Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach |
| |
| Affiliation: | 1. Center for Biomaterials and Tissue Engineering, Universitat Politècnica de València, Camí de Vera s/n, 46022 Valencia, Spain;2. Radiology Department, Hospital Universitario de la Ribera, 46600 Alzira, Valencia, Spain;1. Medical Physics Unit, McGill University, Montreal, Quebec, Canada;2. Department of Biomedical Engineering, McGill University, Montreal, Quebec, Canada;3. Department of Nuclear Medicine and Radiobiology, Université de Sherbrooke, Sherbrooke, Quebec, Canada;4. Aarhus University Hospital, Aarhus, Denmark;5. Department of Oncology, McGill University, Montreal, Quebec, Canada;6. Research Institute of the McGill University Health Centre, Montreal, Quebec H3H 2L9, Canada;7. Lady Davis Institute for Medical Research, Jewish General Hospital, Montreal, Quebec H3T 1E2, Canada;1. Medical Physics, San Raffaele Scientific Institute, Milano, Italy;2. Radiology, San Raffaele Scientific Institute, Milano, Italy;3. Pancreatic Surgery Unit, Pancreas Translational and Clinical Research Center, San Raffaele Scientific Institute, Milano, Italy;4. Università Vita-Salute, Milano, Italy;1. Department of Radiation Oncology, Mayo Clinic, Rochester, Minnesota;2. Department of Diagnostic Radiology, Mayo Clinic, Rochester, Minnesota;3. Department of Radiation Oncology, Mayo Clinic, Jacksonville, Florida;1. Department of Radiology, The First Affiliated Hospital of Dalian Medical University, Dalian 116000, China;2. College of medical imaging, Dalian Medical University, Dalian, 116044, China;3. Department of Radiology, Beijing Tian Tan Hospital, Capital Medical University, Beijing, 100050, China;4. Life science, GE Healthcare, Shenyang, 110000, China;5. GE Healthcare, MR Research China, Beijing, China;6. Department of Chronic Disease Epidemiology, Yale School of Public Health, Yale University, New Haven, Connecticut, USA;1. Department of Radiology, First Clinical Medical College, Shanxi Medical University, Taiyuan 030001, Shanxi Province, China;2. College of Medical Imaging, Shanxi Medical University, Taiyuan 030001, Shanxi Province, China;3. Departments of Cancer Physiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida, USA |
| |
| Abstract: | PurposeTo evaluate the potential of 2D texture features extracted from magnetic resonance (MR) images for differentiating brain metastasis (BM) and glioblastomas (GBM) following a radiomics approach.MethodsThis retrospective study included 50 patients with BM and 50 with GBM who underwent T1-weighted MRI between December 2010 and January 2017. Eighty-eight rotation-invariant texture features were computed for each segmented lesion using six texture analysis methods. These features were also extracted from the four images obtained after applying the discrete wavelet transform (88 features × 4 images). Three feature selection methods and five predictive models were evaluated. A 5-fold cross-validation scheme was used to randomly split the study group into training (80 patients) and testing (20 patients), repeating the process ten times. Classification was evaluated computing the average area under the receiver operating characteristic curve. Sensibility, specificity and accuracy were also computed. The whole process was tested quantizing the images with different gray-level values to evaluate their influence in the final results.ResultsHighest classification accuracy was obtained using the original images quantized with 128 gray-levels and a feature selection method based on the p-value. The best overall performance was achieved using a support vector machine model with a subset of 32 features (AUC = 0.896 ± 0.067, sensitivity of 82% and specificity of 80%). Naïve Bayes and k-nearest neighbors models showed also valuable results (AUC ≈ 0.8) with a lower number of features (<13), thus suggesting that these models may be more generalizable when using external validations.ConclusionThe proposed radiomics MRI approach is able to discriminate between GBM and BM with high accuracy employing a set of 2D texture features, thus helping in the diagnosis of brain lesions in a fast and non-invasive way. |
| |
| Keywords: | Radiomics Texture analysis Brain tumors Magnetic resonance imaging |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
