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

The Importance of Simultaneous Surgical and Endoscopic Polypectomies in Peutz-Jeghers Syndrome: A Case Report

Peutz-Jeghers syndrome may be presented with gastrointestinal and extra-intestinal malignancies. Herein, we report a case of Peutz-Jeghers syndrome with a malignant intestinal polyp accompanied by synchronous multiple ha...

Methaemoglobinemia Developing Following Lidocain Use

Methaemoglobinemia is a severe haematological disease occurring when haemoglobin Fe+2 is oxidised to Fe+3, and characterised by cyanosis due to inability to transport sufficient oxygen to the tissues. Our case report is...

A Case of Sarcoidosis with Diffuse Cavitary Lesion in the Lung

Sarcoidosis is a granulomatous disease of unknown origin, which affects many organs and systems, and is often seen in young adults. The most common organ involved in sarcoidosis is the lung and various radiological featu...

Preliminary Outcomes of Hip Arthroscopy in the Treatment of Femoroacetabular Impingement with Early Stage Osteoarthritis

Introduction: Femoroacetabular impingement (FAI) has been recognized as a risk factor of osteoarthrosis that causes a painful joint and decreased range of motion. Arthroscopic procedures were used for the treatment of FA...

Determination of Vestibulo-ocular Reflex Gain Normal Values in Children with Video Head Impuls Test

Introduction: Video head impuls test (vHIT) is used in the diagnosis of vestibular dysfunction. There is no study conducted on vHIT application and its results on children in our country. Our study aimed to examine vHIT...

Download PDF file
  • EP ID EP675960
  • DOI 10.4274/imj.galenos.2019.09582
  • Views 162
  • 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