Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer
Abstract Background To determine the predictive capability of MRI-based radiomics for extrathyroidal extension detection in papillary thyroid cancer (PTC) pre-surgically. Methods The present retrospective trial assessed individuals with thyroid nodules examined by multiparametric MRI and subsequentl...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-02-01
|
Series: | BMC Medical Imaging |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12880-021-00553-z |
id |
doaj-9e3ea027fd1b4c66baac2c3af7039aeb |
---|---|
record_format |
Article |
spelling |
doaj-9e3ea027fd1b4c66baac2c3af7039aeb2021-02-14T12:45:43ZengBMCBMC Medical Imaging1471-23422021-02-012111810.1186/s12880-021-00553-zRadiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancerRan Wei0Hao Wang1Lanyun Wang2Wenjuan Hu3Xilin Sun4Zedong Dai5Jie Zhu6Hong Li7Yaqiong Ge8Bin Song9Department of Radiology, Minhang Hospital, Fudan UniversityDepartment of Radiology, Minhang Hospital, Fudan UniversityDepartment of Radiology, Minhang Hospital, Fudan UniversityDepartment of Radiology, Minhang Hospital, Fudan UniversityDepartment of Radiology, Minhang Hospital, Fudan UniversityDepartment of Radiology, Minhang Hospital, Fudan UniversityDepartment of Radiology, Minhang Hospital, Fudan UniversityDepartment of Radiology, Minhang Hospital, Fudan UniversityGE HealthcareDepartment of Radiology, Minhang Hospital, Fudan UniversityAbstract Background To determine the predictive capability of MRI-based radiomics for extrathyroidal extension detection in papillary thyroid cancer (PTC) pre-surgically. Methods The present retrospective trial assessed individuals with thyroid nodules examined by multiparametric MRI and subsequently administered thyroid surgery. Diagnosis and extrathyroidal extension (ETE) feature of PTC were based on pathological assessment. The thyroid tumors underwent manual segmentation, for radiomic feature extraction. Participants were randomized to the training and testing cohorts, at a ratio of 7:3. The mRMR (maximum correlation minimum redundancy) algorithm and the least absolute shrinkage and selection operator were utilized for radiomics feature selection. Then, a radiomics predictive model was generated via a linear combination of the features. The model’s performance in distinguishing the ETE feature of PTC was assessed by analyzing the receiver operating characteristic curve. Results Totally 132 patients were assessed in this study, including 92 and 40 in the training and test cohorts, respectively). Next, the 16 top-performing features, including 4, 7 and 5 from diffusion weighted (DWI), T2-weighted (T2 WI), and contrast-enhanced T1-weighted (CE-T1WI) images, respectively, were finally retained to construct the radiomics signature. There were 8 RLM, 5 CM, 2 shape, and 1 SZM features. The radiomics prediction model achieved AUCs of 0.96 and 0.87 in the training and testing sets, respectively. Conclusions Our study indicated that MRI radiomics approach had the potential to stratify patients based on ETE in PTCs preoperatively.https://doi.org/10.1186/s12880-021-00553-zRadiomicsPapillary thyroid carcinomaExtrathyroidal extensionMagnetic resonance imaging |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ran Wei Hao Wang Lanyun Wang Wenjuan Hu Xilin Sun Zedong Dai Jie Zhu Hong Li Yaqiong Ge Bin Song |
spellingShingle |
Ran Wei Hao Wang Lanyun Wang Wenjuan Hu Xilin Sun Zedong Dai Jie Zhu Hong Li Yaqiong Ge Bin Song Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer BMC Medical Imaging Radiomics Papillary thyroid carcinoma Extrathyroidal extension Magnetic resonance imaging |
author_facet |
Ran Wei Hao Wang Lanyun Wang Wenjuan Hu Xilin Sun Zedong Dai Jie Zhu Hong Li Yaqiong Ge Bin Song |
author_sort |
Ran Wei |
title |
Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer |
title_short |
Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer |
title_full |
Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer |
title_fullStr |
Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer |
title_full_unstemmed |
Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer |
title_sort |
radiomics based on multiparametric mri for extrathyroidal extension feature prediction in papillary thyroid cancer |
publisher |
BMC |
series |
BMC Medical Imaging |
issn |
1471-2342 |
publishDate |
2021-02-01 |
description |
Abstract Background To determine the predictive capability of MRI-based radiomics for extrathyroidal extension detection in papillary thyroid cancer (PTC) pre-surgically. Methods The present retrospective trial assessed individuals with thyroid nodules examined by multiparametric MRI and subsequently administered thyroid surgery. Diagnosis and extrathyroidal extension (ETE) feature of PTC were based on pathological assessment. The thyroid tumors underwent manual segmentation, for radiomic feature extraction. Participants were randomized to the training and testing cohorts, at a ratio of 7:3. The mRMR (maximum correlation minimum redundancy) algorithm and the least absolute shrinkage and selection operator were utilized for radiomics feature selection. Then, a radiomics predictive model was generated via a linear combination of the features. The model’s performance in distinguishing the ETE feature of PTC was assessed by analyzing the receiver operating characteristic curve. Results Totally 132 patients were assessed in this study, including 92 and 40 in the training and test cohorts, respectively). Next, the 16 top-performing features, including 4, 7 and 5 from diffusion weighted (DWI), T2-weighted (T2 WI), and contrast-enhanced T1-weighted (CE-T1WI) images, respectively, were finally retained to construct the radiomics signature. There were 8 RLM, 5 CM, 2 shape, and 1 SZM features. The radiomics prediction model achieved AUCs of 0.96 and 0.87 in the training and testing sets, respectively. Conclusions Our study indicated that MRI radiomics approach had the potential to stratify patients based on ETE in PTCs preoperatively. |
topic |
Radiomics Papillary thyroid carcinoma Extrathyroidal extension Magnetic resonance imaging |
url |
https://doi.org/10.1186/s12880-021-00553-z |
work_keys_str_mv |
AT ranwei radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT haowang radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT lanyunwang radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT wenjuanhu radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT xilinsun radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT zedongdai radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT jiezhu radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT hongli radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT yaqiongge radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer AT binsong radiomicsbasedonmultiparametricmriforextrathyroidalextensionfeaturepredictioninpapillarythyroidcancer |
_version_ |
1724270083704881152 |