MR-based radiomics signature in differentiating ocular adnexal lymphoma from idiopathic orbital inflammation
To assess the value of the MR-based radiomics signature in differentiating ocular adnexal lymphoma (OAL) and idiopathic orbital inflammation (IOI).
One hundred fifty-seven patients with pathology-proven OAL (84 patients) and IOI (73 patients) were divided into primary and validation cohorts. Eight hundred six radiomics features were extracted from morphological MR images. The least absolute shrinkage and selection operator (LASSO) procedure and linear combination were used to select features and build radiomics signature for discriminating OAL from IOI. Discriminating performance was assessed by the area under the receiver-operating characteristic curve (AUC). The predictive results were compared with the assessment of radiologists by chi-square test.
Five radiomics features were included in the radiomics signature, which differentiated OAL from IOI with an AUC of 0.74 and 0.73 in the primary and validation cohorts respectively. There was a significant difference between the classification results of the radiomics signature and those of a radiology resident (p < 0.05), although there was no significant difference between the results of the radiomics signature and those of a more experienced radiologist (p > 0.05).
Radiomics features have the potential to differentiate OAL from IOI.
• Clinical and imaging findings of OAL and IOI often overlap, which makes diagnosis difficult.
• Radiomics features can potentially differentiate OAL from IOI non invasively.
• The radiomics signature discriminates OAL from IOI at the same level as an experienced radiologist.
KeywordsRadiomics Inflammation Lymphoma Orbital neoplasms Magnetic resonance imaging (MRI)
Apparent diffusion coefficient
Area under the ROC curve
Dynamic contrast enhanced
Echo train length
Fast spin echo
Grey level co-occurrence matrix
Grey level run length matrix
Intraclass correlation coefficient
Idiopathic orbital inflammation
Least absolute shrinkage and selection operators procedure
Magnetic resonance imaging
Number of excitations
Ocular adnexal lymphoma
Short-run high-grey emphasis
The authors would like to express their sincere appreciation to all reviewers for their kind comments.
This work was presented in part at the 2017 International Society of Magnetic Resonance Imaging in Medicine Annual Meeting.
This study has received funding from the High Level Health Technical Personnel of Bureau of Health in Beijing under grant no. 2014-2-005; Beijing Municipal Administration of Hospitals Clinical Medicine Development of Special Funding Support under grant no. ZYLX201704; Key Talent Project of Beijing under Grant no. 2014001; The Priming Scientific Research Foundation for the Senior Researcher in Beijing Tongren Hospital, Capital Medical University, under grant no. 2016-YJJ-GGL-011.
Compliance with ethical standards
The scientific guarantor of this publication is Junfang Xian.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise.
Written informed consent was obtained from all subjects (patients) in this study.
Institutional Review Board approval was obtained.
• diagnostic study
• performed at one institution
- 11.Mombaerts I, Rose GE, Garrity JA (2016) Orbital Inflammation: Biopsy first. Survey of Ophthalmology 61:664-669Google Scholar
- 31.Wang J, Kato F, Oyama-Manabe N et al (2015) Identifying triple-negative breast cancer using background parenchymal enhancement heterogeneity on dynamic contrast-enhanced MRI: A pilot radiomics study. PLOS ONE 10. https://doi.org/10.1371/journal.pone.0143308