Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques

Ahuja, Sakshi; Panigrahi, Bijaya Ketan; Gandhi, Tapan Kumar

doi:10.1016/j.mlwa.2021.100212

Cited by 36 publications

(12 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be observed from Table 6 that the proposed brain tumor detection method achieves a superior performance with M-SVM classification. [28] VGG19 & image augmentation 94.58% Gumaei et al [31] Regularized Extreme Learning MAchine 94.23% Swati et al [32] Fine-tuned VGG19 94.82% Kumar et al [33] ResNet50 & Global Average Pooling 97.48% Cheng et al [48] Linear discriminant analysis (LDA) 93.60% Badza et al [49] CNN 96.50% Tripathi et al [50] SVM 94.63% Ahuja et al [51] DarkNet-53 98.15% Noreen et al [52] InceptionV3 & ensemble of KNN, SVM & RF 94.34% Bodapati et al [53] Two channel DNN 97.23% Anaraki et al [54] CNN & Genetic Algorithm 94.20% Deepak et al [55] GoogleNet 97.10% Proposed Method 17-layered CNN, MobileNetV2 & M-SVM 98.92%…”

Section: Figshare Dataset Resultsmentioning

confidence: 99%

Multi-Modal Brain Tumor Detection Using Deep Neural Network and Multiclass SVM

2022

View full text Add to dashboard Cite

Background and Objectives: Clinical diagnosis has become very significant in today’s health system. The most serious disease and the leading cause of mortality globally is brain cancer which is a key research topic in the field of medical imaging. The examination and prognosis of brain tumors can be improved by an early and precise diagnosis based on magnetic resonance imaging. For computer-aided diagnosis methods to assist radiologists in the proper detection of brain tumors, medical imagery must be detected, segmented, and classified. Manual brain tumor detection is a monotonous and error-prone procedure for radiologists; hence, it is very important to implement an automated method. As a result, the precise brain tumor detection and classification method is presented. Materials and Methods: The proposed method has five steps. In the first step, a linear contrast stretching is used to determine the edges in the source image. In the second step, a custom 17-layered deep neural network architecture is developed for the segmentation of brain tumors. In the third step, a modified MobileNetV2 architecture is used for feature extraction and is trained using transfer learning. In the fourth step, an entropy-based controlled method was used along with a multiclass support vector machine (M-SVM) for the best features selection. In the final step, M-SVM is used for brain tumor classification, which identifies the meningioma, glioma and pituitary images.Results: The proposed method was demonstrated on BraTS 2018 and Figshare datasets. Experimental study shows that the proposed brain tumor detection and classification method outperforms other methods both visually and quantitatively, obtaining an accuracy of 97.47% and 98.92%, respectively. Finally, we adopt the eXplainable Artificial Intelligence (XAI) method to explain the result. Conclusion: Our proposed approach for brain tumor detection and classification has outperformed prior methods. These findings demonstrate that the proposed approach obtained higher performance in terms of both visually and enhanced quantitative evaluation with improved accuracy.

show abstract

Section: Figshare Dataset Resultsmentioning

confidence: 99%

Multi-Modal Brain Tumor Detection Using Deep Neural Network and Multiclass SVM

2022

View full text Add to dashboard Cite

show abstract

“…However, there is a limited number of labeled datasets in the field of medical imaging. To solve this problem, data augmentation methods aiming to reproduce the data synthetically are used [48,49]. Therefore, in order to avoid the above-mentioned problems, in the preprocessing stage, original X-ray images were synthetically augmented by rotation, scaling and mirroring methods from geometric transformation-based data augmentation techniques [50].…”

