Brain Tumor Imaging Research Articles

Classification and Segmentation of MRI Images of Brain Tumors Using Deep Learning and Hybrid Approach

Manual prediction of brain tumors is a time-consuming and subjective task, reliant on radiologists' expertise, leading to potential inaccuracies. In response, this study proposes an automated solution utilizing a Convolutional Neural Network (CNN) for brain tumor classification, achieving an impressive accuracy of 98.89%. Following classification, a hybrid approach, integrating graph-based and threshold segmentation techniques, accurately locates the tumor region in magnetic resonance (MR) brain images across sagittal, coronal, and axial views. Comparative analysis with existing research papers validates the effectiveness of the proposed method, and similarity coefficients, including a Bfscore of 1 and a Jaccard similarity of 93.86%, attest to the high concordance between segmented images and ground truth.

Classification of brain tumors based on magnetic resonance imaging (MRI) using deep learning models

Nowadays, With the advancements in medical care and the improvement in global living standards, there has been a continuous increase in the average life expectancy of people around the world, and the aging problem is constantly aggravated, brain tumors have become a growing global health problem. The project aims to use deep learning models to classify magnetic resonance imaging (MRI) images of brain tumors. By constructing convolutional neural network model, image feature extraction and classification are carried out. Data preprocessing, data enhancement, Adaptive Moment Estimation (Adam) are used to improve the model performance, plot the accuracy curve and generate the confusion matrix, and visualize the classification performance of the model. Possible future tasks may include optimizing the model architecture and expanding the exploration of data augmentation techniques to bolster the model's performance, while also further investigating the model's interpretability to understand the internal mechanisms of the model when making predictions. In addition, the project has great application potential, and the model can be applied to the actual clinical assisted diagnosis system, which has good scalability and application prospect. By using deep learning model and related technologies, the accuracy of brain tumor classification can be improved in clinical diagnosis, and better diagnosis and treatment services can be provided for the majority of brain tumor patients.

A robust approach for multi-type classification of brain tumor using deep feature fusion.

Brain tumors can be classified into many different types based on their shape, texture, and location. Accurate diagnosis of brain tumor types can help doctors to develop appropriate treatment plans to save patients' lives. Therefore, it is very crucial to improve the accuracy of this classification system for brain tumors to assist doctors in their treatment. We propose a deep feature fusion method based on convolutional neural networks to enhance the accuracy and robustness of brain tumor classification while mitigating the risk of over-fitting. Firstly, the extracted features of three pre-trained models including ResNet101, DenseNet121, and EfficientNetB0 are adjusted to ensure that the shape of extracted features for the three models is the same. Secondly, the three models are fine-tuned to extract features from brain tumor images. Thirdly, pairwise summation of the extracted features is carried out to achieve feature fusion. Finally, classification of brain tumors based on fused features is performed. The public datasets including Figshare (Dataset 1) and Kaggle (Dataset 2) are used to verify the reliability of the proposed method. Experimental results demonstrate that the fusion method of ResNet101 and DenseNet121 features achieves the best performance, which achieves classification accuracy of 99.18 and 97.24% in Figshare dataset and Kaggle dataset, respectively.

A Dendritic Architecture‐Based Deep Learning for Tumor Detection

Brain tumor detection typically involves classifying various tumor types. Traditional classifiers, based on the McCulloch‐Pitts model, have faced criticism due to their oversimplified structure and limited capabilities in detecting brain tumor images with complex features. In this study, we propose a multiclassification model inspired by dendritic architectures in neurons, which leverages synaptic and dendritic nonlinear information processing capabilities. Experimental results using brain tumor detection datasets demonstrate that our proposed model outperforms other state‐of‐the‐art models across all evaluation metrics. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

Deep learning applications in MRI for brain tumor detection and image segmentation

Deep learning holds great potential in the field of MRI applications. By leveraging its advanced algorithms and neural networks, it can effectively analyze and interpret intricate patterns in medical images, aiding in precise disease detection, segmentation, and classification. Integrating deep learning techniques with MRI technology is expected to revolutionize radiology practice, facilitating enhanced diagnostic accuracy and customized treatment strategies, ultimately leading to improved patient outcomes. This article provides an overview of of the latest advancements in deep learning techniques applied to magnetic resonance imaging, specifically focusing on brain tumor detection and segmentation. The study examines eight different deep learning methods, including a multi-scale convolutional neural network, U-Net-based fully convolutional networks, cascaded anisotropic convolutional neural networks, missing modality-based tumor segmentation, Hough-CNN for deep brain region segmentation, k-Space deep learning for accelerated MRI, Multi-level Kronecker Convolutional Neural Network, and a heuristic approach for clinical brain tumor segmentation. Each method is analyzed, highlighting its specific techniques, advantages, and limitations. The comparative performance of these methods in terms of accuracy and efficiency, addressing key factors such as computational requirements, training time, and robustness, was discussed in this article. By assessing the merits and limitations of different approaches, this review seeks to offer valuable perspectives on effective utilization of deep learning techniques in clinical MRI settings for detecting and delineating brain tumors.

