scholarly journals RADIOMICS BASED SINGLE AND MULTI-CLASS GLIOMA CLASSIFICATION USING SUPPORT VECTOR MACHINE VARIANTS

2021 ◽  
Vol 57 (2) ◽  
pp. 265-273
Author(s):  
P.D. Seema ◽  
◽  
T. Bobby Christy ◽  
K.R. Anandh ◽  
◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Clinical Decision Making ◽  
World Health ◽  
Support Vector ◽  
Low Grade ◽  
Whole Brain ◽  
Grade Ii ◽  
Linear Svm ◽  
Grade Iii

The common type of primary brain tumor is glioma. The mortality rate of glioma patients is high due to delayed diagnosis, incorrect grading and treatment planning. Traditionally, gliomas were classified into Low Grade (grade-I and grade-II) and High Grade (grade-III and grade-IV). However, World Health Organization has insisted to classify the grades into grade-I(G-I), grade II(G-II), grade III(G-III) and grade IV(G-IV) individually to aid the physicians in clinical decision-making. Although there are limited number of studies reported to differentiate individual grades, the classification accuracy was low. Consequently, in this work single-class (G-II vs. G-III, G-II vs. G-IV and G-III vs. G-IV) and multi-class (G-II vs. G-III+IV, G-III vs. G-II+IV and G-IV vs. G-II+III) analysis was performed using specific region of tumor and whole brain as Regions of Interest(ROI) by extracting radiomic features. The images for this study (N=75) were obtained from The Cancer Imaging Archive. Further, the statistically significant features were used in the classification of individual grades by implementing variants of Support Vector Machine (SVM) algorithm: SVM, Linear-SVM and Least-Squared SVM. Among these, Linear-SVM resulted in the highest classification accuracy (>80%) with average sensitivity, specificity and AUC values of >70%. The comparative analysis of whole brain versus tumor ROI showed that the latter yielded better classification accuracy.

scholarly journals Intracranial solitary fibrous tumors/hemangiopericytomas: first report of malignant progression

2018 ◽  
Vol 128 (6) ◽  
pp. 1719-1724 ◽  
Author(s):  
Caroline Apra ◽  
Karima Mokhtari ◽  
Philippe Cornu ◽  
Matthieu Peyre ◽  
Michel Kalamarides
Keyword(s):  
Case Series ◽  
Malignant Progression ◽  
World Health ◽  
Low Grade ◽  
Lower Grade ◽  
First Report ◽  
Solitary Fibrous Tumors ◽  
Initial Surgery ◽  
Grade Ii ◽  
Grade Iii

OBJECTIVEMeningeal solitary fibrous tumors/hemangiopericytomas (MSFTs/HPCs) are rare intracranial tumors resembling meningiomas. Their classification was redefined in 2016 by the World Health Organization (WHO) as benign Grade I fibrohyaline type, intermediate Grade II hypercellular type, and malignant highly mitotic Grade III. This grouping is based on common histological features and identification of a common NAB2-STAT6 fusion.METHODSThe authors retrospectively identified 49 cases of MSFT/HPC. Clinical data were obtained from the medical records, and all cases were analyzed according to this new 2016 WHO grading classification in order to identify malignant transformations.RESULTSRecurrent surgery was performed in 18 (37%) of 49 patients. Malignant progression was identified in 5 (28%) of these 18 cases, with 3 Grade I and 2 Grade II tumors progressing to Grade III, 3–13 years after the initial surgery. Of 31 Grade III tumors treated in this case series, 16% (5/31) were proved to be malignant progressions from lower-grade tumors.CONCLUSIONSLow-grade MSFTs/HPCs can transform into higher grades as shown in this first report of such progression. This is a decisive argument in favor of a common identity for MSFT and meningeal HPC. High-grade MSFTs/HPCs tend to recur more often and be associated with reduced overall survival. Malignant progression could be one mechanism explaining some recurrences or metastases, and justifying long-term follow-up, even for patients with Grade I tumors.

