Share：
Share this content in WeChat
X
[Chinese][PDF]5774
• Special Focus •
3D-ultrashort echo time MRI-based radiomics model facilitates the assessment of lymph node metastasis in non-small cell lung cancer
WANG Ying  CUI Yingying  WANG Xinhui  MENG Nan  FENG Pengyang  YU Xuan  YUAN Jianmin  YANG Yang  WANG Zhe  WANG Meiyun 

Cite this article as: WANG Y, CUI Y Y, WANG X H, et al. 3D-ultrashort echo time MRI-based radiomics model facilitates the assessment of lymph node metastasis in non-small cell lung cancer[J]. Chin J Magn Reson Imaging, 2023, 14(3): 17-20, 41. DOI:10.12015/issn.1674-8034.2023.03.004.


[Abstract] Objectives To develop a three-dimensional ultrashort echo time (3D-UTE) based radiomic model for the assessment of lymph node metastasis in non-small cell lung cancer (NSCLC).Materials and Methods The 3D-UTE imaging data of 48 NSCLC patients from Henan Provincial People's Hospital from April 2022 to October 2022 were collected, and their radiomic features were extracted using relevant software. Least absolute shrinkage and selection operator (LASSO) regression analysis and SelectKBest were used for feature screening. The support vector machine (SVM) algorithm was used to build the prediction model and its performance was evaluated by the receiver operating characteristic (ROC) curve. Bootstrap (1000 samples) and calibration curve were used for the validation of the model.Results The 3D-UTE radiomic model established by the SVM algorithm was able to better predict lymph node metastasis in NSCLC patients with an area under the curve (AUC) of 0.89 [95% confidence interval (CI): 0.77-0.96], sensitivity of 88.00% and specificity of 86.96%. The predictive model still had high diagnostic performance in Bootstrap-based validation with an AUC of 0.87 (95% CI: 0.85-0.89); the calibration curve showed good agreement between the predicted and actual observed values of the model.Conclusions The 3D-UTE radiomics model based on the SVM algorithm can be used to assess whether lymph nodes are metastatic in NSCLC patients and is expected to provide a less radiation-burdensome option for patients with associated NSCLC.
[Keywords] non-small cell lung cancer；lymph node metastasis；3D-ultrashort echo time；radiomic；magnetic resonance imaging

WANG Ying1   CUI Yingying1   WANG Xinhui1, 2   MENG Nan1, 2   FENG Pengyang2, 3   YU Xuan1, 2   YUAN Jianmin4   YANG Yang5   WANG Zhe4   WANG Meiyun1, 2*  

1 Department of Medical Imaging, Henan Provincial People's Hospital (Zhengzhou University People's Hospital), Zhengzhou 450003, China

2 Laboratory of Brain Science and Brain-Like Intelligence Technology, Institute for Integrated Medical Science and Engineering, Henan Academy of Sciences, Zhengzhou 450046, China

3 Department of Medical Imaging, Henan Provincial People's Hospital (Henan University People's Hospital), Zhengzhou 450003, China

4 Central Research Institute, United Imaging Healthcare Group, Shanghai 201807, China

5 Beijing United Imaging Research Institute of Intelligent Imaging, United Imaging Healthcare Group, Beijing 100094, China

Corresponding author: Wang MY, E-mail: mywang@zzu.edu.cn

Conflicts of interest   None.

ACKNOWLEDGMENTS Medical Science and Technological Project of Henan Province (No. SBGJ202101002); Zhengzhou Collaborative Innovation Major Project (No. 20XTZX05015).
Received  2022-12-16
Accepted  2023-03-06
DOI: 10.12015/issn.1674-8034.2023.03.004
Cite this article as: WANG Y, CUI Y Y, WANG X H, et al. 3D-ultrashort echo time MRI-based radiomics model facilitates the assessment of lymph node metastasis in non-small cell lung cancer[J]. Chin J Magn Reson Imaging, 2023, 14(3): 17-20, 41. DOI:10.12015/issn.1674-8034.2023.03.004.

