Brain Tumor Classification and Segmentation Using Transfer Learning from MRI Images

Segmentation and classification of brain tumor are time-consuming and challenging chore in clinical image processing. Magnetic Resonance Imaging (MRI) offers more information related to human soft tissues that assists in diagnosing brain tumor. Precise segmentation of the MRI images is vital to diagnose brain tumor by means of computer-aided medical tools. Afterwards suitable segmentation of MRI brain tumor images, tumor classification is performed that is a hard chore owing to complications. Therefore, Gannet Aquila Optimization Algorithm_deep maxout network (GAOA_DMN) and GAOA_K-Net+speech enhancement generative adversarial network (GAOA_K-Net+Segan) is presented for classification and segmentation of brain tumor utilizing MRI images. Here, pre-processing phase performs noise removal from input image utilizing the Laplacian filter and also the region of interest (ROI) extraction is also carried out. Then, segmentation of brain tumor is conducted by K-Net+Segan, which is combined by Motyka similarity. However, K-Net+Segan for segmentation is trained by GAOA that is an amalgamation of Gannet Optimization Algorithm (GOA) and Aquila Optimizer (AO). From segmented image, features are extracted for performing classification phase. At last, brain tumor classification is conducted by DMN, which is tuned by GAOA and thus, output is obtained. Furthermore, GAOA_K-Net+Segan obtained better outcomes in terms of segmentation accuracy whereas devised GAOA_DMN achieved maximum accuracy, true negative rate (TNR) and true positive rate (TPR) of 92.7%, 94.5% and 91.5%.

Brain tumor is the phenomenal growth of abnormal tissues in the human brain. A malignant tumor is known as a cancerous cell, and it is the major cause of death among people across the globe. Nowadays, the detection and classification of brain tumors from Magnetic Resonance Images (MRI) is a very crucial task. This chapter addresses various computing methods such as Edge Detection (ED), feature extraction, and classification techniques for the detection and classification of brain tumor regions from MRI datasets. Initially, MRI images are collected, and then various pre-processing steps such as filtering and edge detection are applied. Then, different edge detection methods such as Sobel ED, Robert’s ED, Prewitt ED, Canny ED, Laplacian ED, and Laplacian of Gaussian (LoG) with sigma 3 are applied for the MRI datasets. Subsequently, segmentation techniques are applied for detecting tumor regions from MRI, and essential features are extracted using Discrete Wavelet Transform (DWT) method. Otsu’s thresholding and K-means clustering segmentation methods are used for the investigation. Further, the support vector machines (SVMs), Naïve Bayes (NB), K-nearest neighbors (KNN), Back Propagation Neural Network (BPNN), and feedforward neural networks (FFNN) classifiers are employed for the MRI classification purpose. The experiments are 146conducted using the brain tumor dataset in the MATLAB 2019a software environment. The experimental results are analyzed in multiple dimensions, and it shows that the SVM with Otsu’s thresholding method exhibits better performance with 86.11% accuracy during the classification.

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

A new clinical diagnosis system for detecting brain tumor using integrated ResNet_Stacking with XGBoost

Brain tumors are abnormal tissue growth characterized by uncontrolled and rapid cell proliferation. Early detection of brain tumors is critical for improving patient outcomes, and magnetic resonance imaging (MRI) has become the most widely used modality for diagnosis due to its superior image quality and non-invasive nature. Deep learning, a subset of artificial intelligence, has revolutionized automated medical image analysis by enabling highly accurate and efficient classification tasks. The objective of this study is to develop a robust and effective brain tumor detection system using MRI images through transfer learning. A diagnostic framework is constructed based on convolutional neural networks (CNN), integrating both a custom sequential CNN model and pretrained architectures, namely VGG16 and EfficientNetB4, trained on the ImageNet dataset. Prior to model training, image preprocessing techniques are applied to enhance feature extraction and overall model performance. This research addresses the common challenge of limited MRI datasets by combining EfficientNetB4 with targeted preprocessing, data augmentation, and an appropriate optimizer selection strategy. The proposed methodology significantly reduces overfitting, improves classification accuracy on small datasets, and remains computationally efficient. Unlike previous studies that focus solely on CNN or VGG16 architectures, this work systematically compares multiple transfer learning models and demonstrates the superiority of EfficientNetB4. Experimental results on the Br35H dataset show that EfficientNetB4, combined with the ADAM optimizer, achieves outstanding performance with an accuracy of 99.66%, precision of 99.68%, and an F1-score of 100%. The findings confirm that integrating EfficientNetB4 with dataset-specific preprocessing and transfer learning provides a highly accurate and cost-effective solution for brain tumor classification, facilitating rapid and reliable medical diagnosis.