Brain Tumor Imaging without Gadolinium-based Contrast Agents: Feasible or Fantasy?

Gadolinium-based contrast agents (GBCAs) form the cornerstone of current primary brain tumor MRI protocols at all stages of the patient journey. Though an imperfect measure of tumor grade, GBCAs are repeatedly used for diagnosis and monitoring. In practice, however, radiologists will encounter situations where GBCA injection is not needed or of doubtful benefit. Reducing GBCA administration could improve the patient burden of (repeated) imaging (especially in vulnerable patient groups, such as children), minimize risks of putative side effects, and benefit costs, logistics, and the environmental footprint. On the basis of the current literature, imaging strategies to reduce GBCA exposure for pediatric and adult patients with primary brain tumors will be reviewed. Early postoperative MRI and fixed-interval imaging of gliomas are examples of GBCA exposure with uncertain survival benefits. Half-dose GBCAs for gliomas and T2-weighted imaging alone for meningiomas are among options to reduce GBCA use. While most imaging guidelines recommend using GBCAs at all stages of diagnosis and treatment, non-contrast-enhanced sequences, such as the arterial spin labeling, have shown a great potential. Artificial intelligence methods to generate synthetic postcontrast images from decreased-dose or non-GBCA scans have shown promise to replace GBCA-dependent approaches. This review is focused on pediatric and adult gliomas and meningiomas. Special attention is paid to the quality and real-life applicability of the reviewed literature.

Brain Tumor Imaging in Adolescents and Young Adults: 2021 WHO Updates for Molecular-based Tumor Types.

Published in 2021, the fifth edition of the World Health Organization (WHO) classification of tumors of the central nervous system (CNS) introduced new molecular criteria for tumor types that commonly occur in either pediatric or adult age groups. Adolescents and young adults (AYAs) are at the intersection of adult and pediatric care, and both pediatric-type and adult-type CNS tumors occur at that age. Mortality rates for AYAs with CNS tumors have increased by 0.6% per year for males and 1% per year for females from 2007 to 2016. To best serve patients, it is crucial that both pediatric and adult radiologists who interpret neuroimages are familiar with the various pediatric- and adult-type brain tumors and their typical imaging morphologic characteristics. Gliomas account for approximately 80% of all malignant CNS tumors in the AYA age group, with the most common types observed being diffuse astrocytic and glioneuronal tumors. Ependymomas and medulloblastomas also occur in the AYA population but are seen less frequently. Importantly, biologic behavior and progression of distinct molecular subgroups of brain tumors differ across ages. This review discusses newly added or revised gliomas in the fifth edition of the CNS WHO classification, as well as other CNS tumor types common in the AYA population.

Improved diagnostic confidence and tumor type prediction in adult-type diffuse glioma by multimodal imaging including DCE perfusion and diffusion kurtosis mapping – A standardized multicenter study

Background and purposeTo evaluate the feasibility of a multimodal approach involving dynamic contrast-enhanced (DCE) perfusion imaging and diffusion kurtosis imaging (DKI) in the preoperative imaging of brain tumors in a multicenter setting, and to evaluate the effect on diagnostic confidence and accuracy for tumor grade and type prediction. Materials and MethodsOne hundred and thirty-three patients with brain tumors were imaged in six hospitals with a standardized multimodal protocol. Standard imaging and six parameter maps derived from DCE and DKI sequences were reviewed off-site by two independent readers. Image quality and diagnostic confidence were evaluated in qualitative analyses. Quantitative analyses were performed to assess diagnostic accuracy and the performance of DKI and DCE parameters for tumor grade differentiation and molecular tumor type determination. ResultsStandardized acquisition of DCE and DKI maps was feasible with excellent image quality. Diagnostic confidence was significantly improved from 85 % to 96 % (p = 0.0005) by additional review of the DCE and DKI maps. The combination of mean kurtosis and CBV was particularly advantageous for differentiating low-grade and high-grade glioma, oligodendroglial vs. astrocytic, and IDH1/2 wild type vs. mutated tumors. ConclusionA multimodal imaging approach with DCE and DKI improves diagnostic confidence and yields higher diagnostic accuracy for predicting tumor grade and type in adult-type glioma.

