RESUMO
OBJECTIVE: Detecting brain tumor using the segmentation technique is a big challenge for researchers and takes a long time in medical image processing. Magnetic resonance image analysis techniques facilitate the accurate detection of tissues and abnormal tumors in the brain. The size of a brain tumor can vary with the individual and the specifics of the tumor. Radiologists face great difficulty in diagnosing and classifying brain tumors. METHOD: This paper proposed a hybrid model-based convolutional neural network with a stationary wavelet trans-form named "CNN-SWT" to segment brain tumors using MR brain big data. We utilized 7 layers for classification in the proposed model that include 3 convolutional and 3 ReLU. Firstly, the input MR image is divided into multiple patches, and then the central pixel value of each patch is provided to the CNN-SWT. Secondly, the pre-processing stage is per-formed using the mean filter to remove the noise. Then the convolution neural network-layer approach is utilized to segment brain tumors. After segmentation, robust feature extraction such as information-extraction methods is used for the feature extraction process. Finally, a CNN-based hybrid scheme based on the stationary wavelet transform technique is used to detect tumors using MR brain images. MATERIALS: These experiments were obtained using 11500 MR brain images data from the hospital national of oncology. RESULTS: It was proved that the proposed hybrid achieved a high classification accuracy of (98.7 %) as compared with existing methods. CONCLUSION: The advantage of the hybrid novelty of the model and the ability to detect the tumor area achieved excellent overall performance using different values.
RESUMO
Brain tumor is one of the most aggressive diseases nowadays, resulting in a very short life span if it is diagnosed at an advanced stage. The treatment planning phase is thus essential for enhancing the quality of life for patients. The use of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumors is extremely widespread, but the manual interpretation of large amounts of images requires considerable effort and is prone to human errors. Hence, an automated method is necessary to identify the most common brain tumors. Convolutional Neural Network (CNN) architectures are successful in image classification due to their high layer count, which enables them to conceive the features effectively on their own. The tuning of CNN hyperparameters is critical in every dataset since it has a significant impact on the efficiency of the training model. Given the high dimensionality and complexity of the data, manual hyperparameter tuning would take an inordinate amount of time, with the possibility of failing to identify the optimal hyperparameters. In this paper, we proposed a Bayesian Optimization-based efficient hyperparameter optimization technique for CNN. This method was evaluated by classifying 3064 T-1-weighted CE-MRI images into three types of brain tumors (Glioma, Meningioma, and Pituitary). Based on Transfer Learning, the performance of five well-recognized deep pre-trained models is compared with that of the optimized CNN. After using Bayesian Optimization, our CNN was able to attain 98.70% validation accuracy at best without data augmentation or cropping lesion techniques, while VGG16, VGG19, ResNet50, InceptionV3, and DenseNet201 achieved 97.08%, 96.43%, 89.29%, 92.86%, and 94.81% validation accuracy, respectively. Moreover, the proposed model outperforms state-of-the-art methods on the CE-MRI dataset, demonstrating the feasibility of automating hyperparameter optimization.
RESUMO
The process of diagnosing brain tumors is very complicated for many reasons, including the brain's synaptic structure, size, and shape. Machine learning techniques are employed to help doctors to detect brain tumor and support their decisions. In recent years, deep learning techniques have made a great achievement in medical image analysis. This paper proposed a deep wavelet autoencoder model named "DWAE model", employed to divide input data slice as a tumor (abnormal) or no tumor (normal). This article used a high pass filter to show the heterogeneity of the MRI images and their integration with the input images. A high median filter was utilized to merge slices. We improved the output slices' quality through highlight edges and smoothened input MR brain images. Then, we applied the seed growing method based on 4-connected since the thresholding cluster equal pixels with input MR data. The segmented MR image slices provide two two-layer using the proposed deep wavelet auto-encoder model. We then used 200 hidden units in the first layer and 400 hidden units in the second layer. The softmax layer testing and training are performed for the identification of the MR image normal and abnormal. The contribution of the deep wavelet auto-encoder model is in the analysis of pixel pattern of MR brain image and the ability to detect and classify the tumor with high accuracy, short time, and low loss validation. To train and test the overall performance of the proposed model, we utilized 2500 MR brain images from BRATS2012, BRATS2013, BRATS2014, BRATS2015, 2015 challenge, and ISLES, which consists of normal and abnormal images. The experiments results show that the proposed model achieved an accuracy of 99.3%, loss validation of 0.1, low FPR and FNR values. This result demonstrates that the proposed DWAE model can facilitate the automatic detection of brain tumors.