The classification of brain tumor is a very important section of medical diagnosis because correct and early diagnosis can greatly enhance the outcome of the patient. To aid in automated and dependable diagnostic methods, this paper examines the efficacy of already trained deep learning model to classify brain magnetic resonance imaging (MRI) scans into four categories, namely, pituitary tumor, meningioma, glioma, and no tumor. This was done using a publicly available set of 7,023 brain MRI images. DenseNet121, ResNet50, Xception and MobileNet four advanced convolutional neural network (CNN) models were also fine-tuned with transfer learning, as well as image preprocessing and data augmentation methods. Transfer learning was used to facilitate effective model adaptation with a low computation complexity and improved classification. According to the experimental findings, DenseNet121 performed better as it obtained the highest classification accuracy of 98.47% and the highest F1 score of 98.47%. The assessed models presented a high level of generalization and steady performance under a variety of evaluation criteria, which also indicates their possible application in the clinical decision support systems. These encouraging findings, however, need additional performance to improve recall on individual tumor classes, as well as the interpretability of deep-learning predictions in clinical settings. On the whole, the results highlight the great potential of the deep learning and transfer learning methods in medical image analysis, which is an opportunity to establish a more reliable, scalable and efficient solution to diagnosis. The next phase of work will involve diversifying the datasets, enhancing the model explainability, and assessing the performance of AI-oriented healthcare systems in practice to make them more widely adopted.

BrainView: A cloud-based deep learning system for brain image segmentation, tumor detection and visualization.

Brain tumors pose a significant clinical challenge due to their aggressive nature and the complexity of accurate diagnosis. Traditional deep learning models, primarily based on Convolutional Neural Networks (CNNs), have shown promise in tumor segmentation and classification from Magnetic Resonance Imaging (MRI) scans. However, these approaches often struggle with capturing global spatial dependencies, generalizing from limited annotated data, and fine-tuning performance across varying imaging conditions. This paper presents an advanced hybrid framework that combines self-supervised learning, Vision Transformer (ViT), and Quantum Particle Swarm Optimization (QPSO) to enhance segmentation and classification of brain tumors. The methodology begins with preprocessing involving skull stripping, contrast enhancement, and denoising using a Cycle-Consistent Generative Adversarial Network (CycleGAN). Feature representation is learned through a Simple Framework for Contrastive Learning of Visual Representations (SimCLR), followed by segmentation using a DeepLabv3+ architecture with a ViT encoder. Tumor classification is handled by a lightweight ViT model, whose hyperparameters are optimized using QPSO. Evaluation on the Brain Tumor Segmentation (BraTS) 2021 dataset demonstrates a Dice Similarity Coefficient (DSC) of 95.4% and classification accuracy of 96.7%, confirming the robustness and superiority of the proposed approach over conventional methods.

Segmentation and classification of brain tumors from MRI images based on adaptive mechanisms and ELDP feature descriptor

Currently, the radiologist can more accurately identify brain tumours through the development of Computer-Assisted Diagnosis (CAD), Machine Learning and Deep Learning. Recently, Deep Learning (DL) strategies have gained traction as a means to rapidly and accurately construct automated systems for diagnosing and segmenting the image. The standard approach to this issue is to create a custom feature for classification. Most neurological diseases originate from abnormal growth of brain cells, which can compromise brain architecture and even lead to malignant brain tumours. Brain tumour detection and classification algorithms that are both quick and accurate have been the subject of extensive study. This facilitates the straight forward diagnosis of brain tumours using Magnetic Resonance Image (MRI) images. Through Deep Learning (DL) model the diagnosis of brain malignancies in MRI images using Convolutional Neural Network (CNN) is possible by training the data. So, in this paper the brain tumouris predicted byproposing a Hybridfeature extraction technique i.e., tuned CNN model with ResNet150 and U-net.

Brain tumor is a type of cancer which causes abnormal cells growth in the brain. It can be cured if we detect the brain tumor at an early stage. Brain tumor patients often suffer from blood clot, movement control loss, vision loss, behavioral changes, hormone changes, etc. The location, type, and size of the tumor have an effect on the normal functioning of the individual. To examine the size, shape, and location of tumor in the brain, Magnetic Resonance Imaging (MRI) is used. MRI image produces a clear anatomical view of brain and any small abnormality of brain is perceptible by MRI image. Brain tumor classification, detection, and segmentation are huge concerns of researchers. Artificial Intelligence (AI)-based methods can be used to detect brain tumor. Among various deep learning-based algorithms CNN acquired a better position in image classification. CNN classification accuracy depends on some network parameters as convolutional filters, rectification functions, polling functions, and iteration numbers, etc. It is a problem to determine effective values of the convolution filter size, number, and convolution stride for better accuracy in classification. CNN has the capabilities to produce and learn effective features on large datasets. In this paper, we are using convolutional neural network model which takes the feature maps preprocessed to classify the MRI brain image datasets. This paper uses deep learning which processes NIFTI images and creates 3D convolutional neural network, which can be trained to detect and segment structures if corresponding ground truth labels are provided for training.