Intraoperative in vivo confocal laser endomicroscopy imaging at glioma margins: can we detect tumor infiltration?

Confocal laser endomicroscopy (CLE) is a US Food and Drug Administration-cleared intraoperative real-time fluorescence-based cellular resolution imaging technology that has been shown to image brain tumor histoarchitecture rapidly in vivo during neuro-oncological surgical procedures. An important goal for successful intraoperative implementation is in vivo use at the margins of infiltrating gliomas. However, CLE use at glioma margins has not been well studied. Matching in vivo CLE images and tissue biopsies acquired at glioma margin regions of interest (ROIs) were collected from 2 institutions. All images were reviewed by 4 neuropathologists experienced in CLE. A scoring system based on the pathological features was implemented to score CLE and H&E images from each ROI on a scale from 0 to 5. Based on the H&E scores, all ROIs were divided into a low tumor probability (LTP) group (scores 0-2) and a high tumor probability (HTP) group (scores 3-5). The concordance between CLE and H&E scores regarding tumor probability was determined. The intraclass correlation coefficient (ICC) and diagnostic performance were calculated. Fifty-six glioma margin ROIs were included for analysis. Interrater reliability of the scoring system was excellent when used for H&E images (ICC [95% CI] 0.91 [0.86-0.94]) and moderate when used for CLE images (ICC [95% CI] 0.69 [0.40-0.83]). The ICCs (95% CIs) of the LTP group (0.68 [0.40-0.83]) and HTP group (0.68 [0.39-0.83]) did not differ significantly. The concordance between CLE and H&E scores was 61.6%. The sensitivity and specificity values of the scoring system were 79% and 37%. The positive predictive value (PPV) and negative predictive value were 65% and 53%, respectively. Concordance, sensitivity, and PPV were greater in the HTP group than in the LTP group. Specificity was higher in the newly diagnosed group than in the recurrent group. CLE may detect tumor infiltration at glioma margins. However, it is not currently dependable, especially in scenarios where low probability of tumor infiltration is expected. The proposed scoring system has excellent intrinsic interrater reliability, but its interrater reliability is only moderate when used with CLE images. These results suggest that this technology requires further exploration as a method for consistent actionable intraoperative guidance with high dependability across the range of tumor margin scenarios. Specific-binding and/or tumor-specific fluorophores, a CLE image atlas, and a consensus guideline for image interpretation may help with the translational utility of CLE.

A hybrid deep CNN model for brain tumor image multi-classification

The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-classification system for brain malignancies. This article aims to leverage a deep convolutional neural network (CNN) to enhance early detection and presents three distinct CNN models designed for different types of classification tasks. The first CNN model achieves an impressive detection accuracy of 99.53% for brain tumors. The second CNN model, with an accuracy of 93.81%, proficiently categorizes brain tumors into five distinct types: normal, glioma, meningioma, pituitary, and metastatic. Furthermore, the third CNN model demonstrates an accuracy of 98.56% in accurately classifying brain tumors into their different grades. To ensure optimal performance, a grid search optimization approach is employed to automatically fine-tune all the relevant hyperparameters of the CNN models. The utilization of large, publicly accessible clinical datasets results in robust and reliable classification outcomes. This article conducts a comprehensive comparison of the proposed models against classical models, such as AlexNet, DenseNet121, ResNet-101, VGG-19, and GoogleNet, reaffirming the superiority of the deep CNN-based approach in advancing the field of brain tumor classification and early detection.

Multimodal brain tumor image segmentation based on DenseNet.

A brain tumor magnetic resonance image processing algorithm can help doctors to diagnose and treat the patient's condition, which has important application significance in clinical medicine. This paper proposes a network model based on the combination of U-net and DenseNet to solve the problems of class imbalance in multi-modal brain tumor image segmentation and the loss of effective information features caused by the integration of features in the traditional U-net network. The standard convolution blocks of the coding path and decoding path on the original network are improved to dense blocks, which enhances the transmission of features. The mixed loss function composed of the Binary Cross Entropy Loss function and the Tversky coefficient is used to replace the original single cross-entropy loss, which restrains the influence of irrelevant features on segmentation accuracy. Compared with U-Net, U-Net++, and PA-Net the algorithm in this paper has significantly improved the segmentation accuracy, reaching 0.846, 0.861, and 0.782 respectively in the Dice coefficient index of WT, TC, and ET. The PPV coefficient index has reached 0.849, 0.883, and 0.786 respectively. Compared with the traditional U-net network, the Dice coefficient index of the proposed algorithm exceeds 0.8%, 4.0%, and 1.4%, respectively, and the PPV coefficient index in the tumor core area and tumor enhancement area increases by 3% and 1.2% respectively. The proposed algorithm has the best performance in tumor core area segmentation, and its Sensitivity index has reached 0.924, which has good research significance and application value.

