MS UNet: Multi-scale 3D UNet for Brain Tumor Segmentation

Currently, brain tumors are extremely harmful and prevalent. Deep learning technologies, including CNNs, UNet, and Transformer, have been applied in brain tumor segmentation for many years and have achieved some success. However, traditional CNNs and UNet capture insufficient global information, and Transformer cannot provide sufficient local information. Fusing the global information from Transformer with the local information of convolutions is an important step toward improving brain tumor segmentation. We propose the Group Normalization Shuffle and Enhanced Channel Self-Attention Network (GETNet), a network combining the pure Transformer structure with convolution operations based on VT-UNet, which considers both global and local information. The network includes the proposed group normalization shuffle block (GNS) and enhanced channel self-attention block (ECSA). The GNS is used after the VT Encoder Block and before the downsampling block to improve information extraction. An ECSA module is added to the bottleneck layer to utilize the characteristics of the detailed features in the bottom layer effectively. We also conducted experiments on the BraTS2021 dataset to demonstrate the performance of our network. The Dice coefficient (Dice) score results show that the values for the regions of the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) were 91.77, 86.03, and 83.64, respectively. The results show that the proposed model achieves state-of-the-art performance compared with more than eleven benchmarks.

GCAUNet: A group cross-channel attention residual UNet for slice based brain tumor segmentation

Glioblastoma is an aggressive type of cancer that can develop in the brain or spinal cord. Magnetic Resonance Imaging (MRI) is key to diagnosing and tracking brain tumors in clinical settings. Brain tumor segmentation in MRI is required for disease diagnosis, surgical planning, and prognosis. As these tumors are heterogeneous in shape and appearance, their segmentation becomes a challenging task. The performance of automated medical image segmentation has considerably improved because of recent advances in deep learning. Introducing context encoding with deep CNN models has shown promise for semantic segmentation of brain tumors. In this work, we use a 3D UNet-Context Encoding (UNCE) deep learning network for improved brain tumor segmentation. Further, we introduce epistemic and aleatoric Uncertainty Quantification (UQ) using Monte Carlo Dropout (MCDO) and Test Time Augmentation (TTA) with the UNCE deep learning model to ascertain confidence in tumor segmentation performance. We build our model using the training MRI image sets of RSNA-ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2021. We evaluate the model performance using the validation and test images from the BraTS challenge dataset. Online evaluation of validation data shows dice score coefficients (DSC) of 0.7787, 0.8499, and 0.9159 for enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively. The dice score coefficients of the test datasets are 0.6684 for ET, 0.7056 for TC, and 0.7551 for WT, respectively.

To develop a novel method based on feature selection, combining convolutional neural network (CNN) and ensemble learning (EL), to achieve high accuracy and efficiency of glioma detection and segmentation using multiparametric MRIs. We proposed an evolutionary feature selection-based hybrid approach for glioma detection and segmentation on 4MR sequences (T2-FLAIR, T1, T1Gd, and T2). First, we trained a lightweight CNN to detect glioma and mask the suspected region to process large batch of MRI images. Second, we employed a differential evolution algorithm to search a feature space, which composed of 416-dimensions radiomics features extracted from four sequences of MRIs and 128-dimensions high-order features extracted by the CNN, to generate an optimal feature combination for pixel classification. Finally, we trained an EL classifier using the optimal feature combination to segment whole tumor (WT) and its subregions including non-enhancing tumor (NET), peritumoral edema (ED), and enhancing tumor (ET) in the suspected region. Experiments were carried out on 300 glioma patients from the BraTS2019 dataset using fivefold cross-validation, and the model was independently validated using the rest 35 patients from the same database. The approach achieved a detection accuracy of 98.8% using four MRIs. The Dice coefficients (and standard deviations) were 0.852±0.057, 0.844±0.046, and 0.799±0.053 for segmentation of WT (NET+ET+ED), tumor core (NET+ET), and ET, respectively. The sensitivities and specificities were 0.873±0.074, 0.863±0.072, and 0.852±0.082; the specificities were 0.994±0.005, 0.994±0.005, and 0.995±0.004 for the WT, tumor core, and ET, respectively. The performances and calculation times were compared with the state-of-the-art approaches, our approach yielded a better overall performance with average processing time of 139.5s per set of four sequence MRIs. We demonstrated a robust and computational cost-effective hybrid segmentation approach for glioma and its subregions on multi-sequence MR images. The proposed approach can be used for automated target delineation for glioma patients.

