Share：
Share this content in WeChat
X
[Chinese][PDF]1184
• Clinical Article •
Predictive value of multimodal MRI histology for mediastinal lymph node metastasis in non-small cell lung cancer
CAO Xiayin  LI Rui  WANG Wanqiong  XUE Ying  JIANG Jianqin  CUI Lei 

Cite this article as: CAO X Y, LI R, WANG W Q, et al. Predictive value of multimodal MRI histology for mediastinal lymph node metastasis in non-small cell lung cancer[J]. Chin J Magn Reson Imaging, 2024, 15(4): 72-77. DOI:10.12015/issn.1674-8034.2024.04.012.


[Abstract] Objective To construct radiomic models utilizing conventional MRI sequences to assess and compare their effectiveness in predicting mediastinal lymph node metastasis in non-small cell lung cancer (NSCLC).Materials and Methods Preoperative MRI data from 90 patients diagnosed with NSCLC at the First People's Hospital of Nantong between October 2012 and May 2022 were retrospectively collected. Based on the surgical pathology results, these patients were categorized into two groups: lymph node metastasis-positive (52 cases) and negative (38 cases). The patients were allocated into a training set and a test set using a complete randomization method, with a ratio of 7∶3. Additionally, data from 31 patients at the First People's Hospital of Yancheng were used for external validation, consisting of 9 positive cases and 22 negative cases. Radiologists used layer-by-layer semi-automated delineation of the primary lesions, radiomics features were extracted from axial T1WI, T2WI, high b-value diffusion weighted imaging (DWI), and apparent diffusion coefficient (ADC) images, and selected the best method for dimensionality reduction among the feature screening methods, such as ANOVA F-value, Linear models penalized with the L1 norm, Tree-Based, etc., by the hyperparameter search. Eleven models were established, including logistic regression (LR), Gaussian naive Bayes (Gaussian NB), random forest (RF), and Support vector machine (SVM), decision tree (DT), etc. The receiver operating characteristic (ROC) curves were calculated for each model.Results DT, LR, and SVM models all performed well in different sequences. The SVM model based on T2WI images had the best performance, with area under the curve (AUC) of 0.98, 0.98, and 0.72 for the training, test, and external validation sets, respectively, and with accuracies of 96%, 67%, and 61%, sensitivities of 88%, 67%, and 55%, and specificities of 100%, 67%, and 78%, respectively.Conclusions MRI-based radiomics is valuable in identifying mediastinal lymph node metastasis in NSCLC, with the SVM model based on T2WI images showing the best performance.
[Keywords] non-small cell lung cancer；lymph node metastasis；prediction model；radiomic；machine learning；magnetic resonance imaging

CAO Xiayin1   LI Rui1   WANG Wanqiong1   XUE Ying2   JIANG Jianqin3   CUI Lei1*  

1 Department of Radiology, the Second Affiliated Hospital of Nantong University, Nantong 226006, China

2 Department of Radiology, Nantong Hospital of Traditional Chinese Medicine, Nantong 226007, China

3 Department of Radiology, Yancheng No.1 People's Hospital, Yancheng 224006, China

Corresponding author: CUI L, E-mail: cuigeleili@126.com

Conflicts of interest   None.

Received  2023-11-30
Accepted  2024-03-29
DOI: 10.12015/issn.1674-8034.2024.04.012
Cite this article as: CAO X Y, LI R, WANG W Q, et al. Predictive value of multimodal MRI histology for mediastinal lymph node metastasis in non-small cell lung cancer[J]. Chin J Magn Reson Imaging, 2024, 15(4): 72-77. DOI:10.12015/issn.1674-8034.2024.04.012.