[1]
SIEGEL R L, MILLER K D, JEMAL A. Cancer statistics, 2015[J]. CA A Cancer J Clin, 2015, 65(1): 5-29. DOI: 10.3322/caac.21254.
[2]
WU F Y, WANG L, ZHOU C C. Lung cancer in China: current and prospect[J]. Curr Opin Oncol, 2021, 33(1): 40-46. DOI: 10.1097/CCO.0000000000000703.
[3]
ETTINGER D S, WOOD D E, AISNER D L, et al. NCCN guidelines insights: non-small cell lung cancer, version 2.2021[J]. J Natl Compr Canc Netw, 2021, 19(3): 254-266. DOI: 10.6004/jnccn.2021.0013.
[4]
HOY H, LYNCH T, BECK M. Surgical treatment of lung cancer[J]. Crit Care Nurs Clin North Am, 2019, 31(3): 303-313. DOI: 10.1016/j.cnc.2019.05.002.
[5]
BINCZYK F, PRAZUCH W, BOZEK P, et al. Radiomics and artificial intelligence in lung cancer screening[J]. Transl Lung Cancer Res, 2021, 10(2): 1186-1199. DOI: 10.21037/tlcr-20-708.
[6]
MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[7]
GEIGER J, ZEIMPEKIS K G, JUNG A, et al. Clinical application of ultrashort echo-time MRI for lung pathologies in children[J/OL]. Clin Radiol, 2021, 76(9): 708.e9-708.e17 [2022-12-15]. https://pubmed.ncbi.nlm.nih.gov/34120734/. DOI: 10.1016/j.crad.2021.05.015.
[8]
HEIDENREICH J F, WENG A M, METZ C, et al. Three-dimensional ultrashort echo time MRI for functional lung imaging in cystic fibrosis[J]. Radiology, 2020, 296(1): 191-199. DOI: 10.1148/radiol.2020192251.
[9]
SCHIEBLER M L, PARRAGA G, GEFTER W B, et al. Synopsis from expanding applications of pulmonary MRI in the clinical evaluation of lung disorders: fleischner society position paper[J]. Chest, 2021, 159(2): 492-495. DOI: 10.1016/j.chest.2020.09.075.
[10]
OHNO Y, KOYAMA H, YOSHIKAWA T, et al. Pulmonary high-resolution ultrashort TE MR imaging: comparison with thin-section standard- and low-dose computed tomography for the assessment of pulmonary parenchyma diseases[J]. J Magn Reson Imaging, 2016, 43(2): 512-532. DOI: 10.1002/jmri.25008.
[11]
SURUCU M, ISLER Y, PERC M, et al. Convolutional neural networks predict the onset of paroxysmal atrial fibrillation: theory and applications[J/OL]. Chaos, 2021, 31(11): 113119 [2022-12-15]. https://aip.scitation.org/doi/10.1063/5.0069272. DOI: 10.1063/5.0069272.
[12]
YANG Y Z, WANG L, YANG Y F, et al. Z-score regression model for coronary artery diameter in healthy Chinese Han children[J]. Acta Radiol, 2023, 64(2): 798-805. DOI: 10.1177/02841851221085685.
[13]
MA X, MO C H, HUANG L Z, et al. An robust rank aggregation and least absolute shrinkage and selection operator analysis of novel gene signatures in dilated cardiomyopathy[J/OL]. Front Cardiovasc Med, 2021, 8: 747803 [2022-12-15]. https://pubmed.ncbi.nlm.nih.gov/34970603/. DOI: 10.3389/fcvm.2021.747803.
[14]
NARALA S, LI S Q, KLIMAS N K, et al. Application of least absolute shrinkage and selection operator logistic regression for the histopathological comparison of chondrodermatitis nodularis helicis and hyperplastic actinic keratosis[J]. J Cutan Pathol, 2021, 48(6): 739-744. DOI: 10.1111/cup.13931.
[15]
XU X H, ZHANG J S, YANG K, et al. Prognostic prediction of hypertensive intracerebral hemorrhage using CT radiomics and machine learning[J/OL]. Brain Behav, 2021, 11(5): e02085 [2022-12-15]. https://onlinelibrary.wiley.com/doi/10.1002/brb3.2085. DOI: 10.1002/brb3.2085.
[16]
SENAN E M, ABUNADI I, JADHAV M E, et al. Score and correlation coefficient-based feature selection for predicting heart failure diagnosis by using machine learning algorithms[J/OL]. Comput Math Methods Med, 2021, 2021: 8500314 [2022-12-15]. https://pubmed.ncbi.nlm.nih.gov/34966445/. DOI: 10.1155/2021/8500314.
[17]
KUMAR B, GUPTA D. Universum based Lagrangian twin bounded support vector machine to classify EEG signals[J/OL]. Comput Methods Programs Biomed, 2021, 208: 106244 [2022-11-18]. https://doi.org/10.1016/j.cmpb.2021.106244. DOI: 10.1016/j.cmpb.2021.106244.
[18]
WANG H J, SHAO Y H, ZHOU S L, et al. Support vector machine classifier via L0/1 soft-margin loss[J]. IEEE Trans Pattern Anal Mach Intell, 2022, 44(10): 7253-7265. DOI: 10.1109/TPAMI.2021.3092177.