Gliomas, the most aggressive primary tumors in the central nervous system, are characterized by high morphological heterogeneity and diffusely infiltrating boundaries. Such complexity poses significant challenges for accurate segmentation in clinical practice. Although deep learning methods have shown promising results, they often struggle to achieve a satisfactory trade-off among precise boundary delineation, robust multi-scale feature representation, and computational efficiency, particularly when processing high-resolution three-dimensional (3D) magnetic resonance imaging (MRI) data. Therefore, the aim of this study is to develop a novel 3D segmentation framework that specifically addresses these challenges, thereby improving clinical utility in brain tumor analysis. To accomplish this, we propose a multi-level channel-spatial attention and light-weight scale-fusion network (MCSLF-Net), which integrates a multi-level channel-spatial attention mechanism (MCSAM) and a light-weight scale-fusion module. By strategically enhancing subtle boundary features while maintaining a compact network design, our approach seeks to achieve high accuracy in delineating complex glioma morphologies, reduce computational burden, and provide a more clinically feasible segmentation solution. We propose MCSLF-Net, a network integrating two key components: (I) MCSAM: by strategically inserting a 3D channel-spatial attention module at critical semantic layers, the network progressively emphasizes subtle, infiltrative edges and small, easily overlooked contours. This avoids reliance on an additional edge detection branch while enabling fine-grained localization in ambiguous transitional regions. (II) Light-weight scale fusion unit (LSFU): leveraging depth-wise separable convolutions combined with multi-scale atrous (dilated) convolutions, LSFU enhances computational efficiency and adapts to varying feature requirements at different network depths. In doing so, it effectively captures small infiltrative lesions as well as extensive tumor areas. By coupling these two modules, MCSLF-Net balances global contextual information with local fine-grained features, simultaneously reducing the computational burden typically associated with 3D medical image segmentation. Extensive experiments on the BraTS 2019, BraTS 2020, and BraTS 2021 datasets validated the effectiveness of our approach. On BraTS 2021, MCSLF-Net achieved a mean Dice similarity coefficient (DSC) of 0.8974 and a mean 95th percentile Hausdorff distance (HD95) of 2.52 mm. Notably, it excels in segmenting intricate transitional areas, including the enhancing tumor (ET) region and the tumor core (TC), thereby demonstrating superior boundary delineation and multi-scale feature fusion capabilities relative to existing methods. These findings underscore the clinical potential of deploying multi-level channel-spatial attention and light-weight multi-scale fusion strategies in high-precision 3D glioma segmentation. By striking an optimal balance among boundary accuracy, multi-scale feature capture, and computational efficiency, the proposed MCSLF-Net offers a practical framework for further advancements in automated brain tumor analysis and can be extended to a range of 3D medical image segmentation tasks.

Accurate and efficient automatic segmentation of brain tumors is critical for diagnosis and treatment. However, the diversity in the appearance, location, and shape of brain tumors and their subregions, coupled with complex boundaries, presents significant challenges. We aim to improve segmentation accuracy by addressing limitations in V-Net, including insufficient utilization of multi-scale features and difficulties in managing complex spatial relationships and long-range dependencies. We propose an improved network structure, dynamic convolution enhanced fusion axial V-Net (DCEF-AVNet), which integrates an enhanced feature fusion module and axial attention mechanisms. The feature fusion module integrates dynamic convolution with a redesigned skip connection strategy to effectively combine multi-scale features, reducing feature inconsistencies and improving representation capability. Axial attention mechanisms are introduced at encoder-decoder connections to manage spatial relationships and alleviate long-range dependency issues. The network was evaluated using the BraTS2021 dataset, with performance measured in terms of Dice coefficients and Hausdorff distances. DCEF-AVNet achieved Dice coefficients of 92.49%, 91.35%, and 91.96% for the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) regions, respectively, significantly outperforming baseline methods. The model also demonstrated robust performance across multiple runs, with consistently low standard deviations in metrics. The integration of dynamic convolution, enhanced feature fusion, and axial attention mechanisms enables DCEF-AVNet to deliver superior segmentation accuracy and robustness. These results underscore its potential for advancing automated brain tumor segmentation and improving clinical decision-making.

We developed a fully automated method for brain tumor segmentation using deep learning; 285 brain tumor cases with multiparametric magnetic resonance images from the BraTS2018 data set were used. We designed 3 separate 3D-Dense-UNets to simplify the complex multiclass segmentation problem into individual binary-segmentation problems for each subcomponent. We implemented a 3-fold cross-validation to generalize the network's performance. The mean cross-validation Dice-scores for whole tumor (WT), tumor core (TC), and enhancing tumor (ET) segmentations were 0.92, 0.84, and 0.80, respectively. We then retrained the individual binary-segmentation networks using 265 of the 285 cases, with 20 cases held-out for testing. We also tested the network on 46 cases from the BraTS2017 validation data set, 66 cases from the BraTS2018 validation data set, and 52 cases from an independent clinical data set. The average Dice-scores for WT, TC, and ET were 0.90, 0.84, and 0.80, respectively, on the 20 held-out testing cases. The average Dice-scores for WT, TC, and ET on the BraTS2017 validation data set, the BraTS2018 validation data set, and the clinical data set were as follows: 0.90, 0.80, and 0.78; 0.90, 0.82, and 0.80; and 0.85, 0.80, and 0.77, respectively. A fully automated deep learning method was developed to segment brain tumors into their subcomponents, which achieved high prediction accuracy on the BraTS data set and on the independent clinical data set. This method is promising for implementation into a clinical workflow.

