Noninvasive Grading of Glioma Tumor Using Magnetic Resonance Imaging with Convolutional Neural Networks

Khawaldeh, Saed; Pervaiz, Usama; Rafiq, Azhar; Alkhawaldeh, Rami S.

doi:10.3390/app8010027

Cited by 141 publications

(58 citation statements)

References 33 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, in this work conventional MRI (T 1Gd and 455 T 2 contrasts) was studied, while others have analyzed advanced MRI or a combination 456 of both [5,[21][22][23][24][51][52][53][54]. The model was created from a simple mathematical method (a 457 multiple linear regression), in comparison to others in which mathematical tools of 458 higher complexity were utilized [7,[52][53][54]]. The best model was found to use only 3 459 variables of a single type (quantitative, being also only texture features), instead of a 460 combination of different classes and types of variables [21,24,51,53].…”

mentioning

confidence: 99%

A simple model for glioma grading based on texture analysis applied to conventional brain MRI

Suárez-García

Hernández-López

Moreno-Barbosa

et al. 2020

Preprint

View full text Add to dashboard Cite

11Accuracy of glioma grading is fundamental for the diagnosis, treatment planning and 12 prognosis of patients. The purpose of this work was to develop a low cost and easy to 13 implement classification model which distinguishes low grade gliomas (LGGs) from high 14 grade gliomas (HGGs), through texture analysis applied to conventional brain MRI. 15Different combinations between MRI contrasts (T 1Gd and T 2 ) and one segmented 16 glioma region (necrotic and non-enhancing tumor core (NCR/NET)) were studied. 17 Texture features obtained from the Gray Level Size Zone Matrix (GLSZM) were 18 calculated. An under-samplig method was proposed to divide the data into different 19 training subsets and subsequently extract complementary information for the creation 20 of distinct classification models. The sensitivity, specificity and accuracy of the models 21 were calculated. The best model was explicitly reported. The best model included only 22 three texture features and reached a sensitivity, specificity and accuracy of 94.12%, 23 88.24% and 91.18% respectively. According to the features of the model, when the 24 NCR/NET region was studied, HGGs had a more heterogeneous texture than LGGs in 25 the T 1Gd images and LGGs had a more heterogeneous texture than HGGs in the T 2 26 images. These novel results partially contrast with results from literature. The best 27 model proved to be useful for the classification of gliomas. Complementary results 28 showed that heterogeneity of gliomas depended on the studied MRI contrast. The 29 model presented stands out as a simple, low cost, easy to implement, reproducible and 30 highly accurate glioma classifier. What is more important, it should be accessible to 31 populations with reduced economic and scientific resources.32

show abstract

mentioning

confidence: 99%

A simple model for glioma grading based on texture analysis applied to conventional brain MRI

Suárez-García

Hernández-López

Moreno-Barbosa

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…These maps are then analyzed to create increasingly more complex and abstract representation of the items represented in the images. A broad number of applications of DCNNs in neuroradiology are being studied, and the most thoroughly investigated are: 1) automatic brain segmentation; 2) automatic detection of Alzheimer's disease‐associated lesions from functional MRI; 3) automatic detection of stroke‐related lesions from CT images; 4) prediction of genetic mutation; and 5) grading of gliomas …”

mentioning

confidence: 99%

“…A broad number of applications of DCNNs in neuroradiology are being studied, and the most thoroughly investigated are: 1) automatic brain segmentation 11,12 ; 2) automatic detection of Alzheimer's disease-associated lesions from functional MRI 13 ; 3) automatic detection of stroke-related lesions from CT images 14 ; 4) prediction of genetic mutation 15 ; and 5) grading of gliomas. 16,17 Recently, the scope to predict the grading of spontaneously occurring meningiomas from routine MRI sequences by means of DCNNs has been explored in dogs; an 82% accuracy in discrimination between benign, atypical, and malignant lesions was achieved on a small-sized dataset (56 patients). 18 Thus, the aim of our study was to determine whether application of DCNNs on apparent diffusion coefficient (ADC) maps and postcontrast T 1 -weighted (PCT 1 W) images could enable accurate discrimination of the histopathological grading of human meningiomas.…”

