Advancing Brain Tumor Segmentation with Optimal Data Augmentation

Brain tumors are one of the most common neurological complications that affect millions each year. Current studies have focused only on either the segmentation of brain tumors or healthy anatomical regions. Unfortunately, there is a lack of research on whole brain segmentation of patients with existing tumors. The segmentation of these regions is cruical for understanding patient pathologies. Due to the distortions in the brain caused by tumors, whole-brain segmentation models trained on healthy brains will not perform accurately on diseased ones. To address this issue, this paper proposes a novel unified 3D nnU-Net model for the segmentation of both brain tumor and whole-brain structures for the first time. Training a model on datasets that include both healthy and cancerous brain regions could enhance the generalizability of machine learning (ML) models for performing both whole-brain segmentation and tumor segmentation tasks. Currently, there are no datasets that are publicly available for this purpose. This paper proposes to address this challenge by augmenting data from OASIS-1 and BraTS2023 to train the baseline model. The model successfully achieves a Dice Similarity Coefficient (DSC) of 0.814 for whole brain structures and 0.874 for tumor segmentation, demonstrating its effectiveness across diverse regions.

Brain tumors are considered as most fatal cancers. To reduce the risk of death, early identification of the disease is required. One of the best available methods to evaluate brain tumors is Magnetic resonance Images (MRI). Brain tumor detection and segmentation are tough as brain tumors may vary in size, shape, and location. That makes manual detection of brain tumors by exploring MRI a tedious job for radiologists and doctors’. So an automated brain tumor detection and segmentation is required. This work suggests a Region-based Convolution Neural Network (RCNN) approach for automated brain tumor identification and segmentation using MR images, which helps solve the difficulties of brain tumor identification efficiently and accurately. Our methodology is based on the accurate and efficient selection of tumorous areas. That reduces computational complexity and time. We have validated the designed experimental setup on a standard dataset, BraTS 2020. We used binary evaluation matrices based on Dice Similarity Coefficient (DSC) and Mean Average Precision (mAP). The segmentation results are compared with state-of-the-art methodologies to demonstrate the effectiveness of the proposed method. The suggested approach attained an average DSC of 0.92 and mAP 0.92 for 10 patients, while on the whole dataset, the scores are DSC 0.89 and mAP 0.90. The following results clearly show the performance efficiency of the proposed methodology.

A Validation Framework for Brain Tumor Segmentation

Achieving accurate bladder wall and tumor segmentation from MRI is critical for diagnosing and treating bladder cancer. However, automated segmentation remains challenging due to factors such as comparable density distributions, intricate tumor morphologies, and unclear boundaries. Considering the attributes of bladder MRI images, we propose an efficient multiscale hierarchical hybrid attention with a transformer (MH2AFormer) for bladder cancer and wall segmentation. Specifically, a multiscale hybrid attention and transformer (MHAT) module in the encoder is designed to adaptively extract and aggregate multiscale hybrid feature representations from the input image. In the decoder stage, we devise a multiscale hybrid attention (MHA) module to generate high-quality segmentation results from multiscale hybrid features. Combining these modules enhances the feature representation and guides the model to focus on tumor and wall regions, which helps to solve bladder image segmentation challenges. Moreover, MHAT utilizes the Fast Fourier Transformer with a large kernel (e.g., 224 × 224) to model global feature relationships while reducing computational complexity in the encoding stage. The model performance was evaluated on two datasets. As a result, the model achieves relatively best results regarding the intersection over union (IoU) and dice similarity coefficient (DSC) on both datasets (Dataset A: IoU = 80.26%, DSC = 88.20%; Dataset B: IoU = 89.74%, DSC = 94.48%). These advantageous outcomes substantiate the practical utility of our approach, highlighting its potential to alleviate the workload of radiologists when applied in clinical settings.

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%.

For determining the appropriate treatment for brain tumors, an accurate diagnosis is necessary. Many studies have focused on the deep learning-based classification of brain tumors. This study employed a comprehensive approach using deep learning techniques to improve diagnostic accuracy and treatment planning for brain tumors. The Random Forest algorithm, SVM, YOLOv5, and Neural Network classifier were utilized to classify brain tumors and different planes of brain MRI images. To segment the tumors, the U-Net architecture with various neural network backbones (VGG16, Resnet34, and InceptionV3) was implemented, and metrics such as intersection over union (IOU) and dice coefficient were used to assess the segmentation outcome. The U-Net model achieved an IOU of 0.73 and a dice coefficient of 0.84. The Random Forest algorithm achieved 99 percent and 95 percent classification accuracy in image planes and tumor types, respectively. The SVM, YOLOv5, and Neural Network Classifier provided classification accuracies of 91 percent, 95 percent, and 96 percent, respectively, in classifying brain tumors. The ensemble models predicted the final result, demonstrating the potential of this approach to improve brain tumor diagnosis and treatment planning.