In this paper, we look at how to design and build a system to find tumors using 2 Convolutional Neural Network (CNN) models. With the help of digital image processing and deep Learning, we can make a system that automatically diagnoses and finds different diseases and abnormalities. The tumor detection system may include image enhancement, segmentation, data enhancement, feature extraction, and classification. These options are set up so that the CNN model can give the best results. During the training phase, the learning rate is used to change the weights and bias. The learning rate also changes the weights. One Epoch is when all of the training images are shown to the model. As the training data may be very large, the data in each epoch are split into batches. Every epoch has a training session and a test session. After each epoch, the weights are changed based on how fast the CNN is learning. This is done with the help of optimization algorithms. The suggested technique uses the anticipated mean intersection over union value to identify failure instances in addition to forecasting the mean intersection over union. This paper talks about how to separate brain tumors from magnetic resonance images of patients taken from "Brain web." Using basic ideas of digital image processing, magnetic resonance images are used to extract and find tumors using a hybrid method. In this paper, the proposed algorithm is applied with the help of MATLAB. In medical image processing, brain tumor segmentation is an important task. The goal of this paper is to look at different ways to divide brain tumors using magnetic resonance imaging. Recently, automatic segmentation using deep learning methods has become popular because these methods get the best results and are better at solving this problem than others. Deep learning methods can also be used to process and evaluate large amounts of magnetic resonance imaging image data quickly and objectively. A classification method based on a convolution neural network is also added to the proposed scheme to make it more accurate and cut down on the amount of time it takes to do the calculations. Also, the results of the classification are given as images of a tumor or a healthy brain. The training is 98.5% correct. In the same way, both the validation accuracy and validation loss are high.

This paper proposes a glioma segmentation method based on neural networks. The base of the network is a UNet, expanded by residual blocks. Several preprocessing steps were applied before training, such as intensity normalization, high intensity cutting, cropping, and random flips. 2D and 3D solutions are implemented and tested, and results show that the 3D network outperforms 2D directions, therefore we stayed with 3D directions.The novelty of the method is the energy-based post-processing. Snakes [10], and conditional random fields (CRF) [11] were applied to the neural network’s predictions. Snake or active contour needs an initial outline around the object – e.g. the network’s prediction outline - and it can correct the contours of the tumor based on calculating the energy minimum, based on the intensity values at a given area. CRF is a specific type of graphical model, it uses the network’s prediction and the raw image features to estimate the posterior distribution (the tumor contour) using energy function minimization.The proposed methods are evaluated within the framework of the BRATS 2020 challenge. Measured on the test dataset the mean dice scores of the whole tumor (WT), tumor core (TC) and enhancing tumor (ET) are 86.9%, 83.2% and 81.8% respectively. The results show high performance and promising future work in tumor segmentation, even outside of the brain.KeywordsTumor segmentationMedical imagingNeural networksSupervised segmentationUNetResNetRadiation therapy

A Review on Convolutional Neural Networks for Brain Tumor Segmentation: Methods, Datasets, Libraries, and Future Directions

Automated 3D volumetric segmentation of brain tumors from multi-modal MRI is essential for clinical practice.[1] This study provides a rigorous, statistically validated comparison of four 3D deep learning architectures: 3D U-Net, 3D DeepLabV3+, and their lightweight counterparts, U-Net3D_Simple and DeepLabV3Plus3D_Simple. The comparison yielded nuanced results. The standard 3D U-Net achieved the highest Whole Tumor (WT) Dice score (0.884). However, the standard 3D DeepLabV3+ demonstrated a statistically significant advantage in segmenting the critical sub-regions, with a Tumor Core (TC) Dice of 0.846 (p = 0.032) and an Enhancing Tumor (ET) Dice of 0.788 (p = 0.045). DeepLabV3+ also showed superior boundary accuracy (WT HD95 of 5.89 mm). Critically, this study analyzes the performance-efficiency trade-off. The simplified models offered massive parameter reductions (68-72%) and faster inference (37-41% speedup) while incurring only a minor, though statistically significant, drop in average Dice performance (≈1.5-1.8%). The results confirm DeepLabV3+'s contextual advantage for complex sub-regions and demonstrate that lightweight models are a highly compelling and viable option for computationally constrained clinical environments. Repository: https://github.com/Mohamed-Moukbil/Brain-Tumor-Segmentation-3D

