Machine Learning-based Texture Analysis of Contrast-enhanced MR Imaging to Differentiate between Glioblastoma and Primary Central Nervous System Lymphoma

Autor: Akira Kunimatsu, Takeyuki Watadani, Natsuko Kunimatsu, Hiroyuki Akai, Kouhei Kamiya, Osamu Abe, Koichiro Yasaka, Harushi Mori
Rok vydání: 2019
Předmět:
Support Vector Machine
Lymphoma
Brain tumor
Contrast Media
Machine learning
computer.software_genre
030218 nuclear medicine & medical imaging
Central Nervous System Neoplasms
Diagnosis
Differential
Machine Learning
03 medical and health sciences
0302 clinical medicine
Image Interpretation
Computer-Assisted
medicine
Humans
Radiology
Nuclear Medicine and imaging
Retrospective Studies
primary central nervous system lymphoma
medicine.diagnostic_test
Contextual image classification
Receiver operating characteristic
business.industry
glioblastoma
Primary central nervous system lymphoma
Magnetic resonance imaging
medicine.disease
Magnetic Resonance Imaging
Support vector machine
ROC Curve
classification
Artificial intelligence
business
computer
Classifier (UML)
Major Paper
030217 neurology & neurosurgery
Test data
Zdroj: Magnetic Resonance in Medical Sciences
ISSN: 1880-2206
1347-3182
DOI: 10.2463/mrms.mp.2017-0178
Popis: Purpose: Although advanced MRI techniques are increasingly available, imaging differentiation between glioblastoma and primary central nervous system lymphoma (PCNSL) is sometimes confusing. We aimed to evaluate the performance of image classification by support vector machine, a method of traditional machine learning, using texture features computed from contrast-enhanced T1-weighted images. Methods: This retrospective study on preoperative brain tumor MRI included 76 consecutives, initially treated patients with glioblastoma (n = 55) or PCNSL (n = 21) from one institution, consisting of independent training group (n = 60: 44 glioblastomas and 16 PCNSLs) and test group (n = 16: 11 glioblastomas and 5 PCNSLs) sequentially separated by time periods. A total set of 67 texture features was computed on routine contrast-enhanced T1-weighted images of the training group, and the top four most discriminating features were selected as input variables to train support vector machine classifiers. These features were then evaluated on the test group with subsequent image classification. Results: The area under the receiver operating characteristic curves on the training data was calculated at 0.99 (95% confidence interval [CI]: 0.96–1.00) for the classifier with a Gaussian kernel and 0.87 (95% CI: 0.77–0.95) for the classifier with a linear kernel. On the test data, both of the classifiers showed prediction accuracy of 75% (12/16) of the test images. Conclusions: Although further improvement is needed, our preliminary results suggest that machine learning-based image classification may provide complementary diagnostic information on routine brain MRI.
Databáze: OpenAIRE
Externí odkaz: