Updates on Deep Learning and Glioma

Chow, Daniel; Khatri, Deepak; Chang, Peter D.; Zlochower, Avraham; Boockvar, John A.; Filippi, Christopher G.

doi:10.1016/j.nic.2020.07.002

Cited by 18 publications

(10 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Glioma segmentation approach, which is based on the deep learning, may resolve the issues of manual analysis of data and design segmentation features in traditional image processing algorithms and machine learning algorithms and can automatically segment gliomas, which greatly overcomes the brain. e shortcomings of glioma segmentation that require strong prior constraints and manual intervention improve the robustness and effectiveness of the algorithm and can achieve better segmentation results in large-scale multimodal and complex glioma segmentation scenes [6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning Technology in Glioma

Qian

Sha

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

A common and most basic brain tumor is glioma that is exceptionally dangerous to health of various patients. A glioma segmentation, which is primarily magnetic resonance imaging (MRI) oriented, is considered as one of common tools developed for doctors. These doctors use this system to examine, analyse, and diagnose appearance of the glioma’s outward for both patients, i.e., indoor and outdoor. In the literature, a widely utilized approach for the segmentation of glioma is the deep learning-oriented method. To cope with this issue, a segmentation of glioma approach, i.e., primarily on the convolution neural networks, is developed in this manuscript. A DM-DA-enabled cascading approach for the segmentation of glioma, which is 2DResUnet-enabled model, is reported to resolve the problem of spatial data acquisition of insufficient 3D specifically in the 2D full CNN along with the core issue of memory consumption of 3D full CNN. For gliomas segmentation at various stages, we have utilized multiscale fusion approach, attention, segmentation, and DenseBlock. Moreover, for reducing three dimensionalities of the Unet model, a sampling of fixed region is used along with multisequence data of the glioma image. Finally, the CNN model has the ability of producing a better segmentation of tumor preferably with minimum possible memory. The proposed model has used BraTS18 and BraTS17 benchmark data sets for fivefold cross-validation (local) and online evaluation preferably official, respectively. Evaluation results have verified that edema’s Dice Score preferable average, enhancement, and core areas of the segmentation of the glioma with DM-DA-Unet perform exceptionally well on the validation set of BraTS17. Finally, average sensitivity was observed to be high as well, which is approximately closer to the best segmentation model and its effect on the validation set of BraTS1 and has segmented gliomas accurately.

show abstract

Section: Introductionmentioning

confidence: 99%

Application of Deep Learning Technology in Glioma

Qian

Sha

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

“…This can be attributed to the lack of new networks for extracting important features from training images, which is a result of the small amount of noise variation data used in training them [ 18 , 19 ]. In previous studies, the reconstruction of the learning mechanism for a specific purpose was achieved by optimizing the learning model by transfer learning [ 20 – 22 ]. In these studies, training data were experimentally created using human image and phantom data; therefore, the accuracy of their noise features was realistic and of high quality.…”

Section: Discussionmentioning

confidence: 99%

Quantitative evaluation of deep convolutional neural network-based image denoising for low-dose computed tomography

Usui

Ogawa

Goto

et al. 2021

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

To minimize radiation risk, dose reduction is important in the diagnostic and therapeutic applications of computed tomography (CT). However, image noise degrades image quality owing to the reduced X-ray dose and a possible unacceptably reduced diagnostic performance. Deep learning approaches with convolutional neural networks (CNNs) have been proposed for natural image denoising; however, these approaches might introduce image blurring or loss of original gradients. The aim of this study was to compare the dose-dependent properties of a CNN-based denoising method for low-dose CT with those of other noise-reduction methods on unique CT noise-simulation images. To simulate a low-dose CT image, a Poisson noise distribution was introduced to normal-dose images while convoluting the CT unit-specific modulation transfer function. An abdominal CT of 100 images obtained from a public database was adopted, and simulated dose-reduction images were created from the original dose at equal 10-step dose-reduction intervals with a final dose of 1/100. These images were denoised using the denoising network structure of CNN (DnCNN) as the general CNN model and for transfer learning. To evaluate the image quality, image similarities determined by the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) were calculated for the denoised images. Significantly better denoising, in terms of SSIM and PSNR, was achieved by the DnCNN than by other image denoising methods, especially at the ultra-low-dose levels used to generate the 10% and 5% dose-equivalent images. Moreover, the developed CNN model can eliminate noise and maintain image sharpness at these dose levels and improve SSIM by approximately 10% from that of the original method. In contrast, under small dose-reduction conditions, this model also led to excessive smoothing of the images. In quantitative evaluations, the CNN denoising method improved the low-dose CT and prevented over-smoothing by tailoring the CNN model.

show abstract

“…For classification in neuroimaging, imaging features are extracted and act as inputs to enter a neural network, like the convolutional neural network (CNN), which outputs a probability of the image belonging to each class. Deep learning methods have been applied in multiple aspects of gliomas, using MRI metrics to predict long-term outcome, treatment response like pseudopregression, and tumor genetics including 1p19q codeletion, O-6-methylguanine DNA-methyltransferase promoter, and IDH mutations (28). A deep learning approach would be able to model more complex and non-linear relationships between dependent and independent variables.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Malignant Transformation of WHO II Astrocytoma Using Mathematical Models Incorporating Apparent Diffusion Coefficient and Contrast Enhancement

et al. 2021

View full text Add to dashboard Cite

Using only increasing contrast enhancement as a marker of malignant transformation (MT) in gliomas has low specificity and may affect interpretation of clinical outcomes. Therefore we developed a mathematical model to predict MT of low-grade gliomas (LGGs) by considering areas of reduced apparent diffusion coefficient (ADC) with increased contrast enhancement. Patients with contrast-enhancing LGGs who had contemporaneous ADC and histopathology were retrospectively analyzed. Multiple clinical factors and imaging factors (contrast-enhancement size, whole-tumor size, and ADC) were assessed for association with MT. Patients were split into training and validation groups for the development of a predictive model using logistic regression which was assessed with receiver operating characteristic analysis. Among 132 patients, (median age 46.5 years), 106 patients (64 MT) were assigned to the training group and 26 (20 MT) to the validation group. The predictive model comprised age (P = 0.110), radiotherapy (P = 0.168), contrast-enhancement size (P = 0.015), and ADC (P < 0.001). The predictive model (area-under-the-curve [AUC] 0.87) outperformed ADC (AUC 0.85) and contrast-enhancement size (AUC 0.67). The model had an accuracy of 84% for the training group and 85% respectively for the validation group. Our model incorporating ADC and contrast-enhancement size predicted MT in contrast-enhancing LGGs.

show abstract

Updates on Deep Learning and Glioma

Cited by 18 publications

References 49 publications

Application of Deep Learning Technology in Glioma

Application of Deep Learning Technology in Glioma

Quantitative evaluation of deep convolutional neural network-based image denoising for low-dose computed tomography

Prediction of Malignant Transformation of WHO II Astrocytoma Using Mathematical Models Incorporating Apparent Diffusion Coefficient and Contrast Enhancement

Contact Info

Product

Resources

About