Reliability of 2D Magnetic Resonance Imaging Texture Analysis in Cerebral Gliomas: Influence of Slice Selection Bias on Reproducibility of Radiomic Features

Journal Title: Istanbul Medical Journal - Year 2019, Vol 20, Issue 5

Abstract

Introduction: In this study, we aimed to investigate the reproducibility of two-dimensional (2D) texture features between adjacent magnetic resonance imaging (MRI) slices in patients with cerebral gliomas. Methods: For this retrospective methodological study, T2-weighted MRI and semi-automatic segmentation data of 25 patients with lower-grade gliomas were obtained from a public database. Only two regions of interests were used in this study: (i), the largest slice and (ii) one of the adjacent slices. Using PyRadiomics, an open source software to extract radiomic features from medical images, a total of 1116 texture features from six different feature classes were extracted from original, Laplacian of Gaussian-filtered, and wavelet-transformed images. Intra-class correlation coefficient (ICC) values with and without 95% confidence interval (CI) were used for reliability analysis. The ICC threshold for excellent reproducibility was 0.9. Results: In the reliability analysis without considering the 95% CI for the ICC values, 28% of the texture features had excellent reproducibility. On the other hand, considering the 95% CI, only 10% of the texture features had excellent reproducibility. Neither a feature class (range of excellent reproducibility rates without 95% CI, 21.2%-34.4%; with 95% CI, 2.1%-18.3%) nor an image type (range of excellent reproducibility rates without 95% CI, 22.3%-41.9%; with 95% CI, 9.1%-14%) had considerable reliability in two adjacent MRI slices. Conclusion: 2D MRI texture analysis of gliomas using T2- weighted sequence is substantially sensitive to slice selection bias, which may lead to non-reproducible results in radiomic works.

Authors and Affiliations

Burak Koçak

Keywords

Related Articles

Short- and Long-term Outcomes After Curative Surgery for Rectal Cancer in Patients Under the Age of Fourty Years: A Stage Based Case-match Analysis

Introduction: The aim of the study is to compare the short and long-term outcomes after curative surgery for rectal cancer in patients under the age of 40 years and over the age of 50 years. Methods: A total of 46 patie...

The Value of F-18-fluorodeoxyglucose Positron Emission Tomography/Computed Tomography for the Detection of Residual Breast Tumor or Axillary Metastasis after Neoadjuvant Chemotherapy in Invasive Ductal Carcinoma of the Breast

Introduction: Accurate evaluation of pathological response after neoadjuvant chemotherapy would aid in treatment and surgical planning as well as prediction of outcomes. This study examined the value of F-18-fluorodeoxyg...

Health Care Transitions for Children with Sickle Cell Disease: Interventions, Perspectives of Health Care Providers and Caregivers

The incapacitating episodic complications associated with the Sickle Cell disease (SCD) limit the opportunities of those SCD patients in education, societal roles, career options, and quality of life, leading to an incre...

Can Complete Blood Count Inflammation Markers Be Used to Predict Graft Success After Tympanoplasty?

Introduction: This study aimed to investigate the effect of preoperative neutrophil lymphocyte ratio (NLR), platelet lymphocyte ratio (PLR), eosinophil lymphocyte ratio (ELR), basophil lymphocyte ratio (BLR) and lymphocy...

Download PDF file
  • EP ID EP675960
  • DOI 10.4274/imj.galenos.2019.09582
  • Views 117
  • Downloads 0

How To Cite

Burak Koçak (2019). Reliability of 2D Magnetic Resonance Imaging Texture Analysis in Cerebral Gliomas: Influence of Slice Selection Bias on Reproducibility of Radiomic Features. Istanbul Medical Journal, 20(5), -. https://europub.co.uk/articles/-A-675960