Voxel-based clustered imaging by multiparameter diffusion tensor images for glioma grading

Inano, Rika; Oishi, Naoya; Kunieda, Takeharu; Arakawa, Yoshiki; Yamao, Yukihiro; Shibata, Sumiya; Kikuchi, Takayuki; Fukuyama, Hidenao; Miyamoto, Susumu

doi:10.1016/j.nicl.2014.08.001

Cited by 43 publications

(63 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The leave-one-out cross validation (LOOCV) strategy, which is widely used in machine learning studies and allows the use of most training data, was applied to assess the performance of each classifier in our study [ 18 , 33 ]. Assuming the sample number is N , N -1 samples were selected as training data to construct the classifying model while the remained one sample was used as the testing data to testify the predicting accuracy.…”

Section: Methodsmentioning

confidence: 99%

“…First, a subset of vital features that contribute most or are most relevant to glioma grading can be picked up with suitable feature selection methods [ 4 , 17 ]. Furthermore, the machine can automatically learn the discrimination patterns from the existing data and establish the corresponding model to predict the individual glioma grade [ 16 , 18 ]. Additionally, the classifying model can be further optimized to improve its diagnostic accuracy by selecting an appropriated classifier, optimizing model parameters or specific validation procedure [ 4 , 19 , 20 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

et al. 2017

View full text Add to dashboard Cite

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Multiple tensor metrics, including average diffusion coefficient (ADC), fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), radial diffusivity (RD), planar tensor (Cp), spherical tensor (Cs), and linear tensor (Cl) can be calculated from DTI ( Basser and Pierpaoli, 2011 ). However, although previous studies mainly demonstrated the role of ADC, FA, and MD in glioma imaging ( Stadlbauer et al, 2006 ; Inano et al, 2014 ; Davanian et al, 2017 ), few have investigated the value of the rest of the scalar parameters, including the AD, RD, Cp, Cs, and Cl values in gliomas grade diagnosis. ADC, FA, and MD in the tumor zone are useful for distinguishing glioma grades.…”

Section: Introductionmentioning

confidence: 99%

Analysis of DTI-Derived Tensor Metrics in Differential Diagnosis between Low-grade and High-grade Gliomas

Jiang

Xiao

et al. 2017

Front. Aging Neurosci.

View full text Add to dashboard Cite

Purpose: It is critical and difficult to accurately discriminate between high- and low-grade gliomas preoperatively. This study aimed to ascertain the role of several scalar measures in distinguishing high-grade from low-grade gliomas, especially the axial diffusivity (AD), radial diffusivity (RD), planar tensor (Cp), spherical tensor (Cs), and linear tensor (Cl) derived from diffusion tensor imaging (DTI).Materials and Methods: Fifty-three patients with pathologically confirmed brain gliomas (21 low-grade and 32 high-grade) were included. Contrast-enhanced T1-weighted images and DTI were performed in all patients. The AD, RD, Cp, Cs, and Cl values in the tumor zone, peritumoral edema zone, white matter (WM) adjacent to edema and contralateral normal-appearing white matter (NAWM) were calculated. The DTI parameters and tumor grades were statistically analyzed, and receiver operating characteristic (ROC) curve analysis was also performed.Results: The DTI metrics in the affected hemisphere showed significant differences from those in the NAWM, except for the AD values in the tumor zone and the RD values in WM adjacent to edema in the low-grade groups, as well as the Cp values in WM adjacent to edema in the high-grade groups. AD in the tumor zone as well as Cs and Cl in WM adjacent to edema revealed significant differences between the low- and high-grade gliomas. The areas under the curve (Az) of all three metrics were greater than 0.5 in distinguishing low-grade from high-grade gliomas by ROC curve analysis, and the best DTI metric was Cs in WM adjacent to edema (Az: 0.692).Conclusion: AD in the tumor zone as well as Cs and Cl in WM adjacent to edema will provide additional information to better classify gliomas and can be used as non-invasive reliable biomarkers in glioma grading.

show abstract

“…Several articles reported that pre-operative assessment with the DTI provided helpful information for neurosurgery. Continuously growing numbers of literature data indicate DTI is not only used for demonstration of fiber destruction by tumor invasion but also as a part of multiparametric assessment complex for differential diagnosis and tumor grading [12]- [15].…”

Section: Discussionmentioning

confidence: 99%

Diffusion Tensor Imaging without Complex Statistical Analysis Could Be Helpful for Diagnosis

Yıldırım¹,

Alış²,

Samancı³

et al. 2016

OJMI

View full text Add to dashboard Cite

Objective: Thanks to fast developing technology, visualization of fiber tracts at brain is possible. But with the new developments, data processing and interpretation are becoming more difficult. Actually interpretations in these fields are mostly in-group analysis and are generally not useful on the basis of individual patient evaluations. In these regards, we investigated our cases with diffusion tensor imaging (DTI) and tried to show if the data could be interpreted simply by radiologist's eye or not. Material: Our study consisted of 31 cases that were evaluated in our center with 3 Tesla Magnetic Resonance Imaging (MRI) units. Cranial DTI studies performed for ischemia, posttraumatic axonal injury, congenital malformation, neoplasia, autism, mental retardation and epilepsy. Cranial DTI was performed to demonstrate effected fiber tracts in neoplasia and ischemia cases and was applied to identify any gross anomaly in microstructural anatomy beside normal conventional MRI in other cases. DTI images were evaluated, along with fused conventional T1 weighted 3D high-resolution images and FA maps. DTI were performed at the first administration of the patients. Results: In addition to chronic ischemic focuses in patients with ischemia, DTI-FA images showed us relevant signal changes secondary to Wallerian degeneration in two cases. In traumatic brain injury cases, though being isointense on conventional sequences, FA values showed decreased values at the levels of the axonal discontinuity. Major abnormalities of association and projection fibers in congenital malformation cases were visualized at both 3D-DTI fused images and FA map images. Displacement, infiltration, destruction fibers were clearly visualized in neoplasia cases. However, any objective abnormality wasn't reported at any cases diagnosed with motor mental retardation, epilepsy or neuropsychiatric diseases. Conclusion: Colored DTI images and FA maps are helpful in the way of diagnosis in most cases with organic

show abstract

Voxel-based clustered imaging by multiparameter diffusion tensor images for glioma grading

Cited by 43 publications

References 60 publications

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

Analysis of DTI-Derived Tensor Metrics in Differential Diagnosis between Low-grade and High-grade Gliomas

Diffusion Tensor Imaging without Complex Statistical Analysis Could Be Helpful for Diagnosis

Contact Info

Product

Resources

About