MRI-based Texture Analysis in Differentiation of Benign and Malignant Vertebral Compression Fractures
Open Access
- 17 April 2024
- journal article
- research article
- Published by Bentham Science Publishers Ltd. in Current Medical Imaging
- Vol. 20, 1-9
Abstract
Introduction:: The diagnosis and characterization of vertebral compression fractures are very important for clinical management. In this evaluation, which is usually performed with diagnostic (conventional) imaging, the findings are not always typical or diagnostic. Therefore, it is important to have new information to support imaging findings. Texture analysis is a method that can evaluate information contained in diagnostic images and is not visually noticeable. This study aimed to evaluate the magnetic resonance images of cases diagnosed with vertebral compression fractures by the texture analysis method, compare them with histopathological data, and investigate the effectiveness of this method in the differentiation of benign and malignant vertebral compression fractures. Methods:: Fifty-five patients with a total of 56 vertebral compression fractures were included in the study. Magnetic resonance images were examined and segmented using Local Image Feature Extraction (LIFEx) software, which is an open-source program for texture analysis. The results were compared with the histopathological diagnosis. Results:: The application of the Decision Tree algorithm to the dataset yielded impressively accurate predictions (≈95% in accuracy, precision, and recall). Conclusion:: Interpreting tissue analysis parameters together with conventional magnetic resonance imaging findings can improve the abilities of radiologists, lead to accurate diagnoses, and prevent unnecessary invasive procedures. Further prospective trials in larger populations are needed to verify the role and performance of texture analysis in patients with vertebral compression fractures.Keywords
This publication has 25 references indexed in Scilit:
- Differentiation of benign and malignant vertebral fractures using a convolutional neural network to extract CT-based texture featuresEuropean Spine Journal, 2023
- PlexusNet: A neural network architectural concept for medical image classificationComputers in Biology and Medicine, 2023
- Vertebral trabecular bone texture analysis in opportunistic MRI and CT scan can distinguish patients with and without osteoporotic vertebral fracture: A preliminary studyEuropean Journal of Radiology, 2022
- Radiomics of computed tomography and magnetic resonance imaging in renal cell carcinoma—a systematic review and meta-analysisEuropean Radiology, 2020
- Diagnostic Performance of Mammographic Texture Analysis in the Differential Diagnosis of Benign and Malignant Breast TumorsClinical Breast Cancer, 2018
- Beyond imaging: The promise of radiomicsPhysica Medica, 2017
- Prediction of the therapeutic response after FOLFOX and FOLFIRI treatment for patients with liver metastasis from colorectal cancer using computerized CT texture analysisEuropean Journal of Radiology, 2016
- Shape, texture and statistical features for classification of benign and malignant vertebral compression fractures in magnetic resonance imagesComputers in Biology and Medicine, 2016
- Assessment of tumor heterogeneity by CT texture analysis: Can the largest cross-sectional area be used as an alternative to whole tumor analysis?European Journal of Radiology, 2013
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012