68Ga]Ga-FAPI PET/CT in brain tumors: comparison with [18F]F-FDG PET/CT.

To investigate the feasibility of [68Ga]Ga-FAPI PET/CT in brain tumor imaging and to compare it with [18F]F-FDG PET/CT. 25 patients with MRI-suspected brain tumors were included in the study. They underwent whole body [18F]F-FDG PET/CT and [68Ga]Ga-FAPI PET/CT and brain scans. The target-to-background ratio (TBR) of brain tumors was calculated with the background of surrounding normal brain tissues uptake. The SUVmax and TBR of [18F]F-FDG PET/CT and [68Ga]Ga-FAPI PET/CT were compared. Additionally, the correlation between the uptake of the tracer by lesions with the greatest diameter of the lesion, the breadth of the oedema band, and the enhancement scores of the MRI enhancement scans was analyzed. [68Ga]Ga-FAPI PET/CT was superior to [18F]F-FDG PET/CT for lesion detection, especially for brain metastases. Among gliomas, only high-grade gliomas uptake [68Ga]Ga-FAPI. Compared with [18F]F-FDG PET/CT, [68Ga]Ga-FAPI PET/CT had a lower SUVmax but a significantly better TBR. On [68Ga]Ga-FAPI PET/CT, the TBR may be associated with brain tumor blood-brain barrier disruption. [68Ga]Ga-FAPI PET/CT is a promising imaging tool for the assessment of brain tumors. Lack of physiological uptake of [68Ga]Ga-FAPI in normal brain parenchyma results in high TBR values, leading to better visualization of lesions and contributing to subsequent targeted therapy studies. Clinical utility of [68Ga]Ga-FAPI PET/CT in brain tumors remains unclear, and there aren't many similar studies in the literature. We evaluated the role of [68Ga]Ga-FAPI PET/CT in diagnosing brain tumors.

MRI Brain Tumour Segmentation Using Multiscale Attention U-Net

Focusing on the problems of failing to make full use of spatial context information and limited local receptive field when U-Net is utilized to solve MRI brain tumour segmentation, a novel 3D multi-scale attention U-Net method, i.e. MAU-Net, is proposed in this paper. Firstly, a Mixed Depth-wise Convolution (MDConv) module is introduced in the encoder and decoder, which leverages various convolution kernels to extract the multi-scale features of brain tumour images, and effectively strengthens the feature expression of the brain tumour lesion region in the up and down sampling. Secondly, a Context Pyramid Module (CPM) combining multi-scale and attention is embedded in the skip connection position to achieve the combination of local feature enhancement at multi-scale with global feature correlation. Finally, MAU-Net adopts Self-ensemble in the decoding process to achieve complementary detailed features of sampled brain tumour images at different scales, thereby further improving segmentation performance. Ablation and comparison experiment results on the publicly available BraTS 2019/2020 datasets well validate its effectiveness. It respectively achieves the Dice Similarity Coefficients (DSC) of 90.6%/90.2%, 82.7%/82.8%, and 77.9%/78.5% on the whole tumour (WT), tumour core (TC) and enhanced tumour (ET) segmentation. Additionally, on the BraTS 2021 training set, the DSC for WT, TC, and ET reached 93.7%, 93.2%, and 88.9%, respectively.

Contrast Normalization Strategies in Brain Tumor Imaging: From Preprocessing to Classification

Contrast Normalization Strategies in Brain Tumor Imaging: From Preprocessing to Classification

Enhancing brain tumor detection: a novel CNN approach with advanced activation functions for accurate medical imaging analysis.

Brain tumors are characterized by abnormal cell growth within or around the brain, posing severe health risks often associated with high mortality rates. Various imaging techniques, including magnetic resonance imaging (MRI), are commonly employed to visualize the brain and identify malignant growths. Computer-aided diagnosis tools (CAD) utilizing Convolutional Neural Networks (CNNs) have proven effective in feature extraction and predictive analysis across diverse medical imaging modalities. This study explores a CNN trained and evaluated with nine activation functions, encompassing eight established ones from the literature and a modified version of the soft sign activation function. The latter demonstrates notable efficacy in discriminating between four types of brain tumors in MR images, achieving an accuracy of 97.6%. The sensitivity for glioma is 93.7%; for meningioma, it is 97.4%; for cases with no tumor, it is 98.8%; and for pituitary tumors, it reaches 100%. In this manuscript, we propose an advanced CNN architecture that integrates a newly developed activation function. Our extensive experimentation and analysis showcase the model's remarkable ability to precisely distinguish between different types of brain tumors within a substantial and diverse dataset. The findings from our study suggest that this model could serve as an invaluable supplementary tool for healthcare practitioners, including specialized medical professionals and resident physicians, in the accurate diagnosis of brain tumors.