In this work, we propose a fully automatic brain tumor and edema segmentation technique in brain magnetic resonance (MR) images. Different brain tissues are characterized using the novel texture features such as piece-wise triangular prism surface area (PTPSA), multi-fractional Brownian motion (mBm) and Gabor-like textons, along with regular intensity and intensity difference features. Classical Random Forest (RF) classifier is used to formulate the segmentation task as classification of these features in multi-modal MRIs. The segmentation performance is compared with other state-of-art works using a publicly available dataset known as Brain Tumor Segmentation (BRATS) 2012 [1]. Quantitative evaluation is done using the online evaluation tool from Kitware/MIDAS website [2]. The results show that our segmentation performance is more consistent and, on the average, outperforms other state-of-the art works in both training and challenge cases in the BRATS competition.

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

Gliomas are a common and aggressive kind of brain tumour that is difficult to diagnose due to their infiltrative development, variable clinical presentation, and complex behaviour, making them an important focus in neuro-oncology. Segmentation of brain tumour images is critical for improving diagnosis, prognosis, and treatment options. Manually segmenting brain tumours is time-consuming and challenging. Automatic segmentation algorithms can significantly improve the accuracy and efficiency of tumour identification, thus improving treatment planning and outcomes. Deep learning-based segmentation tumours have shown significant advances in the last few years. This study evaluates the impact of four denoising filters, namely median, Gaussian, anisotropic diffusion, and bilateral, on tumour detection and segmentation. The U-Net architecture is applied for the segmentation of 3064 contrast-enhanced magnetic resonance images from 233 patients diagnosed with meningiomas, gliomas, and pituitary tumours. The results of this work demonstrate that bilateral filtering yields superior outcomes, proving to be a robust and computationally efficient approach in brain tumour segmentation. This method reduces the processing time by 12 epochs, which in turn contributes to lowering greenhouse gas emissions by optimizing computational resources and minimizing energy consumption.

Accurately separating healthy tissue from tumorous regions is crucial for effective diagnosis and treatment planning based on magnetic resonance imaging (MRI) data. Current manual detection methods rely heavily on human expertise, so MRI-based segmentation is essential to improving diagnostic accuracy and treatment outcomes. The purpose of this paper is to compare the performance of detecting brain tumors from MRI images through segmentation using an unmodified and modified U-Net architecture from deep neural network (DNN) that has been modified by adding batch normalization and dropout on the encoder layer with and without the freeze layer. The study utilizes a public 2D brain tumor dataset containing 3064 T1-weighted contrast-enhanced images of meningioma, glioma, and pituitary tumors. Model performance was evaluated using intersection over union (IoU) and standard metrics such as precision, recall, f1-score, and accuracy across training, validation, and testing stages. Statistical analysis, including ANOVA and Duncan's multiple range test, was conducted to determine the significance of performance differences across the architectures. Results indicate that while the modified architectures show improved stability and convergence, the freeze layer model demonstrated superior IoU and efficiency, making it a promising approach for more accurate and efficient brain tumor segmentation. The comparison of the three methods revealed that the modified U-Net architecture with a freeze layer significantly reduced training time by 81.72% compared to the unmodified U-Net while maintaining similar performance across validation and testing stages. All three methods showed comparable accuracy and consistency, with no significant differences in performance during validation and testing.

Highly accurate tumor segmentation and classification are required to treat the brain tumor appropriately. Brain tumor segmentation (BTS) approaches can be categorized into manual, semi-automated, and full-automated. The deep learning (DL) approach has been broadly deployed to automate tumor segmentation in therapy, treatment planning, and diagnosing evaluation. It is mainly based on the U-Net model that has recently attained state-of-the-art performances for multimodal BTS. This paper demonstrates a literature review for BTS using U-Net models. Additionally, it represents a common way to design a novel U-Net model for segmenting brain tumors. The steps of this DL way are described to obtain the required model. They include gathering the dataset, pre-processing, augmenting the images (optional), designing/selecting the model architecture, and applying transfer learning (optional). The model architecture and the performance accuracy are the two most important metrics used to review the works of literature. This review concluded that the model accuracy is proportional to its architectural complexity, and the future challenge is to obtain higher accuracy with low-complexity architecture. Challenges, alternatives, and future trends are also presented.