3D brain tumor segmentation is essential for the diagnosis, monitoring, and treatment planning of brain diseases. In recent studies, the Deep Convolution Neural Network (DCNN) is one of the most potent methods for medical image segmentation. In this paper, we review the different kinds of tricks applied to 3D brain tumor segmentation with DNN. We divide such tricks into three main categories: data processing methods including data sampling, random patch-size training, and semi-supervised learning, model devising methods including architecture devising and result fusing, and optimizing processes including warming-up learning and multi-task learning. Most of these approaches are not particular to brain tumor segmentation, but applicable to other medical image segmentation problems as well. Evaluated on the BraTS2019 online testing set, we obtain Dice scores of 0.810, 0.883 and 0.861, and Hausdorff Distances (95th percentile) of 2.447, 4.792, and 5.581 for enhanced tumor core, whole tumor, and tumor core, respectively. Our method won the second place of the BraTS 2019 Challenge for the tumor segmentation.

Intracranial tumors are commonly known as brain tumors, which can be life-threatening in severe cases. Magnetic resonance imaging (MRI) is widely used in diagnosing brain tumors because of its harmless to the human body and high image resolution. Due to the heterogeneity of brain tumor height, MRI imaging is exceptionally irregular. How to accurately and quickly segment brain tumor MRI images is still one of the hottest topics in the medical image analysis community. However, according to the brain tumor segmentation algorithms, we could find now, most segmentation algorithms still stay in two-dimensional (2D) image segmentation, which could not obtain the spatial dependence between features effectively. In this study, we propose a brain tumor automatic segmentation method called scSE-NL V-Net. We try to use three-dimensional (3D) data as the model input and process the data by 3D convolution to get some relevance between dimensions. Meanwhile, we adopt non-local block as the self-attention block, which can reduce inherent image noise interference and make up for the lack of spatial dependence due to convolution. To improve the accuracy of convolutional neural network (CNN) image recognition, we add the “Spatial and Channel Squeeze-and-Excitation” Network (scSE-Net) to V-Net. The dataset used in this paper is from the brain tumor segmentation challenge 2020 database. In the test of the official BraTS2020 verification set, the Dice similarity coefficient is 0.65, 0.82, and 0.76 for the enhanced tumor (ET), whole tumor (WT), and tumor core (TC), respectively. Thereby, our model can make an auxiliary effect on the diagnosis of brain tumors established.

Brain tumors are one of the deadliest cancers in the world. Researchers have conducted a lot of research work on brain tumor segmentation with good performance due to the rapid development of deep learning for assisting doctors in diagnosis and treatment. However, most of these methods cannot fully combine multiple feature information and their performances need to be improved. This study developed a novel network fusing local features representing detailed information, global features representing global information, and multi-scale features enhancing the model’s robustness to fully extract the features of brain tumors and proposed a novel axial-deformable attention module for modeling global information to improve the performance of brain tumor segmentation to assist clinicians in the automatic segmentation of brain tumors. Moreover, positional embeddings were used to make the network training faster and improve the method’s performance. Six metrics were used to evaluate the proposed method on the BraTS2018 dataset. Outstanding performance was obtained with Dice score, mean Intersection over Union, precision, recall, params, and inference time of 0.8735, 0.7756, 0.9477, 0.8769, 69.02 M, and 15.66 millisecond, respectively, for the whole tumor. Extensive experiments demonstrated that the proposed network obtained excellent performance and was helpful in providing supplementary advice to the clinicians.

Diagnosis, treatment planning, surveillance, and the monitoring of clinical trials for brain diseases all benefit greatly from neuroimaging-based tumor segmentation. Recently, Convolutional Neural Networks (CNNs) have demonstrated promising results in enhancing the efficiency of image-based brain tumor segmentation. Most current work on CNNs, however, is devoted to creating increasingly complicated convolution modules to improve performance, which in turn raises the computing cost of the model. This work proposes a simple and effective feed-forward CNN, LightNet (Light Network). Based on multi-path and multi-level, it replaces traditional convolutional methods with light operations, which reduces network parameters and redundant feature maps. In the up-sampling stage, a light channel attention module is added to achieve richer multi-scale and spatial semantic feature information extraction of brain tumor. The performance of the network is evaluated in the Multimodal Brain Tumor Segmentation Challenge (BraTS 2015) dataset, and results are presented here alongside other high-performing CNNs. Results show comparable accuracy with other methods but with increased efficiency, segmentation performance, and reduced redundancy and computational complexity. The result is a high-performing network with a balance between efficiency and accuracy, allowing, for example, better energy performance on mobile devices.