Classifying tumor brain images using parallel deep learning algorithms

Kazemi, Ahmad; Shiri, Mohammad Ebrahim; Sheikhahmadi, Amir; khodamoradi, Mohamad

doi:10.1016/j.compbiomed.2022.105775

Cited by 20 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep parallel convolution neural network model based on the AlexNet and VGGNet networks is used in the proposed strategy by Kazemi et.al. 22 The softmax function is used to initially classify the features once they have been merged. When compared to the models that are already in use, the proposed model has provided results that are superior.…”

Section: Literature Surveymentioning

confidence: 99%

Design and assessment of improved Convolutional Neural Network based brain tumor segmentation and classification system

Chauhan,

Singh,

Kumar

et al. 2024

JIST

View full text Add to dashboard Cite

Deep learning techniques have recently demonstrated promising outcomes in the segmentation of brain tumors from MRI images. Due to its capability to handle high-resolution images and segment the entire tumor region, the U-Net model is one of them and is frequently utilized. For the analysis and planning of brain tumors treatments, accurate segmentation of brain tumors using multi-contrast MRI images is essential. Deep learning models including U-Net, PSPNet, DeepLabV3+, and ResNet50 have demonstrated encouraging outcomes in the segmentation of brain tumors. Using the BraTS 2018 dataset, we compare these models in this research. We evaluate the models using a variety of measures, including the Hausdorff Distance (HD), the Absolute Volume Difference (AVD), and the Dice Similarity Coefficient (DSC), and we look into how data augmentation and transfer learning approaches affect the models' performance. The findings demonstrate that the 3D U-Net model performed the best, with a DSC of 0.90, HD of 10.69mm, and AVD of 11.15%. The PSPNet model achieved comparable performance, with a DSC of 0.89, HD of 11.37mm, and AVD of 12.24%. The DeepLabV3+ and ResNet50 models achieved lower performance, with DSCs of 0.85 and 0.83, respectively. Based on the discoveries and analysis, the 3D U-Net model with data augmentation and transfer learning is suggested for brain tumors segmentation utilizing multi-contrast MRI images.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Design and assessment of improved Convolutional Neural Network based brain tumor segmentation and classification system

Chauhan,

Singh,

Kumar

et al. 2024

JIST

View full text Add to dashboard Cite

show abstract

“…Recent research has shown that the CAD system for brain tumors can be much improved with the help of deep learning algorithms [ 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 ]. Brain images were classified into four types of tumors using a DCNN [ 66 ].…”

Section: Literature Reviewmentioning

confidence: 99%

Clinical Decision Support Framework for Segmentation and Classification of Brain Tumor MRIs Using a U-Net and DCNN Cascaded Learning Algorithm

et al. 2022

View full text Add to dashboard Cite

Brain tumors (BTs) are an uncommon but fatal kind of cancer. Therefore, the development of computer-aided diagnosis (CAD) systems for classifying brain tumors in magnetic resonance imaging (MRI) has been the subject of many research papers so far. However, research in this sector is still in its early stage. The ultimate goal of this research is to develop a lightweight effective implementation of the U-Net deep network for use in performing exact real-time segmentation. Moreover, a simplified deep convolutional neural network (DCNN) architecture for the BT classification is presented for automatic feature extraction and classification of the segmented regions of interest (ROIs). Five convolutional layers, rectified linear unit, normalization, and max-pooling layers make up the DCNN’s proposed simplified architecture. The introduced method was verified on multimodal brain tumor segmentation (BRATS 2015) datasets. Our experimental results on BRATS 2015 acquired Dice similarity coefficient (DSC) scores, sensitivity, and classification accuracy of 88.8%, 89.4%, and 88.6% for high-grade gliomas. When it comes to segmenting BRATS 2015 BT images, the performance of our proposed CAD framework is on par with existing state-of-the-art methods. However, the accuracy achieved in this study for the classification of BT images has improved upon the accuracy reported in prior studies. Image classification accuracy for BRATS 2015 BT has been improved from 88% to 88.6%.

show abstract

“…Climate change is currently causing changes in the distribution and abundance of many fish stocks that support fisheries, leading to overfishing and conflicts resulting from changes in fisheries access and distribution of fishery benefits. As usual, if the trade continues, these problems are likely to worsen, with 80 percent of the world's reserves being overfished by the middle of the next decade [10][11][12][13]. More than 80 percent of the world's catch comes from stocks without formal inventory valuation, making it difficult to implement strong management forms.…”

Section: Related Workmentioning

confidence: 99%

“…This article discusses the two methods: The Differentiation in Differentiation (DID) method and optimal artificial neural networks. Also, it will examine the impact of each of the existing factors on economic productivity and then compare the results based on statistical criteria [10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Differentiation in Differentiation Method and Neural Network to Investigate Different Criteria of Economic Productivity

Amiri

Raghibnezhad

et al. 2022

IJPTE

View full text Add to dashboard Cite

Economic productivity is one of the most important concepts in economics. Increasing economic productivity will boost a society. This study intends to compare the impact of different criteria on the economic productivity of Iranian factories with differential methods and neural networks. The model estimation results using the difference-in-difference method show that exports have a significant positive effect on productivity growth. The model estimation results using the neural network method show that export has a significant positive effect on productivity growth. The presentation of export development variables in two methods of difference in difference and neural networks showed that the level of productivity could be increased well according to the predictability of the neural network.

show abstract

Classifying tumor brain images using parallel deep learning algorithms

Cited by 20 publications

References 32 publications

Design and assessment of improved Convolutional Neural Network based brain tumor segmentation and classification system

Design and assessment of improved Convolutional Neural Network based brain tumor segmentation and classification system

Clinical Decision Support Framework for Segmentation and Classification of Brain Tumor MRIs Using a U-Net and DCNN Cascaded Learning Algorithm

Differentiation in Differentiation Method and Neural Network to Investigate Different Criteria of Economic Productivity

Contact Info

Product

Resources

About