Simulation and Performance Analysis of Tilted Time Window and Support Vector Machine Based Learning Object Ranking Method

2020 ◽  
Vol 13 (2) ◽  
pp. 153-164
Author(s):  
Narina Thakur ◽  
Deepti Mehrotra ◽  
Abhay Bansal ◽  
Manju Bala
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Time Window ◽  
Optimal Solution ◽  
Similarity Score ◽  
Learning Objects ◽  
Retrieval Algorithm ◽  
Support Vector ◽  
Computationally Efficient ◽  
User Query

Objective: Since the adequacy of Learning Objects (LO) is a dynamic concept and changes in its use, needs and evolution, it is important to consider the importance of LO in terms of time to assess its relevance as the main objective of the proposed research. Another goal is to increase the classification accuracy and precision. Methods: With existing IR and ranking algorithms, MAP optimization either does not lead to a comprehensively optimal solution or is expensive and time - consuming. Nevertheless, Support Vector Machine learning competently leads to a globally optimal solution. SVM is a powerful classifier method with its high classification accuracy and the Tilted time window based model is computationally efficient. Results: This paper proposes and implements the LO ranking and retrieval algorithm based on the Tilted Time window and the Support Vector Machine, which uses the merit of both methods. The proposed model is implemented for the NCBI dataset and MAT Lab. Conclusion: The experiments have been carried out on the NCBI dataset, and LO weights are assigned to be relevant and non - relevant for a given user query according to the Tilted Time series and the Cosine similarity score. Results showed that the model proposed has much better accuracy.

A visual terrain classification method for mobile robots’ navigation based on convolutional neural network and support vector machine

2021 ◽  
pp. 014233122098791
Author(s):  
Wanli Wang ◽  
Botao Zhang ◽  
Kaiqi Wu ◽  
Sergey A Chepinskiy ◽  
Anton A Zhilenkov ◽  
...  
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Mobile Robots ◽  
Convolutional Neural Network ◽  
Hybrid Method ◽  
Classification Accuracy ◽  
Support Vector ◽  
High Classification Accuracy ◽  
Enhance Efficiency ◽  
Multi Class Classification

In this paper, a hybrid method based on deep learning is proposed to visually classify terrains encountered by mobile robots. Considering the limited computing resource on mobile robots and the requirement for high classification accuracy, the proposed hybrid method combines a convolutional neural network with a support vector machine to keep a high classification accuracy while improve work efficiency. The key idea is that the convolutional neural network is used to finish a multi-class classification and simultaneously the support vector machine is used to make a two-class classification. The two-class classification performed by the support vector machine is aimed at one kind of terrain that users are mostly concerned with. Results of the two classifications will be consolidated to get the final classification result. The convolutional neural network used in this method is modified for the on-board usage of mobile robots. In order to enhance efficiency, the convolutional neural network has a simple architecture. The convolutional neural network and the support vector machine are trained and tested by using RGB images of six kinds of common terrains. Experimental results demonstrate that this method can help robots classify terrains accurately and efficiently. Therefore, the proposed method has a significant potential for being applied to the on-board usage of mobile robots.

Financial Distress Prediction Based on Support Vector Machine with a Modified Kernel Function

2016 ◽  
Vol 25 (3) ◽  
pp. 417-429
Author(s):  
Chong Wu ◽  
Lu Wang ◽  
Zhe Shi
Keyword(s):  
Support Vector Machine ◽  
Kernel Function ◽  
Financial Distress ◽  
Classification Accuracy ◽  
Feature Space ◽  
Support Vector ◽  
Input Space ◽  
Financial Distress Prediction ◽  
Support Vectors ◽  
Distress Prediction

AbstractFor the financial distress prediction model based on support vector machine, there are no theories concerning how to choose a proper kernel function in a data-dependent way. This paper proposes a method of modified kernel function that can availably enhance classification accuracy. We apply an information-geometric method to modifying a kernel that is based on the structure of the Riemannian geometry induced in the input space by the kernel. A conformal transformation of a kernel from input space to higher-dimensional feature space enlarges volume elements locally near support vectors that are situated around the classification boundary and reduce the number of support vectors. This paper takes the Gaussian radial basis function as the internal kernel. Additionally, this paper combines the above method with the theories of standard regularization and non-dimensionalization to construct the new model. In the empirical analysis section, the paper adopts the financial data of Chinese listed companies. It uses five groups of experiments with different parameters to compare the classification accuracy. We can make the conclusion that the model of modified kernel function can effectively reduce the number of support vectors, and improve the classification accuracy.