mentioning

confidence: 99%

Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: A preliminary study

Banzato

Causin

Puppa

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Grading of meningiomas is important in the choice of the most effective treatment for each patient. Purpose To determine the diagnostic accuracy of a deep convolutional neural network (DCNN) in the differentiation of the histopathological grading of meningiomas from MR images. Study Type Retrospective. Population In all, 117 meningioma‐affected patients, 79 World Health Organization [WHO] Grade I, 32 WHO Grade II, and 6 WHO Grade III. Field Strength/Sequence 1.5 T, 3.0 T postcontrast enhanced T1 W (PCT1W), apparent diffusion coefficient (ADC) maps (b values of 0, 500, and 1000 s/mm2). Assessment WHO Grade II and WHO Grade III meningiomas were considered a single category. The diagnostic accuracy of the pretrained Inception‐V3 and AlexNet DCNNs was tested on ADC maps and PCT1W images separately. Receiver operating characteristic curves (ROC) and area under the curve (AUC) were used to asses DCNN performance. Statistical Test Leave‐one‐out cross‐validation. Results The application of the Inception‐V3 DCNN on ADC maps provided the best diagnostic accuracy results, with an AUC of 0.94 (95% confidence interval [CI], 0.88–0.98). Remarkably, only 1/38 WHO Grade II–III and 7/79 WHO Grade I lesions were misclassified by this model. The application of AlexNet on ADC maps had a low discriminating accuracy, with an AUC of 0.68 (95% CI, 0.59–0.76) and a high misclassification rate on both WHO Grade I and WHO Grade II–III cases. The discriminating accuracy of both DCNNs on postcontrast T1W images was low, with Inception‐V3 displaying an AUC of 0.68 (95% CI, 0.59–0.76) and AlexNet displaying an AUC of 0.55 (95% CI, 0.45–0.64). Data Conclusion DCNNs can accurately discriminate between benign and atypical/anaplastic meningiomas from ADC maps but not from PCT1W images. Level of evidence: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:1152–1159.

show abstract

“…CNN is a kind of deep learning algorithm equipped with convolutional layers and inspired by a cat's visual cortex [26]. In the 1980s, Fukushima et al proposed a new kind of neural network with multiple simple cells and complex cells, which was regarded as the embryonic form of a CNN [32].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…Typical algorithms, such as a convolutional neural network (CNN), recurrent neural network (RNN), deep belief network (DBN), and so on, contain multiple nonlinear hidden layers to conduct supervised or unsupervised feature extraction, pattern recognition, and classification [25]. CNN is a type of feed-forward artificial neural network with shared weights and local connections [26]. As a kind of supervised algorithm, CNN is widely applied in image detection, speech recognition, handwritten digits identification, and so on.Inspired by the above background research, the authors of this paper aim to propose a cutting pattern recognition method for a coal mining shearer through the cutting sound.…”

mentioning

confidence: 99%

Cutting Pattern Identification for Coal Mining Shearer through Sound Signals Based on a Convolutional Neural Network

Wang

Tan

et al. 2018

Symmetry

View full text Add to dashboard Cite

Recently, sound-based diagnosis systems have been given much attention in many fields due to the advantages of their simple structure, non-touching measurement style, and low-power dissipation. In order to improve the efficiency of coal production and the safety of the coal mining process, accurate information is always essential. It is indicated that the sound signal produced during the cutting process of the coal mining shearer contains much cutting pattern identification information. In this paper, the original acoustic signal is first collected through an industrial microphone. To analyze the signal deeply, an adaptive Hilbert-Huang transform (HHT) was applied to decompose the sound to several intrinsic mode functions (IMFs) to subsequently acquire 1024 Hilbert marginal spectrum points. The 1024 time-frequency nodes were reorganized as a 32 × 32 feature map. Moreover, the LeNet-5 convolutional neural network (CNN), with three convolution layers and two sub-sampling layers, was used as the cutting pattern recognizer. A simulation example, with 10,000 training samples and 2000 testing samples, was conducted to prove the effectiveness of the proposed method. Finally, 1971 testing sound series were recognized accurately through the trained CNN and the proposed method achieved an identification rate of 98.55%. Therefore, it is widely applied in fault diagnosis [7,8], target detection [9], feature extraction [10], and so on.Unfortunately, the original cutting signal acquired from the coal mining field is always nonlinear, nonstationary, and discontinuous. It is an exceedingly difficult problem to extract key information from the signal. Thus, a powerful signal process method is one of the keys to settling the tough matter. However, typical sound signal analysis approaches such as short-time Fourier transform (STFT), wavelet transform (WT), and wavelet packet transform (WPT) are inappropriate to treat the cutting sound. Due to the characteristics of strong nonlinearity and nonstationarity, STFT is unable to play an effective role on the signal due to the Dirichlet condition and Heisenberg uncertainty principle [11,12]. Similarly, the WT and WPT do not work on interval cutting sound signal due to the fixed wavelet basis [13]. In 1998, an adaptive decomposing method, named the Hilbert-Huang transform (HHT), was established by National Aeronautics and Space Administration (NASA) [14]. The HHT is composed of empirical mode decomposition (EMD), proposed by Huang and Wu in 2008, and the Hilbert transform (HT) [15]. As the basis is adaptive, the HHT is not affected by the restrictions of previous approaches and becomes an attractive tool to find faults in diagnosis [16], speech recognition [17], signal denoising [18], pattern recognition [19], forecasting [20], and so on.After decomposing the original sound into a series of time-frequency characteristics, many researchers adopted some feature extractors to reduce the dimension and eliminate redundant information. The effectiveness of feature extracting is a key factor in t...

show abstract

Noninvasive Grading of Glioma Tumor Using Magnetic Resonance Imaging with Convolutional Neural Networks

Cited by 141 publications

References 33 publications

A simple model for glioma grading based on texture analysis applied to conventional brain MRI

A simple model for glioma grading based on texture analysis applied to conventional brain MRI

Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: A preliminary study

Cutting Pattern Identification for Coal Mining Shearer through Sound Signals Based on a Convolutional Neural Network

Contact Info

Product

Resources

About