[1]
SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
[2]
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.
[3]
GOLDSTRAW P, CHANSKY K, CROWLEY J, et al. The IASLC lung cancer staging project: proposals for revision of the TNM stage groupings in the forthcoming (eighth) edition of the TNM classification for lung cancer[J]. J Thorac Oncol, 2016, 11(1): 39-51. DOI: 10.1016/j.jtho.2015.09.009.
[4]
TAKANO N, ARIYASU R, KOYAMA J, et al. Improvement in the survival of patients with stage Ⅳ non-small-cell lung cancer: experience in a single institutional 1995-2017[J/OL]. Lung Cancer, 2019, 131: 69-77 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/31027701/. DOI: 10.1016/j.lungcan.2019.03.008.
[5]
LAMBIN P, LEIJENAAR R T H, DEIST T M, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
[6]
SHAKIR H, DENG Y M, RASHEED H, et al. Radiomics based likelihood functions for cancer diagnosis[J/OL]. Sci Rep, 2019, 9(1): 9501 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/31263186/. DOI: 10.1038/s41598-019-45053-x.
[7]
SHEN G H, LAN Y, ZHANG K, et al. Correction: comparison of 18F-FDG PET/CT and DWI for detection of mediastinal nodal metastasis in non-small cell lung cancer: a meta-analysis[J/OL]. PLoS One, 2017, 12(4): e0176150 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/28406970/. DOI: 10.1371/journal.pone.0176150.
[8]
CAI R F, CUI L, YIN J B, et al. Value of LSR and ADCs in differential diagnosis of hilar and mediastinal lymph nodes in lung cancer[J]. Natl Med J China, 2018, 98(37): 3009-3013. DOI: 10.3760/cma.j.issn.0376-2491.2018.37.012.
[9]
NOMORI H, CONG Y, SUGIMURA H, et al. Diffusion-weighted imaging can correctly identify false-positive lymph nodes on positron emission tomography in non-small cell lung cancer[J]. Surg Today, 2016, 46(10): 1146-1151. DOI: 10.1007/s00595-015-1285-1.
[10]
LI X, YANG L F, JIAO X. Comparison of traditional radiomics, deep learning radiomics and fusion methods for axillary lymph node metastasis prediction in breast cancer[J]. Acad Radiol, 2023, 30(7): 1281-1287. DOI: 10.1016/j.acra.2022.10.015.
[11]
YU Y F, HE Z F, OUYANG J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study[J/OL]. EBioMedicine, 2021, 69: 103460 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/34233259/. DOI: 10.1016/j.ebiom.2021.103460.
[12]
SONG J C, HU Q M, MA Z L, et al. Feasibility of T2WI-MRI-based radiomics nomogram for predicting normal-sized pelvic lymph node metastasis in cervical cancer patients[J]. Eur Radiol, 2021, 31(9): 6938-6948. DOI: 10.1007/s00330-021-07735-x.
[13]
ZHANG Z H, WAN X J, LEI X Y, et al. Intra- and peri-tumoral MRI radiomics features for preoperative lymph node metastasis prediction in early-stage cervical cancer[J/OL]. Insights Imaging, 2023, 14(1): 65 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/37060378/. DOI: 10.1186/s13244-023-01405-w.
[14]
ZHAO L, LIANG M, SHI Z, et al. Preoperative volumetric synthetic magnetic resonance imaging of the primary tumor for a more accurate prediction of lymph node metastasis in rectal cancer[J]. Quant Imaging Med Surg, 2021, 11(5): 1805-1816. DOI: 10.21037/qims-20-659.
[15]
LI J, ZHOU Y, WANG P, et al. Deep transfer learning based on magnetic resonance imaging can improve the diagnosis of lymph node metastasis in patients with rectal cancer[J]. Quant Imaging Med Surg, 2021, 11(6): 2477-2485. DOI: 10.21037/qims-20-525.
[16]
YAN H, YANG H J, JIANG P S, et al. A radiomics model based on T2WI and clinical indexes for prediction of lateral lymph node metastasis in rectal cancer[J]. Asian J Surg, 2024, 47(1): 450-458. DOI: 10.1016/j.asjsur.2023.09.156.
[17]
DARLING G E, ALLEN M S, DECKER P A, et al. Randomized trial of mediastinal lymph node sampling versus complete lymphadenectomy during pulmonary resection in the patient with N0 or N1 (less than hilar) non-small cell carcinoma: results of the American College of Surgery Oncology Group Z0030 Trial[J]. J Thorac Cardiovasc Surg, 2011, 141(3): 662-670. DOI: 10.1016/j.jtcvs.2010.11.008.
[18]
STAMATIS G. Staging of lung cancer: the role of noninvasive, minimally invasive and invasive techniques[J]. Eur Respir J, 2015, 46(2): 521-531. DOI: 10.1183/09031936.00126714.
[19]
RAMI-PORTA R, CALL S, DOOMS C, et al. Lung cancer staging: a concise update[J/OL]. Eur Respir J, 2018, 51(5): 1800190 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/29700105/. DOI: 10.1183/13993003.00190-2018.