Section: Preprocessingmentioning

confidence: 99%

A Novel Deep Transfer Learning-Based Approach for Automated Pes Planus Diagnosis Using X-ray Image

et al. 2023

View full text Add to dashboard Cite

Pes planus, colloquially known as flatfoot, is a deformity defined as the collapse, flattening or loss of the medial longitudinal arch of the foot. The first standard radiographic examination for diagnosing pes planus involves lateral and dorsoplantar weight-bearing radiographs. Recently, many artificial intelligence-based computer-aided diagnosis (CAD) systems and models have been developed for the detection of various diseases from radiological images. However, to the best of our knowledge, no model and system has been proposed in the literature for automated pes planus diagnosis using X-ray images. This study presents a novel deep learning-based model for automated pes planus diagnosis using X-ray images, a first in the literature. To perform this study, a new pes planus dataset consisting of weight-bearing X-ray images was collected and labeled by specialist radiologists. In the preprocessing stage, the number of X-ray images was augmented and then divided into 4 and 16 patches, respectively in a pyramidal fashion. Thus, a total of 21 images are obtained for each image, including 20 patches and one original image. These 21 images were then fed to the pre-trained MobileNetV2 and 21,000 features were extracted from the Logits layer. Among the extracted deep features, the most important 1312 features were selected using the proposed iterative ReliefF algorithm, and then classified with support vector machine (SVM). The proposed deep learning-based framework achieved 95.14% accuracy using 10-fold cross validation. The results demonstrate that our transfer learning-based model can be used as an auxiliary tool for diagnosing pes planus in clinical practice.

show abstract

“…This highlighted the salient feature information and empowered the network to eliminate noisy and irrelevant feature responses. Sakshi et al 35 utilized pre‐trained DarkNets to classify T1WCE MRI images into the tumor and non‐tumor classes. Aboelenein et al 36 proposed a Hybrid Two‐Track U‐Net (HTTU‐Net) for segmenting the tumor cells of the brain.…”

Section: Related Workmentioning

confidence: 99%

MAEU‐NET: A novel supervised architecture for brain tumor segmentation

Kumar,

Biswal

2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

A brain tumor is an abnormal growth of cells that damages the neural system and may lead to severe conditions. These cells are irregular in shape and size, and as a result, the manual analysis of these cells from magnetic resonance (MR) images is a cumbersome and time‐consuming task. To alleviate these issues, a novel U‐Net inspired MAEU‐Net (Multiscale context Aggregation and Edge activation U‐Net) is implemented to detect the brain tumor pixels from MR images more precisely. The encoder block of the proposed model is improved by integrating with multiscale feature aggregation and convolution block attention modules (CBAM) enabling the model to extract both pertinent low‐level and high‐level features. Further, the extracted features are subjected to a parallel pooling module to elevate the features that extract the tumor pixels. In addition to this, the output features of the last encoder are fed to a parallel dilated context aggregation module to mitigate the hyper‐parameter size and further elevate the receptive field strength of the proposed model. Apart from this, edge‐enhanced modules are incorporated with skip connections which concatenate the feature maps of the decoder with respective edge‐enhanced encoder feature maps. As a result, this module increases the aspect ratio and reduces blurry edge problems. To illustrate the performance of the proposed MAEU‐Net, it is trained and tested using Kaggle LGG, BraTS 2018, and BraTS 2021 publicly available datasets. The proposed model outperformed the previously existing models by achieving the test loss, dice coefficient, sensitivity, and specificity of 0.0590, 0.901, 0.942, and 0.998, respectively. Simultaneously, the proposed model is quantitatively analyzed by performing ablation and comparative studies and presented that the proposed MAEU‐Net is superior to other previous existing models like U‐Net++, SegNet, etc.

show abstract

Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques

Cited by 36 publications

References 39 publications

Multi-Modal Brain Tumor Detection Using Deep Neural Network and Multiclass SVM

Multi-Modal Brain Tumor Detection Using Deep Neural Network and Multiclass SVM

A Novel Deep Transfer Learning-Based Approach for Automated Pes Planus Diagnosis Using X-ray Image

MAEU‐NET: A novel supervised architecture for brain tumor segmentation

Contact Info

Product

Resources

About