This study investigates the impact of transfer learning and fine-tuning on the performance of medical image segmentation tasks across different imaging modalities, including MRI, CT, and ultrasound. Leveraging pre-trained models such as U-Net, ResNet, and VGG16, we conduct extensive experiments to compare the efficacy of transfer learning against fine-tuning in segmenting brain tumors, livers, and kidneys. Our results demonstrate that while transfer learning provides a strong baseline for medical image analysis, fine-tuning consistently enhances model performance, leading to significant improvements in Dice coefficient, Intersection over Union (IoU), precision, and recall across all datasets. These findings underscore the importance of fine-tuning in adapting pre-trained models to the unique challenges of medical imaging, offering valuable insights for developing more accurate and reliable segmentation models in clinical practice.

Intraoperative ultrasound (iUS) is increasingly used in pediatric brain tumor surgery. However, accurate tumor tissue identification and localization within the patient with iUS remains challenging. Automatic tumor segmentation may overcome these difficulties by providing quicker, more consistent, and reliable image analysis. This study evaluated the feasibility of automatic 3-dimensional segmentation of pediatric brain tumors using navigated iUS. A retrospective analysis was conducted on 109 navigated iUS acquisitions from 60 pediatric patients who underwent neurosurgical tumor resection. 3-dimensional nnU-Net was trained on 79 preresectional iUS acquisitions with corresponding tumor segmentations. Evaluation was performed on 30 iUS acquisitions against segmentations validated by 2 neurosurgeons. Performance benchmarks were set at a minimum Dice Similarity Coefficient (DSC) of 0.85 and a maximum mean surface distance and 95th percentile Hausdorff distance of 5 mm. The trained algorithm predicted tumor segmentations for all acquisitions in the test set, which met the predefined benchmark values with a median DSC of 0.89 (IQR: 0.13), a median mean surface distance of 1.1 mm (IQR: 1.0 mm), and a median 95th percentile Hausdorff distance of 5.6 mm (IQR: 3.5 mm). The lowest quartile of DSC values consisted of 5 patients, including craniopharyngiomas (n = 3) and high-grade gliomas (n = 2). Oversegmentation of the lateral ventricle as tumor was observed in 2 patients. In 1 high-grade glioma case, edema was misclassified as tumor because of unclear tumor boundaries. This study demonstrates that automatic segmentation of pediatric brain tumors using navigated iUS is feasible and achieved high performance in most cases, with few outliers that showed moderate performance in tumor prediction. Future efforts will focus on real-time segmentation of residual tumor tissue during tumor resection. Ultimately, real-time visualization of automatically segmented tumors in 3 dimensions could improve intraoperative navigation and support neurosurgical decision making.

In this paper, we propose an automated approach based on the geometric median shift algorithm over Riemannian manifolds, for the brain tumor detection and segmentation in magnetic resonance images (MRI). This approach is based on the geometric median, geodesic distance. We propose the median shift to overcome the limitation of mean which is not necessary a point in a set. The geodesic distance can describe data points distributed on a manifold, compared to the Euclidean distance, and produce efficient results for image analysis. Coupled with k-means algorithm, the proposed framework can cluster the brain image into tree regions (gray matter, white matter and cerebrospinal fluid) and abnormalities regions. We applied this approach to clustering the brain tissues and brain tumor segmentation, which is validated on a synthetic brain MRI. The obtained results using two datasets show the efficiency of the used algorithm validated qualitatively by the measurement of Dice Similarity Coefficient.

The number of medical imaging devices is quickly and steadily rising, generating an increasing amount of image records day by day. The number of qualified human experts able to handle this data cannot follow this trend, so there is a strong need to develop reliable automatic segmentation and decision support algorithms. The Brain Tumor Segmentation Challenge (BraTS), first organized seven years ago, provoked a strong intensification of the development of brain tumor detection and segmentation algorithms. Beside many others, several ensemble learning solutions have been proposed lately to the above mentioned problem. This study presents an evaluation framework developed to evaluate the accuracy and efficiency of these algorithms deployed in brain tumor segmentation, based on the BraTS 2016 train data set. All evaluated algorithms proved suitable to provide acceptable accuracy in segmentation, but random forest was found the best, both in terms of precision and efficiency.