[19]
HENDERSON A R. The bootstrap: a technique for data-driven statistics. Using computer-intensive analyses to explore experimental data[J]. Clin Chim Acta, 2005, 359(1/2): 1-26. DOI: 10.1016/j.cccn.2005.04.002.
[20]
VICKERS A J, HOLLAND F. Decision curve analysis to evaluate the clinical benefit of prediction models[J]. Spine J, 2021, 21(10): 1643-1648. DOI: 10.1016/j.spinee.2021.02.024.
[21]
YANG Z W, GUO T, XIE H B, et al. Application of radiomics in the grading of brain tumor[J]. Chin J Magn Reson Imaging, 2018, 9(6): 439-445. DOI: 10.12015/issn.1674-8034.2018.06.008.
[22]
WEI M X, BO G J, GUO L L. The research progress of radiomics in ovarian tumors[J]. Chin J Magn Reson Imaging, 2020, 11(5): 386-389. DOI: 10.12015/issn.1674-8034.2020.05.016.
[23]
CONG M D, YAO H Y, LIU H, et al. Development and evaluation of a venous computed tomography radiomics model to predict lymph node metastasis from non-small cell lung cancer[J/OL]. Medicine, 2020, 99(18): e20074 [2022-12-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7440109. DOI: 10.1097/MD.0000000000020074.
[24]
YANG X G, PAN X H, LIU H, et al. A new approach to predict lymph node metastasis in solid lung adenocarcinoma: a radiomics nomogram[J]. J Thorac Dis, 2018, 10(Suppl 7): S807-S819. DOI: 10.21037/jtd.2018.03.126.
[25]
GRODZKI D M, JAKOB P M, HEISMANN B. Ultrashort echo time imaging using pointwise encoding time reduction with radial acquisition (PETRA)[J]. Magn Reson Med, 2012, 67(2): 510-518. DOI: 10.1002/mrm.23017.
[26]
GIBIINO F, SACOLICK L, MENINI A, et al. Free-breathing, zero-TE MR lung imaging[J]. Magn Reson Mater Phy, 2015, 28(3): 207-215. DOI: 10.1007/s10334-014-0459-y.
[27]
DEO R C. Machine learning in medicine[J]. Circulation, 2015, 132(20): 1920-1930. DOI: 10.1161/circulationaha.115.001593.
[28]
HANDELMAN G S, KOK H K, CHANDRA R V, et al. eDoctor: machine learning and the future of medicine[J]. J Intern Med, 2018, 284(6): 603-619. DOI: 10.1111/joim.12822.
[29]
GOECKS J, JALILI V, HEISER L M, et al. How machine learning will transform biomedicine[J]. Cell, 2020, 181(1): 92-101. DOI: 10.1016/j.cell.2020.03.022.
[30]
JIANG F, JIANG Y, ZHI H, et al. Artificial intelligence in healthcare: past, present and future[J]. Stroke Vasc Neurol, 2017, 2(4): 230-243. DOI: 10.1136/svn-2017-000101.
[31]
MIAO S L, LIN T T, XIAO Q Q, et al. Support vector machine based on clinical risk factors and CT radiomics for diagnosing of axial[J]. J Wenzhou Med Univ, 2022, 52(3): 199-204. DOI: 10.3969/j.issn.2095-9400.2022.03.005.
[32]
LI D, HUO L, WAN M Y, et al. Application of radiomics based on new support vector machine in the classification of hepatic nodules[J]. Chin J Magn Reson, 2022, 39(3): 278-290. DOI: 10.11938/cjmr20212916.
[33]
ZHOU Y, MA X L, ZHANG T, et al. Use of radiomics based on 18F-FDG PET/CT and machine learning methods to aid clinical decision-making in the classification of solitary pulmonary lesions: an innovative approach[J]. Eur J Nucl Med Mol Imaging, 2021, 48(9): 2904-2913. DOI: 10.1007/s00259-021-05220-7.
[34]
MASUDA T, NAKAURA T, FUNAMA Y, et al. Machine learning to identify lymph node metastasis from thyroid cancer in patients undergoing contrast-enhanced CT studies[J]. Radiography (Lond), 2021, 27(3): 920-926. DOI: 10.1016/j.radi.2021.03.001.
[35]
SEIFERT R, WEBER M, KOCAKAVUK E, et al. Artificial intelligence and machine learning in nuclear medicine: future perspectives[J]. Semin Nucl Med, 2021, 51(2): 170-177. DOI: 10.1053/j.semnuclmed.2020.08.003.

PREV Application of 3D convolutional neural network based on fusion of multiple sequence MRI to evaluate the survival prediction of patients with glioma
NEXT Value of DCE-MRI based radiomics features for prediction of axillary lymph node metastasis in breast carcinoma
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn