Brain tumor detection using statistical and machine learning method

Amin, Javeria; Sharif, Muhammad; Raza, Mudassar; Saba, Tanzila; Anjum, Muhammad Almas

doi:10.1016/j.cmpb.2019.05.015

Cited by 176 publications

(73 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The entire image quality evaluation was performed using three quantitative image metrics: peak signal‐to‐noise ratio (PSNR), 33 structural similarity index matrix (SSIM), 34 and root mean square error (RMSE) 35 . The PSNR evaluates the ratio between the maximum power of an input image and the power of features that distort the image.…”

Section: Methodsmentioning

confidence: 99%

“…The RMSE evaluates the visual comparison of input images and ground truth images. The calculation algorithms of the above three metrics were the same as previous studies 33–35 …”

Section: Methodsmentioning

confidence: 99%

“…The calculation algorithms of the above three metrics were the same as previous studies. [33][34][35]…”

Section: Quantitative Image Comparison Between Hr Images and Gt Imagesmentioning

confidence: 99%

See 2 more Smart Citations

High‐Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network

Kim

Pan

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background: A generative adversarial network could be used for high-resolution (HR) medical image synthesis with reduced scan time. Purpose: To evaluate the potential of using a deep convolutional generative adversarial network (DCGAN) for generating HR pre and HR post images based on their corresponding low-resolution (LR) images (LR pre and LR post). Study Type: This was a retrospective analysis of a prospectively acquired cohort. Population: In all, 224 subjects were randomly divided into 200 training subjects and an independent 24 subjects testing set. Field Strength/Sequence: Dynamic contrast-enhanced (DCE) MRI with a 1.5T scanner. Assessment: Three breast radiologists independently ranked the image datasets, using the DCE images as the ground truth, and reviewed the image quality of both the original LR images and the generated HR images. The BI-RADS category and conspicuity of lesions were also ranked. The inter/intracorrelation coefficients (ICCs) of mean image quality scores, lesion conspicuity scores, and Breast Imaging Reporting and Data System (BI-RADS) categories were calculated between the three readers. Statistical Test: Wilcoxon signed-rank tests evaluated differences among the multireader ranking scores. Results: The mean overall image quality scores of the generated HR pre and HR post were significantly higher than those of the original LR pre and LR post (4.77 ± 0.41 vs. 3.27 ± 0.43 and 4.72 ± 0.44 vs. 3.23 ± 0.43, P < 0.0001, respectively, in the multireader study). The mean lesion conspicuity scores of the generated HR pre and HR post were significantly higher than those of the original LR pre and LR post (4.18 ± 0.70 vs. 3.49 ± 0.58 and 4.35 ± 0.59 vs. 3.48 ± 0.61, P < 0.001, respectively, in the multireader study). The ICCs of the image quality scores, lesion conspicuity scores, and BI-RADS categories had good agreements among the three readers (all ICCs >0.75). Data Conclusion: DCGAN was capable of generating HR of the breast from fast pre-and postcontrast LR and achieved superior quantitative and qualitative performance in a multireader study. Level of Evidence: 3 Technical Efficacy Stage: 2

show abstract

Section: Methodsmentioning

confidence: 99%

“…The RMSE evaluates the visual comparison of input images and ground truth images. The calculation algorithms of the above three metrics were the same as previous studies 33–35 …”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

High‐Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network

Kim

Pan

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…Result obtained showed that the supervised learning method is more accurate in comparison to the weakly supervised method. Amin et al (2019) worked on brain tumor detection. Weiner filter with different wavelet bands were used for lesion enhancement and different statistical methods for brain tumor segmentation.…”

Section: Existing Workmentioning

confidence: 99%

Performance Evaluation of a Classification Model for Oral Tumor Diagnosis

Awoyelu¹,

Ojo²,

Aregbesola³

et al. 2019

CIS

View full text Add to dashboard Cite

This paper extracted features from region of interest of histopathology images, formulated a classification model for diagnosis, simulated the model and evaluated the performance of the model. This is with a view to developing a histopathology image classification model for oral tumor diagnosis. The input for the classification is the oral histopathology images obtained from Obafemi Awolowo University Dental Clinic histopathology archive. The model for oral tumor diagnosis was formulated using the multilayered perceptron type of artificial neural network. Image preprocessing on the images was done using Contrast Limited Adaptive Histogram Equalization (CLAHE), features were extracted using Gray Level Confusion Matrix (GLCM). The important features were identified using Sequential Forward Selection (SFS) algorithm. The model classified oral tumor diagnosis into tive classes: Ameloblastoma, Giant Cell Lesions, Pleomorphic Adenoma, Mucoepidermoid Carcinoma and Squamous Cell Carcinoma. The performance of the model was evaluated using specificity and sensitivity. The result obtained showed that the model yielded an average accuracy of 82.14%. The sensitivity and the specificity values of Ameloblastoma were 85.71% and 89.4%, of Giant Cell Lesions were 83.33% and 94.74%, of Pleomorphic Adenoma were 75% and 95.24%, of Mucoepidermoid Carcinoma were 100% and 100%, and of Squamous Cell Carcinoma were 71.43% and 94.74% respectively. The model is capable of assisting pathologists in making consistent and accurate diagnosis. It can be considered as a second opinion to augment a pathologist’s diagnostic decision.

show abstract

“…The experimental results indicate that the proposed method can effectively extract bearing fault features and provides a new solution for condition monitoring and fault diagnosis of rail vehicle axle-box bearings.Entropy 2019, 21, 865 2 of 23 decomposition (EMD) [4], local mean decomposition (LMD) [5], empirical wavelet transform (EWT) [6], and variational mode decomposition (VMD) [7] methods. WT is an effective time-frequency analysis method which has a good noise reduction effect [8], but it only decomposes the low-frequency band of the signal; the high-frequency band is not processed, so, the frequency resolution in the high-frequency band is low. Wavelet packet transform (WPT) methods improve on the wavelet transform, which can decompose the high-and low-frequency bands of the signal into multiple layers and provide a high-resolution analysis method for the signal.…”

mentioning

confidence: 99%

Fault Diagnosis for Rail Vehicle Axle-Box Bearings Based on Energy Feature Reconstruction and Composite Multiscale Permutation Entropy

Wei

et al. 2019

Entropy

View full text Add to dashboard Cite

The fault response signals of an axle-box bearing of a rail vehicle have strongly non-linear and non-stationary characteristics, which can reflect the operating state of the running gears. This paper proposes a novel method for bearing fault diagnosis based on frequency-domain energy feature reconstruction (EFR) and composite multiscale permutation entropy (CMPE). First, a wavelet packet transform (WPT) is applied to decompose the vibration signals into multiple frequency bands. Then, considering that the bearing-localized defects cause the axle-box bearing system to resonate at a high frequency, which will lead to uneven energy distribution of the signal in the frequency domain, the energy factors of each frequency band are calculated by an energy feature extraction algorithm, from which the frequency band with maximum energy factor (which contains abundant fault information) is reconstructed to the time-domain signal. Next, the complexity of the reconstructed signals is calculated by CMPE as fault feature vectors. Finally, the feature vectors are input into a medium Gaussian support vector machine (MG-SVM) for bearing condition classification. The proposed method is validated by a public bearing data set and a wheelset-bearing system test bench data set. The experimental results indicate that the proposed method can effectively extract bearing fault features and provides a new solution for condition monitoring and fault diagnosis of rail vehicle axle-box bearings.

show abstract

Brain tumor detection using statistical and machine learning method

Cited by 176 publications

References 37 publications

High‐Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network

High‐Resolution Breast MRI Reconstruction Using a Deep Convolutional Generative Adversarial Network

Performance Evaluation of a Classification Model for Oral Tumor Diagnosis

Fault Diagnosis for Rail Vehicle Axle-Box Bearings Based on Energy Feature Reconstruction and Composite Multiscale Permutation Entropy

Contact Info

Product

Resources

About