Magnetic Resonance Imaging (MRI) might be a problematic assignment for tumor fluctuation and complexity because of brain image classification. This work presents the brain tumor classification system using Convolutional Gated Recurrent Neural Network (CGRNN) algorithm based on MRI images. The proposed tumor recognition framework comprises of four stages, to be specific preprocessing, feature extraction, segmentation and classification. Extraction of identified tumor framework features was accomplished utilizing Gray Level Co-occurrence Matrix (GLCM) strategy. At long last, the Convolutional Gated Recurrent Neural Network Classifier has been created to perceive various kinds of brain disease. The proposed framework can be effective in grouping these models and reacting to any variation from the abnormality. The entire framework is isolated into different types of phases: the Learning/Training Phase and the Recognition/Test Phase. A CGRNN classifier under the scholarly ideal separation measurements is utilized to decide the chance of every pixel having a place with the foreground (tumor) and the background. MATLAB software is used in the development of the simulation of the proposed system. The suggested method's simulation results show that the analysis of brain tumours is stable. It shows that the proposed brain tumor classifications are superior to those from brain MRIs than existing brain tumor classifications. The overall accuracy of the proposed system is 98.45%.

Brain tumor detection and segmentation from Magnetic Resonance Imaging (MRI) images is being one of the emerging fields in the biomedicine. A formidable undertaking in brain tumor surgery, medical care, treatment programme and quantitative assessment of MRI images is to precisely diagnose its location and extent. Recently, the convolutional neural network (CNN) based detection and segmentation method on brain tumor MRI images is being one of the emerging fields in the medical imaging as an automatic clinic treatment and evaluation solution. In this article, we put forward a brand new quadruplet loss in CNN framework, which achieves higher accuracy in brain tumor detection and segmentation than other pairwise loss and triplet loss methods. By applying the proposed quadruplet loss to the original L2Net CNN architecture leads to a more compact descriptor named QuadrupletNet. From our experiments, QuadrupletNet shows higher performance than other state-of-the-art loss functions e.g., the Triplet loss, as indicated in experiments on Multimodal Brain Tumor Image Segmentation (BRATS 2018) datasets, and on our own collected MRI brain tumor datasets (named MBTD).

In this paper, we present a study on brain tumor detection using the VGG-16 model, a convolutional neural network known to be effective for computer vision tasks. This study proposes an enhanced VGG-16 model by modifying its architecture with batch normalization and dropout layers to improve generalization and prevent overfitting. Unlike previous studies that directly applied VGG-16, this research introduces architectural changes to adapt the model for more effective multi-class classification of brain tumors. The objective of this study is to accurately determine the presence or absence of a brain tumor by classifying magnetic resonance imaging (MRI) images. The dataset used consists of MRI images of brain tumors classified into two classes: No (no tumor) and YES (tumor). The methodology includes environment setup, data import and preprocessing, VGG16 model construction, and performance evaluation using metrics such as accuracy, precision, and recall. The results show an accuracy of about 98.47% on the validation set and 98.32% on the test set, indicating that the VGG-16 model has the potential to assist medical professionals in diagnosing brain tumors. This study contributes to the field of medical image analysis and provides ideas for applying deep learning to brain tumor diagnosis.

Brain tumor segmentation and classification (BTSC) from magnetic resonance imaging (MRI) is an important procedure in medical predictions, improving the precision and speed of treatment plans. However, the automatic detection of tumors is challenging because of similar intensity patterns, indistinct boundaries, and varying tumor shapes. This paper suggests a novel deep transfer learning (DTL) methodology to accurately segment and detect brain tumors (BTs) from MRI. Initially, the denoising is carried out using improved anisotropic diffusion filtering (IADF), and then dataset diversity is enhanced by applying data augmentation. Afterwards, a Swin Transformer U-shaped network with dense connections (STUNetDS) is utilized for segmenting the tumor, and finally, Kullback–Leibler loss with Optimized InceptionResNetv2 (KLOINRNetv2) is used for the classification of the tumor. The system uses the Multi-Strategy Improved Kookaburra Optimization (MSIKBO) algorithm for tuning the network parameters. The model achieves 98.67% accuracy for detecting and classifying BTs from the Kaggle BraTS2019 dataset, higher compared to the baseline techniques. The reliable and scalable solutions are offered by the proposed model, making it more suitable for automated tumor assessment in clinical applications.