[20]
LIMKIN E J, SUN R, DERCLE L, et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology[J]. Ann Oncol, 2017, 28(6): 1191-1206. DOI: 10.1093/annonc/mdx034.
[21]
CONG M D, FENG H, REN J L, et al. Development of a predictive radiomics model for lymph node metastases in pre-surgical CT-based stage IA non-small cell lung cancer[J/OL]. Lung Cancer, 2020, 139: 73-79 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/31743889/. DOI: 10.1016/j.lungcan.2019.11.003.
[22]
HUANG Y, JIANG X, XU H, et al. Preoperative prediction of mediastinal lymph node metastasis in non-small cell lung cancer based on 18F-FDG PET/CT radiomics[J]. Clin Radiol, 2023, 78(1): 8-17. DOI: 10.1016/j.crad.2022.08.140.
[23]
LI Q, HE X Q, FAN X, et al. Development and validation of a combined model for preoperative prediction of lymph node metastasis in peripheral lung adenocarcinoma[J/OL]. Front Oncol, 2021, 11: 675877 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/34109124/. DOI: 10.3389/fonc.2021.675877.
[24]
ZHENG K, WANG X R, JIANG C Z, et al. Pre-operative prediction of mediastinal node metastasis using radiomics model based on 18F-FDG PET/CT of the primary tumor in non-small cell lung cancer patients[J/OL]. Front Med, 2021, 8: 673876 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/34222284/. DOI: 10.3389/fmed.2021.673876.
[25]
ZHONG Y, YUAN M, ZHANG T, et al. Radiomics approach to prediction of occult mediastinal lymph node metastasis of lung adenocarcinoma[J]. AJR Am J Roentgenol, 2018, 211(1): 109-113. DOI: 10.2214/AJR.17.19074.
[26]
PUDERBACH M, EICHINGER M, HAESELBARTH J, et al. Assessment of morphological MRI for pulmonary changes in cystic fibrosis (CF) patients: comparison to thin-section CT and chest x-ray[J]. Invest Radiol, 2007, 42(10): 715-725. DOI: 10.1097/RLI.0b013e318074fd81.
[27]
HOPKINS S R, WIELPÜTZ M O, KAUCZOR H U. Imaging lung perfusion[J]. J Appl Physiol, 2012, 113(2): 328-339. DOI: 10.1152/japplphysiol.00320.2012.
[28]
HATABU H, OHNO Y, GEFTER W B, et al. Expanding applications of pulmonary MRI in the clinical evaluation of lung disorders: fleischner society position paper[J]. Radiology, 2020, 297(2): 286-301. DOI: 10.1148/radiol.2020201138.
[29]
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 Imag, 2023, 14(3): 17-20, 41. DOI: 10.12015/issn.1674-8034.2023.03.004.
[30]
YUEN S, MONZAWA S, YANAI S, et al. The association between MRI findings and breast cancer subtypes: focused on the combination patterns on diffusion-weighted and T2-weighted images[J]. Breast Cancer, 2020, 27(5): 1029-1037. DOI: 10.1007/s12282-020-01105-z.
[31]
OLLITRAULT A, CHARBONNEAU F, HERDAN M L, et al. Dixon-T2WI magnetic resonance imaging at 3tesla outperforms conventional imaging for thyroid eye disease[J]. Eur Radiol, 2021, 31(7): 5198-5205. DOI: 10.1007/s00330-020-07540-y.
[32]
CHEN X, SHAN T Y, LI Y. Prognostic effect of increased postoperative MRI T2WI high signal intensity in degenerative cervical myelopathy[J]. Spine J, 2022, 22(12): 1964-1973. DOI: 10.1016/j.spinee.2022.07.097.
[33]
CHEONG E N, PARK J E, PARK S Y, et al. Achieving imaging and computational reproducibility on multiparametric MRI radiomics features in brain tumor diagnosis: phantom and clinical validation[J]. Eur Radiol, 2024, 34(3): 2008-2023. DOI: 10.1007/s00330-023-10164-7.
[34]
GULLO R L, PARTRIDGE S C, SHIN H J, et al. Update on DWI for breast cancer diagnosis and treatment monitoring[J/OL]. AJR Am J Roentgenol, 2024, 222(1): e2329933 [2023-11-19]. https://pubmed.ncbi.nlm.nih.gov/37850579/. DOI: 10.2214/AJR.23.29933.
[35]
LIU Z Y, WANG S, DONG D, et al. The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges[J]. Theranostics, 2019, 9(5): 1303-1322. DOI: 10.7150/thno.30309.
[36]
GUIOT J, VAIDYANATHAN A, DEPREZ L, et al. A review in radiomics: making personalized medicine a reality via routine imaging[J]. Med Res Rev, 2022, 42(1): 426-440. DOI: 10.1002/med.21846.

PREV Value of CMR radiomics combined with clinical factors in predicting hypertrophic cardiomyopathy complicated by ventricular arrhythmias
NEXT Value of multimodal radiomics nomogram in predicting axillary lymph node metastasis in invasive ductal carcinoma of the breast before surgery
  


LINK


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