryngol 281:2063–2079CrossRefPubMed
32.
go back to reference Zhang M, Zhang Y, Wei H et al (2023) Ultrasound radiomics nomogram for predicting large-number cervical lymph node metastasis in papillary thyroid carcinoma. Front Oncol 13:1159114CrossRefPubMedPubMedCentral Zhang M, Zhang Y, Wei H et al (2023) Ultrasound radiomics nomogram for predicting large-number cervical lymph node metastasis in papillary thyroid carcinoma. Front Oncol 13:1159114CrossRefPubMedPubMedCentral
33.
go back to reference Zhu W, Huang X, Qi Q et al (2022) Artificial neural network-based ultrasound radiomics can predict large-volume lymph node metastasis in clinical N0 papillary thyroid carcinoma patients. J Oncol 2022:7133972CrossRefPubMedPubMedCentral Zhu W, Huang X, Qi Q et al (2022) Artificial neural network-based ultrasound radiomics can predict large-volume lymph node metastasis in clinical N0 papillary thyroid carcinoma patients. J Oncol 2022:7133972CrossRefPubMedPubMedCentral
34.
35.
go back to reference Hwang HS, Orloff LA (2011) Efficacy of preoperative neck ultrasound in the detection of cervical lymph node metastasis from thyroid cancer. Laryngoscope 121:487–491CrossRefPubMed Hwang HS, Orloff LA (2011) Efficacy of preoperative neck ultrasound in the detection of cervical lymph node metastasis from thyroid cancer. Laryngoscope 121:487–491CrossRefPubMed
37.
go back to reference Li MD, Cheng MQ, Chen LD et al (2022) Reproducibility of radiomics features from ultrasound images: influence of image acquisition and processing. Eur Radiol 32:5843–5851CrossRefPubMed Li MD, Cheng MQ, Chen LD et al (2022) Reproducibility of radiomics features from ultrasound images: influence of image acquisition and processing. Eur Radiol 32:5843–5851CrossRefPubMed
Metadata
Title
A radiopathomics model for predicting large-number cervical lymph node metastasis in clinical N0 papillary thyroid carcinoma
Authors
Weihan Xiao
Wang Zhou
Hongmei Yuan
Xiaoling Liu
Fanding He
Xiaomin Hu
Xianjun Ye
Xiachuan Qin
Publication date
29-01-2025
Publisher
Springer Berlin Heidelberg
Keyword
Metastasis
Published in
European Radiology
Print ISSN: 0938-7994
Electronic ISSN: 1432-1084
DOI
https://doi.org/10.1007/s00330-025-11377-8