A Magnetic Resonance Imaging Radiomics Signature to Distinguish Benign From Malignant Orbital Lesions.
Journal
Investigative radiology
ISSN: 1536-0210
Titre abrégé: Invest Radiol
Pays: United States
ID NLM: 0045377
Informations de publication
Date de publication:
01 03 2021
01 03 2021
Historique:
pubmed:
16
9
2020
medline:
16
10
2021
entrez:
15
9
2020
Statut:
ppublish
Résumé
Distinguishing benign from malignant orbital lesions remains challenging both clinically and with imaging, leading to risky biopsies. The objective was to differentiate benign from malignant orbital lesions using radiomics on 3 T magnetic resonance imaging (MRI) examinations. This institutional review board-approved prospective single-center study enrolled consecutive patients presenting with an orbital lesion undergoing a 3 T MRI prior to surgery from December 2015 to July 2019. Radiomics features were extracted from 6 MRI sequences (T1-weighted images [WIs], DIXON-T2-WI, diffusion-WI, postcontrast DIXON-T1-WI) using the Pyradiomics software. Features were selected based on their intraobserver and interobserver reproducibility, nonredundancy, and with a sequential step forward feature selection method. Selected features were used to train and optimize a Random Forest algorithm on the training set (75%) with 5-fold cross-validation. Performance metrics were computed on a held-out test set (25%) with bootstrap 95% confidence intervals (95% CIs). Five residents, 4 general radiologists, and 3 expert neuroradiologists were evaluated on their ability to visually distinguish benign from malignant lesions on the test set. Performance comparisons between reader groups and the model were performed using McNemar test. The impact of clinical and categorizable imaging data on algorithm performance was also assessed. A total of 200 patients (116 [58%] women and 84 [42%] men; mean age, 53.0 ± 17.9 years) with 126 of 200 (63%) benign and 74 of 200 (37%) malignant orbital lesions were included in the study. A total of 606 radiomics features were extracted. The best performing model on the training set was composed of 8 features including apparent diffusion coefficient mean value, maximum diameter on T1-WIs, and texture features. Area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity on the test set were respectively 0.869 (95% CI, 0.834-0.898), 0.840 (95% CI, 0.806-0.874), 0.684 (95% CI, 0.615-0.751), and 0.935 (95% CI, 0.905-0.961). The radiomics model outperformed all reader groups, including expert neuroradiologists (P < 0.01). Adding clinical and categorizable imaging data did not significantly impact the algorithm performance (P = 0.49). An MRI radiomics signature is helpful in differentiating benign from malignant orbital lesions and may outperform expert radiologists.
Identifiants
pubmed: 32932375
pii: 00004424-202103000-00006
doi: 10.1097/RLI.0000000000000722
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
173-180Informations de copyright
Copyright © 2020 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: none declared.
Références
Shields JA, Shields CL, Scartozzi R. Survey of 1264 patients with orbital tumors and simulating lesions: the 2002 Montgomery lecture, part 1. Ophthalmology . 2004;111:997–1008.
Cohen LM, Yoon MK. Update on current aspects of orbital imaging. Int Ophthalmol Clin . 2019;59:69–79.
Koukkoulli A, Pilling JD, Patatas K, et al. How accurate is the clinical and radiological evaluation of orbital lesions in comparison to surgical orbital biopsy? Eye . 2018;32:1329–1333.
Lecler A, Boucenna M, Lafitte F, et al. Usefulness of colour Doppler flow imaging in the management of lacrimal gland lesions. Eur Radiol . 2017;27:779–789.
Soussan JB, Deschamps R, Sadik JC, et al. Infraorbital nerve involvement on magnetic resonance imaging in European patients with IgG4-related ophthalmic disease: a specific sign. Eur Radiol . 2017;27:1335–1343.
Ro SR, Asbach P, Siebert E, et al. Characterization of orbital masses by multiparametric MRI. Eur J Radiol . 2016;85:324–336.
Roshdy N, Shahin M, Kishk H, et al. MRI in diagnosis of orbital masses. Curr Eye Res . 2010;35:986–991.
Fatima Z, Ichikawa T, Ishigame K, et al. Orbital masses: the usefulness of diffusion-weighted imaging in lesion categorization. Clin Neuroradiol . 2014;24:129–134.
Sepahdari AR, Aakalu VK, Setabutr P, et al. Indeterminate orbital masses: restricted diffusion at MR imaging with echo-planar diffusion-weighted imaging predicts malignancy. Radiology . 2010;256:554–564.
Sun B, Song L, Wang X, et al. Lymphoma and inflammation in the orbit: diagnostic performance with diffusion-weighted imaging and dynamic contrast-enhanced MRI. J Magn Reson Imaging . 2017;45:1438–1445.
Xu XQ, Qian W, Ma G, et al. Combined diffusion-weighted imaging and dynamic contrast-enhanced MRI for differentiating radiologically indeterminate malignant from benign orbital masses. Clin Radiol . 2017;72:903.e9–903.e15.
