An Effective Approach for Sub-acute Ischemic Stroke Lesion Segmentation by Adopting Meta-Heuristics Feature Selection Technique Along with Hybrid Naive Bayes and Sample-Weighted Random Forest Classification

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Melingi Sunil Babu ◽  
V. Vijayalakshmi
Keyword(s):  
Feature Selection ◽  
Ischemic Stroke ◽  
Random Forest ◽  
Acute Ischemic Stroke ◽  
Lesion Segmentation ◽  
Feature Selection Technique ◽  
Selection Technique ◽  
Random Forest Classification ◽  
Forest Classification ◽  
Stroke Lesion

scholarly journals Deep Learning-Based Acute Ischemic Stroke Lesion Segmentation Method on Multimodal MR Images Using a Few Fully Labeled Subjects

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Bin Zhao ◽  
Zhiyang Liu ◽  
Guohua Liu ◽  
Chen Cao ◽  
Song Jin ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Segmentation Method ◽  
Lesion Segmentation ◽  
Resonance Imaging ◽  
Mr Images ◽  
Dice Coefficient ◽  
Automatic Methods ◽  
Stroke Lesion ◽  
Magnetic Resonance Imaging Mri

Acute ischemic stroke (AIS) has been a common threat to human health and may lead to severe outcomes without proper and prompt treatment. To precisely diagnose AIS, it is of paramount importance to quantitatively evaluate the AIS lesions. By adopting a convolutional neural network (CNN), many automatic methods for ischemic stroke lesion segmentation on magnetic resonance imaging (MRI) have been proposed. However, most CNN-based methods should be trained on a large amount of fully labeled subjects, and the label annotation is a labor-intensive and time-consuming task. Therefore, in this paper, we propose to use a mixture of many weakly labeled and a few fully labeled subjects to relieve the thirst of fully labeled subjects. In particular, a multifeature map fusion network (MFMF-Network) with two branches is proposed, where hundreds of weakly labeled subjects are used to train the classification branch, and several fully labeled subjects are adopted to tune the segmentation branch. By training on 398 weakly labeled and 5 fully labeled subjects, the proposed method is able to achieve a mean dice coefficient of 0.699 ± 0.128 on a test set with 179 subjects. The lesion-wise and subject-wise metrics are also evaluated, where a lesion-wise F1 score of 0.886 and a subject-wise detection rate of 1 are achieved.

scholarly journals Automatic Acute Ischemic Stroke Lesion Segmentation Using Semi-supervised Learning

2021 ◽  
Vol 14 (1) ◽  
pp. 723
Author(s):  
Bin Zhao ◽  
Shuxue Ding ◽  
Hong Wu ◽  
Guohua Liu ◽  
Chen Cao ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Supervised Learning ◽  
Lesion Segmentation ◽  
Stroke Lesion

scholarly journals Loan Amount Prediction Using Machine Learning

2021 ◽  
pp. 212-215
Author(s):  
Bhagyashri Rajesh Jawale ◽  
Priyanka Anil Badgujar ◽  
Rita Dnyaneshwar Talele ◽  
Dr. Dinesh D. Patil
Keyword(s):  
Feature Selection ◽  
Random Forest ◽  
Research Work ◽  
Ensemble Methods ◽  
Classification Algorithm ◽  
Optimization Techniques ◽  
Random Forest Classification ◽  
Forest Classification ◽  
Or Organization ◽  
Loan Amount

Loan amount prediction is helpful for banks or organization who want their work easier. All Banks give Loan to customer and customer first apply for loan after any bank or organization validate customer information. It must be providing some advantages for banks or company or any organization who wants to give loan. There are various methods to improve the accuracy classification algorithm. The accuracy of random forest classification algorithm can be improved using Ensemble methods. Optimization techniques and Feature selection methods available. In this research work novel hybrid feature selection algorithm using wrapper model and fisher introduced. The main objective of this paper is to prove that new hybrid model produces better accuracy than the traditional random forest algorithm.

Extra Tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences

2015 ◽  
Vol 240 ◽  
pp. 89-100 ◽  
Author(s):  
Oskar Maier ◽  
Matthias Wilms ◽  
Janina von der Gablentz ◽  
Ulrike M. Krämer ◽  
Thomas F. Münte ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Lesion Segmentation ◽  
Stroke Lesion ◽  
Mr Sequences

Feature Selection and Random Forest Classification for Breast Cancer Disease

2021 ◽  
pp. 191-210
Author(s):  
Shubham Raj ◽  
Swati Singh ◽  
Avinash Kumar ◽  
Sobhangi Sarkar ◽  
Chittaranjan Pradhan
Keyword(s):  
Breast Cancer ◽  
Feature Selection ◽  
Random Forest ◽  
Cancer Disease ◽  
Random Forest Classification ◽  
Forest Classification

scholarly journals Nonlinear Random Forest Classification, a Copula-Based Approach

2021 ◽  
Vol 11 (15) ◽  
pp. 7140
Author(s):  
Radko Mesiar ◽  
Ayyub Sheikhi
Keyword(s):  
Feature Selection ◽  
Random Forest ◽  
Linear Function ◽  
Simulation Study ◽  
Random Forest Algorithm ◽  
Real Dataset ◽  
Random Forest Classification ◽  
Forest Classification

In this work, we use a copula-based approach to select the most important features for a random forest classification. Based on associated copulas between these features, we carry out this feature selection. We then embed the selected features to a random forest algorithm to classify a label-valued outcome. Our algorithm enables us to select the most relevant features when the features are not necessarily connected by a linear function; also, we can stop the classification when we reach the desired level of accuracy. We apply this method on a simulation study as well as a real dataset of COVID-19 and for a diabetes dataset.

Sign in / Sign up

Export Citation Format

Share Document