Classification of patients with tumor using MR FLAIR images

Gupta, Tanvi; Gandhi, Tapan Kumar; Gupta, Rakesh K.; Panigrahi, Bijaya Ketan

doi:10.1016/j.patrec.2017.10.037

Cited by 22 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to have better analyses, confusion matrix or error matrix plots, which illustrate the performance of a classification model, were presented [27,46]. These plots are the summary of the prediction results on the issue.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A novel diagnostic and prognostic approach for unresponsive patients with anthroponotic cutaneous leishmaniasis using artificial neural networks

et al. 2021

View full text Add to dashboard Cite

Cutaneous leishmaniasis (CL) imposes a major health burden throughout the tropical and subtropical regions of the globe. Unresponsive cases are common phenomena occurred upon exposure to the standard drugs. Therefore, rapid detection, prognosis and classification of the disease are crucial for selecting the proper treatment modality. Using machine learning (ML) techniques, this study aimed to detect unresponsive cases of ACL, caused by Leishmania tropica, which will consequently be used for a more effective treatment modality. This study was conducted as a case-control setting. Patients were selected in a major ACL focus from both unresponsive and responsive cases. Nine unique and relevant features of patients with ACL were selected. To categorize the patients, different classifier models such as k-nearest neighbors (KNN), support vector machines (SVM), multilayer perceptron (MLP), learning vector quantization (LVQ) and multipass LVQ were applied and compared for this supervised learning task. Comparison of the receiver operating characteristic graphs (ROC) and confusion plots for the above models represented that MLP was a fairly accurate prediction model to solve this problem. The overall accuracy in terms of sensitivity, specificity and area under ROC curve (AUC) of MLP classifier were 87.8%, 90.3%, 86% and 0.88%, respectively. Moreover, the duration of the skin lesion was the most influential feature in MLP classifier, while gender was the least. The present investigation demonstrated that MLP model could be utilized for rapid detection, accurate prognosis and effective treatment of unresponsive patients with ACL. The results showed that the major feature affecting the responsiveness to treatments is the duration of the lesion. This novel approach is unique and can be beneficial in developing diagnostic, prophylactic and therapeutic measures against the disease. This attempt could be a preliminary step towards the expansion of ML application in future directions.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Extensive studies have been conducted for detection and classification of the diseases worldwide. Tanvi Gupta et al [27] accomplished a research using several ML methods to classify 200 patients as normal and abnormal cases. Accordingly, 12 extracted features from MRI images were included.…”

Section: Introductionmentioning

confidence: 99%

A novel diagnostic and prognostic approach for unresponsive patients with anthroponotic cutaneous leishmaniasis using artificial neural networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Even though the results of this hybrid approach give 98% accuracy, it requires a longer time to predict the status of the brain images if the database is larger. Gupta et al [31] proposed a classification model for MRI-FLAIR images to detect a brain stroke. DWT is utilized for extracting the feature and the Principal Component Analysis (PCA) is employed for selecting the optimal features.…”

Section: Related Workmentioning

confidence: 99%

Pattern Descriptors Orientation and MAP Firefly Algorithm Based Brain Pathology Classification Using Hybridized Machine Learning Algorithm

Deepa¹,

Murugappan

Sumithra

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Magnetic Resonance Imaging (MRI) is a significant technique used to diagnose brain abnormalities at early stages. This paper proposes a novel method to classify brain abnormalities (tumor and stroke) in MRI images using a hybridized machine learning algorithm. The proposed methodology includes feature extraction (texture, intensity, and shape), feature selection, and classification. The texture features are extracted by intending a neoteric directional-based quantized extrema pattern. The intensity features are extracted by proposing the clustering-based wavelet transform. The shape-based extraction is preformed using conventional shape descriptors. Maximum A Priori (MAP) based firefly algorithm is proposed for feature selection. Finally, hybridized support vector-based random forest classifier is used for the classification. The MRI brain tumor and stroke images are detected and categorized into four classes which are a high-grade tumor, a low-grade tumor, an acute stroke, and a sub-acute stroke. Besides, three different regions are identified in tumor detection such as edema, and tumor (necrotic and non-enhancing) region. The accuracy of the proposed method is analyzed using various performance metrics in comparison with the few state-of-the-art classification methods. The proposed methodology successfully achieves a reliable accuracy of 88.3% for classifying brain tumor cases and 99.2% for brain stroke classification. The best F-score of 0.91 and the least FPR of 0.06 are attained while considering brain tumor classification against the proposed HSVFC. Likewise, HSVFC has 0.99 as the best F-score and a 0.0 FPR in the case of brain stroke classification. The experimental analysis offers a maximum mean accuracy of different classifiers for categorizing MRI brain tumor are 76.

show abstract

“…In this subsection, we compare the performance of our proposed SA-CNN architecture with popular brain tumor classification techniques; support vector machines (SVM) + statistical features [9], SVM + diffusion tensor segmentation (D-SEG) [10], minimum Redundancy Maximum Relevance (mRMR) + extremely randomized trees (ERT) [43] and discrete wavelet transforms [DWT] + principal component analysis (PCA) + Linear SVM [44]. In this subsection, we present comparative analyses of our proposed SA-CNN with competitive models; spectral network and locally connected networks (LCN) [46], Convolutional neural network (CNN) + fast localized spectral filtering [47], deep convolutional network (DCN) [48], and Dynamic edge filtering and CNN [49].…”

Section: Comparative Evaluation Of Proposed Sa-cnn With Other Machine...mentioning

confidence: 99%

Computer Aided Brain Tumor Diagnosis Network Employing Structure-Aware CNNs

Singh

Goel

Raghuvanshi

2022

Preprint

View full text Add to dashboard Cite

Brain tumor is one of the deadliest cancers diagnosed in humans. Accurate and early detection of brain tumors play pivotal role in analysing and planning its treatment accordingly. Therefore, development of automated assisted framework for brain tumor detection and classification becomes very important. This paper presents structure aware CNN (SA-CNN) for binary brain tumor classification. The proposed SA-CNN extracts discriminant and significant image features from brain tumor images. We develop structure aware convolution (SAC) filters by generalizing the filters in traditional convolution to capture structure information which equips the network with the capability to deal with datasets having Euclidean and non-Euclidean structures. We explore classification capabilities of other pre-trained deep convolutional neural networks, namely Alex-Net, VGG 19, Inception V1, Res-Net 34 and Dense-Net 161 for comparative analysis. The proposed network is more generalized as it does not rely on hand-crafted features maps and achieves better performance. Extensive experiments on benchmark Kaggle dataset and comparative analysis suggests that the proffered framework outperforms state-of-the-art (SOTA) techniques. The proposed framework achieves accuracy of 99.54% and 98.04 % on training dataset and test dataset respectively.

show abstract

Classification of patients with tumor using MR FLAIR images

Cited by 22 publications

References 23 publications

A novel diagnostic and prognostic approach for unresponsive patients with anthroponotic cutaneous leishmaniasis using artificial neural networks

A novel diagnostic and prognostic approach for unresponsive patients with anthroponotic cutaneous leishmaniasis using artificial neural networks

Pattern Descriptors Orientation and MAP Firefly Algorithm Based Brain Pathology Classification Using Hybridized Machine Learning Algorithm

Computer Aided Brain Tumor Diagnosis Network Employing Structure-Aware CNNs

Contact Info

Product

Resources

About