Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural Networks

ObjectiveTo assess the accuracy of pN staging prediction in papillary thyroid carcinoma (PTC) using ultrasound radiomics and deep neural networks (DNN). MethodsA retrospective analysis was conducted on 375 patients with pathologically confirmed PTC, comprising 261 cases in the training set and 114 i...

Full description

Saved in:
Bibliographic Details
Main Authors: Jieli ZHOU, Linjuan WU, Pengtian ZHANG, Yanxia Peng, Dong HAN
Format: Article
Language:zho
Published: Magazine House of Cancer Research on Prevention and Treatment 2025-02-01
Series:Zhongliu Fangzhi Yanjiu
Subjects:
Online Access:http://www.zlfzyj.com/cn/article/doi/10.3971/j.issn.1000-8578.2025.24.0617
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078196859404288
author Jieli ZHOU
Linjuan WU
Pengtian ZHANG
Yanxia Peng
Dong HAN
author_facet Jieli ZHOU
Linjuan WU
Pengtian ZHANG
Yanxia Peng
Dong HAN
author_sort Jieli ZHOU
collection DOAJ
description ObjectiveTo assess the accuracy of pN staging prediction in papillary thyroid carcinoma (PTC) using ultrasound radiomics and deep neural networks (DNN). MethodsA retrospective analysis was conducted on 375 patients with pathologically confirmed PTC, comprising 261 cases in the training set and 114 in the test set. Staging was categorized as pN0 (no cervical lymph node metastasis), pN1a (central neck lymph node metastasis), and pN1b (lateral neck lymph node metastasis). An ultrasound physician manually segmented the regions of interest (ROIs) for PTC, extracting 1899 radiomic features. Dimensionality reduction was performed using the least absolute shrinkage and selection operator (LASSO) regression. A DNN model for predicting PTC pN staging was developed using the H2O deep learning platform, trained on the training set, and validated on the test set to assess the accuracy of the optimal model. ResultsA total of 153 patients were in the pN0 stage, 131 patients in the pN1a stage, and 91 patients in the pN1b stage. LASSO regression selected 15 radiomic features for each PTC. The optimal DNN model, constructed using these 15 features, achieved accuracies of 85.82% on the training set and 81.57% on the test set. ConclusionUltrasound radiomics of PTC demonstrates high accuracy in predicting pN staging and shows potential for automating N staging in patients.
format Article
id doaj-art-ba7013e116f446dcbc66f060787a5e74
institution DOAJ
issn 1000-8578
language zho
publishDate 2025-02-01
publisher Magazine House of Cancer Research on Prevention and Treatment
record_format Article
series Zhongliu Fangzhi Yanjiu
spelling doaj-art-ba7013e116f446dcbc66f060787a5e742025-08-20T02:45:37ZzhoMagazine House of Cancer Research on Prevention and TreatmentZhongliu Fangzhi Yanjiu1000-85782025-02-0152215115510.3971/j.issn.1000-8578.2025.24.061720240617Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural NetworksJieli ZHOU0Linjuan WU1Pengtian ZHANG2Yanxia Peng3Dong HAN4Department of Ultrasound, The First Affiliated Hospital of Air Force Medical University, Xi’an 710032, ChinaDepartment of Ultrasound, Xi’an Fengcheng Hospital, Xi’an 710018, ChinaDepartment of Medical Imaging, Affiliated Hospital of Shaanxi University of Chinese Medicine, Xianyang 712000, ChinaDepartment of Ultrasound, Northwest Women’s and Children’s Hospital, Xi’an 710061, ChinaDepartment of Medical Imaging, Affiliated Hospital of Shaanxi University of Chinese Medicine, Xianyang 712000, ChinaObjectiveTo assess the accuracy of pN staging prediction in papillary thyroid carcinoma (PTC) using ultrasound radiomics and deep neural networks (DNN). MethodsA retrospective analysis was conducted on 375 patients with pathologically confirmed PTC, comprising 261 cases in the training set and 114 in the test set. Staging was categorized as pN0 (no cervical lymph node metastasis), pN1a (central neck lymph node metastasis), and pN1b (lateral neck lymph node metastasis). An ultrasound physician manually segmented the regions of interest (ROIs) for PTC, extracting 1899 radiomic features. Dimensionality reduction was performed using the least absolute shrinkage and selection operator (LASSO) regression. A DNN model for predicting PTC pN staging was developed using the H2O deep learning platform, trained on the training set, and validated on the test set to assess the accuracy of the optimal model. ResultsA total of 153 patients were in the pN0 stage, 131 patients in the pN1a stage, and 91 patients in the pN1b stage. LASSO regression selected 15 radiomic features for each PTC. The optimal DNN model, constructed using these 15 features, achieved accuracies of 85.82% on the training set and 81.57% on the test set. ConclusionUltrasound radiomics of PTC demonstrates high accuracy in predicting pN staging and shows potential for automating N staging in patients.http://www.zlfzyj.com/cn/article/doi/10.3971/j.issn.1000-8578.2025.24.0617thyroid cancerpapillaryultrasonographypn stagingpredictinglymph nodes
spellingShingle Jieli ZHOU
Linjuan WU
Pengtian ZHANG
Yanxia Peng
Dong HAN
Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural Networks
Zhongliu Fangzhi Yanjiu
thyroid cancer
papillary
ultrasonography
pn staging
predicting
lymph nodes
title Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural Networks
title_full Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural Networks
title_fullStr Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural Networks
title_full_unstemmed Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural Networks
title_short Prediction of pN Staging of Papillary Thyroid Carcinoma Using Ultrasonography Radiomics and Deep Neural Networks
title_sort prediction of pn staging of papillary thyroid carcinoma using ultrasonography radiomics and deep neural networks
topic thyroid cancer
papillary
ultrasonography
pn staging
predicting
lymph nodes
url http://www.zlfzyj.com/cn/article/doi/10.3971/j.issn.1000-8578.2025.24.0617
work_keys_str_mv AT jielizhou predictionofpnstagingofpapillarythyroidcarcinomausingultrasonographyradiomicsanddeepneuralnetworks
AT linjuanwu predictionofpnstagingofpapillarythyroidcarcinomausingultrasonographyradiomicsanddeepneuralnetworks
AT pengtianzhang predictionofpnstagingofpapillarythyroidcarcinomausingultrasonographyradiomicsanddeepneuralnetworks
AT yanxiapeng predictionofpnstagingofpapillarythyroidcarcinomausingultrasonographyradiomicsanddeepneuralnetworks
AT donghan predictionofpnstagingofpapillarythyroidcarcinomausingultrasonographyradiomicsanddeepneuralnetworks