Feature Selection Method Based on Mutual Information and Support Vector Machine

2021 ◽  
pp. 2150021
Author(s):  
Gang Liu ◽  
Chunlei Yang ◽  
Sen Liu ◽  
Chunbao Xiao ◽  
Bin Song
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Mutual Information ◽  
Classification Accuracy ◽  
Feature Selection Method ◽  
Selection Method ◽  
Support Vector ◽  
Svm Classifier ◽  
Standard Data ◽  
Feature Dimension

A feature selection method based on mutual information and support vector machine (SVM) is proposed in order to eliminate redundant feature and improve classification accuracy. First, local correlation between features and overall correlation is calculated by mutual information. The correlation reflects the information inclusion relationship between features, so the features are evaluated and redundant features are eliminated with analyzing the correlation. Subsequently, the concept of mean impact value (MIV) is defined and the influence degree of input variables on output variables for SVM network based on MIV is calculated. The importance weights of the features described with MIV are sorted by descending order. Finally, the SVM classifier is used to implement feature selection according to the classification accuracy of feature combination which takes MIV order of feature as a reference. The simulation experiments are carried out with three standard data sets of UCI, and the results show that this method can not only effectively reduce the feature dimension and high classification accuracy, but also ensure good robustness.

Damage Identification for Simply-Supported Bridge Based on SVM Optimized by PSO (PSO-SVM)

2011 ◽  
Vol 80-81 ◽  
pp. 490-494 ◽  
Author(s):  
Han Bing Liu ◽  
Yu Bo Jiao ◽  
Ya Feng Gong ◽  
Hai Peng Bi ◽  
Yan Yi Sun
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Damage Identification ◽  
Fitness Function ◽  
Support Vector ◽  
Detection Accuracy ◽  
Damage Localization ◽  
Swarm Optimization ◽  
Simply Supported ◽  
Beam Bridge

A support vector machine (SVM) optimized by particle swarm optimization (PSO)-based damage identification method is proposed in this paper. The classification accuracy of the damage localization and the detection accuracy of severity are used as the fitness function, respectively. The best and can be obtained through velocity and position updating of PSO. A simply supported beam bridge with five girders is provided as numerical example, damage cases with single and multiple suspicious damage elements are established to verify the feasibility of the proposed method. Numerical results indicate that the SVM optimized by PSO method can effectively identify the damage locations and severity.

Using Stratified Sample and Grid Search to Improve Disease Prediction Accuracy of SVM

2013 ◽  
Vol 295-298 ◽  
pp. 644-647 ◽  
Author(s):  
Yu Kai Yao ◽  
Hong Mei Cui ◽  
Ming Wei Len ◽  
Xiao Yun Chen
Keyword(s):  
Data Mining ◽  
Support Vector Machine ◽  
Classification Accuracy ◽  
Prediction Accuracy ◽  
Support Vector ◽  
Disease Prediction ◽  
Data Mining Algorithm ◽  
Grid Search ◽  
Mining Algorithm ◽  
Stratified Sample

SVM (Support Vector Machine) is a powerful data mining algorithm, and is mainly used to finish classification or regression tasks. In this literature, SVM is used to conduct disease prediction. We focus on integrating with stratified sample and grid search technology to improve the classification accuracy of SVM, thus, we propose an improved algorithm named SGSVM: Stratified sample and Grid search based SVM. To testify the performance of SGSVM, heart-disease data from UCI are used in our experiment, and the results show SGSVM has obvious improvement in classification accuracy, and this is very valuable especially in disease prediction.

scholarly journals The Role of Extent of Resection in IDH1 Wild-Type or Mutant Low-Grade Gliomas