Yuan Y, Kuai XP, Chen XS, et al. Assessment of dynamic contrast-enhanced magnetic resonance imaging in the differentiation of malignant from benign orbital masses. Eur J Radiol . 2013;82:1506–1511.
Lecler A, Savatovsky J, Balvay D, et al. Repeatability of apparent diffusion coefficient and intravoxel incoherent motion parameters at 3.0 tesla in orbital lesions. Eur Radiol . 2017;27:5094–5103.
Lecler A, Balvay D, Cuenod C-A, et al. Quality-based pharmacokinetic model selection on DCE-MRI for characterizing orbital lesions. J Magn Reson Imaging . 2019;50:1514–1525.
Purgason PA, Hornblass A. Complications of surgery for orbital tumors. Ophthal Plast Reconstr Surg . 1992;8:88–93.
Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol . 2017;14:749–762.
Huang C, Cintra M, Brennan K, et al. Development and validation of radiomic signatures of head and neck squamous cell carcinoma molecular features and subtypes. EBioMedicine . 2019;45:70–80.
Jethanandani A, Lin TA, Volpe S, et al. Exploring applications of radiomics in magnetic resonance imaging of head and neck cancer: a systematic review. Front Oncol . 2018;8:131.
Rudie JD, Rauschecker AM, Bryan RN, et al. Emerging applications of artificial intelligence in neuro-oncology. Radiology . 2019;290:607–618.
Lecler A, Duron L, Balvay D, et al. Combining multiple magnetic resonance imaging sequences provides independent reproducible Radiomics features. Sci Rep . 2019;9:2068.
Duron L, Balvay D, Vande Perre S, et al. Gray-level discretization impacts reproducible MRI radiomics texture features. PLoS One . 2019;14:e0213459.
Guo J, Liu Z, Shen C, et al. MR-based radiomics signature in differentiating ocular adnexal lymphoma from idiopathic orbital inflammation. Eur Radiol . 2018;28:3872–3881.
Yushkevich PA, Piven J, Hazlett HC, et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage . 2006;31:1116–1128.
van Griethuysen JJM, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res . 2017;77:e104–e107.
Zwanenburg A, Vallières M, Abdalah MA, et al. The Image Biomarker Standardization Initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology . 2020;295:328–338.
Politi LS, Forghani R, Godi C, et al. Ocular adnexal lymphoma: diffusion-weighted MR imaging for differential diagnosis and therapeutic monitoring. Radiology . 2010;256:565–574.
Phuttharak W, Boonrod A, Patjanasoontorn N, et al. The roles of the diffusion-weighted imaging in orbital masses. J Med Imaging Radiat Oncol . 2017;61:753–758.
Surov A, Meyer HJ, Wienke A. Correlation between apparent diffusion coefficient (ADC) and cellularity is different in several tumors: a meta-analysis. Oncotarget . 2017;8:59492–59499.
Dregely I, Prezzi D, Kelly-Morland C, et al. Imaging biomarkers in oncology: basics and application to MRI. J Magn Reson Imaging . 2018;48:13–26.
Baessler B, Nestler T, Pinto dos Santos D, et al. Radiomics allows for detection of benign and malignant histopathology in patients with metastatic testicular germ cell tumors prior to post-chemotherapy retroperitoneal lymph node dissection. Eur Radiol . 2020;30:2334–2345.
Wu J, Liu A, Cui J, et al. Radiomics-based classification of hepatocellular carcinoma and hepatic haemangioma on precontrast magnetic resonance images. BMC Med Imaging . 2019;19:23.
Aerts HJ, Velazquez ER, Leijenaar RT, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun . 2014;5:4006.
Braman N, Prasanna P, Whitney J, et al. Association of peritumoral radiomics with tumor biology and pathologic response to preoperative targeted therapy for HER2 (ERBB2)-positive breast Cancer. JAMA Netw Open . 2019;2:e192561.
Erb-Eigner K, Asbach P, Ro SR, et al. DCE-MR imaging of orbital lesions: diagnostic performance of the tumor flow residence time τ calculated by a multi-compartmental pharmacokinetic tumor model based on individual factors. Acta Radiol . 2019;60:643–652.
Russo C, Strianese D, Perrotta M, et al. Multi-parametric magnetic resonance imaging characterization of orbital lesions: a triple blind study. Semin Ophthalmol . 2020;35:95–102.
Zhao B, Tan Y, Tsai WY, et al. Reproducibility of radiomics for deciphering tumor phenotype with imaging. Sci Rep . 2016;6:23428.
Baeßler B, Weiss K, Pinto dos Santos D. Robustness and reproducibility of radiomics in magnetic resonance imaging. Invest Radiol . 2019;54:221–228.
Hagiwara A, Fujita S, Ohno Y, et al. Variability and standardization of quantitative imaging: monoparametric to multiparametric quantification, radiomics, and artificial intelligence [published online ahead of print June 24, 2020]. Invest Radiol .
van Timmeren JE, Carvalho S, Leijenaar RTH, et al. Challenges and caveats of a multi-center retrospective radiomics study: an example of early treatment response assessment for NSCLC patients using FDG-PET/CT radiomics. PLoS One . 2019;14:e0217536.