YOLO‐UNet Architecture for Detecting and Segmenting the Localized MRI Brain Tumor Image

Brain tumor detection and segmentation are the main issues in biomedical engineering research fields, and it is always challenging due to its heterogeneous shape and location in MRI. The quality of the MR images also plays an important role in providing a clear sight of the shape and boundary of the tumor. The clear shape and boundary of the tumor will increase the probability of safe medical surgery. Analysis of this different scope of image types requires refined computerized quantification and visualization tools. This paper employed deep learning to detect and segment brain tumor MRI images by combining the convolutional neural network (CNN) and fully convolutional network (FCN) methodology in serial. The fundamental finding is to detect and localize the tumor area with YOLO‐CNN and segment it with the FCN‐UNet architecture. This analysis provided automatic detection and segmentation as well as the location of the tumor. The segmentation using the UNet is run under four scenarios, and the best one is chosen by the minimum loss and maximum accuracy value. In this research, we used 277 images for training, 69 images for validation, and 14 images for testing. The validation is carried out by comparing the segmentation results with the medical ground truth to provide the correct classification ratio (CCR). This study succeeded in the detection of brain tumors and provided a clear area of the brain tumor with a high CCR of about 97%.

High-Quality Fusion and Visualization for MR-PET Brain Tumor Images via Multi-Dimensional Features.

The fusion of magnetic resonance imaging and positron emission tomography can combine biological anatomical information and physiological metabolic information, which is of great significance for the clinical diagnosis and localization of lesions. In this paper, we propose a novel adaptive linear fusion method for multi-dimensional features of brain magnetic resonance and positron emission tomography images based on a convolutional neural network, termed as MdAFuse. First, in the feature extraction stage, three-dimensional feature extraction modules are constructed to extract coarse, fine, and multi-scale information features from the source image. Second, at the fusion stage, the affine mapping function of multi-dimensional features is established to maintain a constant geometric relationship between the features, which can effectively utilize structural information from a feature map to achieve a better reconstruction effect. Furthermore, our MdAFuse comprises a key feature visualization enhancement algorithm designed to observe the dynamic growth of brain lesions, which can facilitate the early diagnosis and treatment of brain tumors. Extensive experimental results demonstrate that our method is superior to existing fusion methods in terms of visual perception and nine kinds of objective image fusion metrics. Specifically, in the results of MR-PET fusion, the SSIM (Structural Similarity) and VIF (Visual Information Fidelity) metrics show improvements of 5.61% and 13.76%, respectively, compared to the current state-of-the-art algorithm. Our code is publicly available at: https://github.com/22385wjy/MdAFuse.

Basics for Pediatric Brain Tumor Imaging: Techniques and Protocol Recommendations.

This review provides an overview of the current state of pediatric brain tumor imaging, emphasizing the role of various imaging sequences and highlighting the advantages of standardizing protocols for pediatric brain tumor imaging in diagnosis and treatment response evaluation. Basic anatomical sequences such as pre- and post-contrast 3D T1-weighted, T2-weighted, fluid-attenuated inversion recovery, T2*-weighted, and diffusion-weighted imaging (DWI), are fundamental for assessing tumor location, extent, and characteristics. Advanced techniques like DWI, diffusion tensor imaging, perfusion imaging, magnetic resonance spectroscopy, and functional MRI offer insights into cellularity, vascularity, metabolism, and function. To enhance consistency and quality, standardized protocols for pediatric brain tumor imaging have been recommended by expert groups. Special considerations for pediatric patients, including the minimization of anesthesia exposure and gadolinium contrast agent usage, are essential to ensure patient safety and comfort. Staying up-to-date with diagnostic imaging techniques can contribute to improved communication, outcomes, and patient care in the field of pediatric neurooncology.

Brain tumor image segmentation based on Semantic Flow Guided Sampling and Attention Mechanism

Brain tumor image segmentation based on Semantic Flow Guided Sampling and Attention Mechanism

CNN-based Approach for Enhancing Brain Tumor Image Classification Accuracy

CNN-based Approach for Enhancing Brain Tumor Image Classification Accuracy