Neurosurgery ◽  
2017 ◽  
Vol 82 (6) ◽  
pp. 808-814 ◽  
Author(s):  
Toral Patel ◽  
Evan D Bander ◽  
Rachael A Venn ◽  
Tiffany Powell ◽  
Gustav Young-Min Cederquist ◽  
...  
Keyword(s):  
Cox Regression ◽  
Extent Of Resection ◽  
World Health ◽  
Low Grade ◽  
Wild Type ◽  
Who Grade ◽  
Cox Regression Analysis ◽  
Low Grade Gliomas ◽  
Grade Ii ◽  
The Impact

Abstract BACKGROUND Maximizing extent of resection (EOR) improves outcomes in adults with World Health Organization (WHO) grade II low-grade gliomas (LGG). However, recent studies demonstrate that LGGs bearing a mutation in the isocitrate dehydrogenase 1 (IDH1) gene are a distinct molecular and clinical entity. It remains unclear whether maximizing EOR confers an equivalent clinical benefit in IDH mutated (mtIDH) and IDH wild-type (wtIDH) LGGs. OBJECTIVE To assess the impact of EOR on malignant progression-free survival (MPFS) and overall survival (OS) in mtIDH and wtIDH LGGs. METHODS We performed a retrospective review of 74 patients with WHO grade II gliomas and known IDH mutational status undergoing resection at a single institution. EOR was assessed with quantitative 3-dimensional volumetric analysis. The effect of predictor variables on MPFS and OS was analyzed with Cox regression models and the Kaplan–Meier method. RESULTS Fifty-two (70%) mtIDH patients and 22 (30%) wtIDH patients were included. Median preoperative tumor volume was 37.4 cm3; median EOR of 57.6% was achieved. Univariate Cox regression analysis confirmed EOR as a prognostic factor for the entire cohort. However, stratifying by IDH status demonstrates that greater EOR independently prolonged MPFS and OS for wtIDH patients (hazard ratio [HR] = 0.002 [95% confidence interval {CI} 0.000-0.074] and HR = 0.001 [95% CI 0.00-0.108], respectively), but not for mtIDH patients (HR = 0.84 [95% CI 0.17-4.13] and HR = 2.99 [95% CI 0.15-61.66], respectively). CONCLUSION Increasing EOR confers oncologic and survival benefits in IDH1 wtLGGs, but the impact on IDH1 mtLGGs requires further study.

MR Imaging of Hepatocellular Carcinoma

1995 ◽  
Vol 36 (2) ◽  
pp. 163-167 ◽  
Author(s):  
H. Honda ◽  
H. Onitsuka ◽  
Y. Kanazawa ◽  
T. Matsumata ◽  
T. Hayashi ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Mr Imaging ◽  
Low Grade ◽  
Hepatic Parenchyma ◽  
Grade Ii ◽  
Paramagnetic Ions ◽  
Grade Malignancy ◽  
Histopathologic Findings ◽  
Signal Intensities ◽  
Grade Iii

In order to clarify the factors contributing to the signal intensities (SIs) of HCC on T1-weighted images, the amount of water, lipid, copper (Cu), iron (Fe), and manganese (Mn) was determined in HCC and surrounding hepatic parenchyma of 13 patients. The relationships among these findings, the histopathologic findings, and the SIs of T1-weighted images were evaluated. Among the 13 HCC, 3 had a high SI, 5 were isointense, and 5 had a low SI on T1-weighted images compared to the surrounding hepatic parenchyma. The paramagnetic ions which contributed to the SI patterns were assumed to be Cu in HCC (38.0±62.4 μg/g ww), and Fe in the liver (61.1±42.4 μg/g ww) and HCC (40.0±34.3 μg/g ww). In 8 HCC with high- or isointensity, 2 were grades I, 5 were grade II, and one was grade III according to the Edmondson-Steiner's histopathologic classification. It is concluded that the SI patterns alone can not be a sign of low grade malignancy because of the existence of Fe in livers and HCC.

Sign in / Sign up

Export Citation Format

Share Document