Dataset Information

A simple model for glioma grading based on texture analysis applied to conventional brain MRI.

ABSTRACT: Accuracy of glioma grading is fundamental for the diagnosis, treatment planning and prognosis of patients. The purpose of this work was to develop a low-cost and easy-to-implement classification model which distinguishes low-grade gliomas (LGGs) from high-grade gliomas (HGGs), through texture analysis applied to conventional brain MRI. Different combinations of MRI contrasts (T1Gd and T2) and one segmented glioma region (necrotic and non-enhancing tumor core, NCR/NET) were studied. Texture features obtained from the gray level size zone matrix (GLSZM) were calculated. An under-sampling method was proposed to divide the data into different training subsets and subsequently extract complementary information for the creation of distinct classification models. The sensitivity, specificity and accuracy of the models were calculated, and the best model explicitly reported. The best model included only three texture features and reached a sensitivity, specificity and accuracy of 94.12%, 88.24% and 91.18%, respectively. According to the features of the model, when the NCR/NET region was studied, HGGs had a more heterogeneous texture than LGGs in the T1Gd images, and LGGs had a more heterogeneous texture than HGGs in the T2 images. These novel results partially contrast with results from the literature. The best model proved to be useful for the classification of gliomas. Complementary results showed that the heterogeneity of gliomas depended on the MRI contrast studied. The chosen model stands out as a simple, low-cost, easy-to-implement, reproducible and highly accurate glioma classifier. Importantly, it should be accessible to populations with reduced economic and scientific resources.

SUBMITTER: Suarez-Garcia JG

PROVIDER: S-EPMC7228074 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A simple model for glioma grading based on texture analysis applied to conventional brain MRI.

Suárez-García José Gerardo JG Hernández-López Javier Miguel JM Moreno-Barbosa Eduardo E de Celis-Alonso Benito B

PloS one 20200515 5

Accuracy of glioma grading is fundamental for the diagnosis, treatment planning and prognosis of patients. The purpose of this work was to develop a low-cost and easy-to-implement classification model which distinguishes low-grade gliomas (LGGs) from high-grade gliomas (HGGs), through texture analysis applied to conventional brain MRI. Different combinations of MRI contrasts (T1Gd and T2) and one segmented glioma region (necrotic and non-enhancing tumor core, NCR/NET) were studied. Texture featu ...[more]

PMID: 32413034

Similar Datasets

Project description:Background: Several neuroimaging studies report structural alterations of the trigeminal nerve in trigeminal neuralgia (TN). Less attention has been paid to structural brain changes occurring in TN, even though such changes can influence the development and response to treatment of other headache and chronic pain conditions. The purpose of this study was to apply a novel neuroimaging technique-texture analysis-to identify structural brain differences between classical TN patients and healthy subjects. Methods: We prospectively recruited 14 medically refractory classical TN patients and 20 healthy subjects. 3-Tesla T1-weighted brain MRI scans were acquired in all participants. Three texture features (autocorrelation, contrast, energy) were calculated within four a priori brain regions of interest (anterior cingulate, insula, thalamus, brainstem). Voxel-wise analysis was used to identify clusters of texture difference between TN patients and healthy subjects within regions of interest (p < 0.001, cluster size >20 voxels). Median raw texture values within clusters were also compared between groups, and further used to differentiate TN patients from healthy subjects (receiver-operator characteristic curve analysis). Median raw texture values were correlated with pain severity (visual analog scale, 1-100) and illness duration. Results: Several clusters of texture difference were observed between TN patients and healthy subjects: right-sided TN patients showed reduced autocorrelation in the left brainstem, increased contrast in the left brainstem and right anterior insula, and reduced energy in right and left anterior cingulate, right midbrain, and left brainstem. Within-cluster median raw texture values also differed between TN patients and healthy subjects: TN patients could be segregated from healthy subjects using brainstem autocorrelation (p = 0.0040, AUC = 0.84, sensitivity = 89%, specificity = 70%), anterior insula contrast (p = 0.0002, AUC = 0.92, sensitivity = 78%, specificity = 100%), and anterior cingulate energy (p = 0.0004, AUC = 0.92, sensitivity = 78%, specificity = 100%). Additionally, anterior insula contrast and duration of TN were inversely correlated (p = 0.030, Spearman r = -0.73). Conclusions: Texture analysis reveals distinct brain abnormalities in TN, which relate to clinical features such as duration of illness. These findings further implicate structural brain changes in the development and maintenance of TN.

Project description:Alzheimer's Disease (AD) is the most common neurodegenerative disease, with 10% prevalence in the elder population. Conventional Machine Learning (ML) was proven effective in supporting the diagnosis of AD, while very few studies investigated the performance of deep learning and transfer learning in this complex task. In this paper, we evaluated the potential of ensemble transfer-learning techniques, pretrained on generic images and then transferred to structural brain MRI, for the early diagnosis and prognosis of AD, with respect to a fusion of conventional-ML approaches based on Support Vector Machine directly applied to structural brain MRI. Specifically, more than 600 subjects were obtained from the ADNI repository, including AD, Mild Cognitive Impaired converting to AD (MCIc), Mild Cognitive Impaired not converting to AD (MCInc), and cognitively-normal (CN) subjects. We used T1-weighted cerebral-MRI studies to train: (1) an ensemble of five transfer-learning architectures pretrained on generic images; (2) a 3D Convolutional Neutral Network (CNN) trained from scratch on MRI volumes; and (3) a fusion of two conventional-ML classifiers derived from different feature extraction/selection techniques coupled to SVM. The AD-vs-CN, MCIc-vs-CN, MCIc-vs-MCInc comparisons were investigated. The ensemble transfer-learning approach was able to effectively discriminate AD from CN with 90.2% AUC, MCIc from CN with 83.2% AUC, and MCIc from MCInc with 70.6% AUC, showing comparable or slightly lower results with the fusion of conventional-ML systems (AD from CN with 93.1% AUC, MCIc from CN with 89.6% AUC, and MCIc from MCInc with AUC in the range of 69.1-73.3%). The deep-learning network trained from scratch obtained lower performance than either the fusion of conventional-ML systems and the ensemble transfer-learning, due to the limited sample of images used for training. These results open new prospective on the use of transfer learning combined with neuroimages for the automatic early diagnosis and prognosis of AD, even if pretrained on generic images.

Dataset Information

A simple model for glioma grading based on texture analysis applied to conventional brain MRI.

Publications

A simple model for glioma grading based on texture analysis applied to conventional brain MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure