Brain tumor segmentation of MRI images: A comprehensive review on the application of artificial intelligence tools

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 152, P. 106405 - 106405

Published: Dec. 7, 2022

Language: Английский

---

Medical image segmentation using deep semantic-based methods: A review of techniques, applications and emerging trends

Information Fusion, Journal Year: 2022, Volume and Issue: 90, P. 316 - 352

Published: Oct. 8, 2022

Language: Английский

---

A Survey of Brain Tumor Segmentation and Classification Algorithms

Journal of Imaging, Journal Year: 2021, Volume and Issue: 7(9), P. 179 - 179

Published: Sept. 6, 2021

A brain Magnetic resonance imaging (MRI) scan of a single individual consists several slices across the 3D anatomical view. Therefore, manual segmentation tumors from magnetic (MR) images is challenging and time-consuming task. In addition, an automated tumor classification MRI non-invasive so that it avoids biopsy make diagnosis process safer. Since beginning this millennia late nineties, effort research community to come-up with automatic method has been tremendous. As result, there are ample literature on area focusing using region growing, traditional machine learning deep methods. Similarly, number tasks have performed in into their respective histological type, impressive performance results obtained. Considering state of-the-art methods performance, purpose paper provide comprehensive survey three, recently proposed, major model techniques, namely, shallow learning. The established works included also covers technical aspects such as strengths weaknesses different approaches, pre- post-processing feature extraction, datasets, models’ evaluation metrics.

Language: Английский

---

A review on brain tumor segmentation based on deep learning methods with federated learning techniques

Computerized Medical Imaging and Graphics, Journal Year: 2023, Volume and Issue: 110, P. 102313 - 102313

Published: Nov. 24, 2023

Brain tumors have become a severe medical complication in recent years due to their high fatality rate. Radiologists segment the tumor manually, which is time-consuming, error-prone, and expensive. In years, automated segmentation based on deep learning has demonstrated promising results solving computer vision problems such as image classification segmentation. recently prevalent task imaging determine location, size, shape using methods. Many researchers worked various machine approaches most optimal solution convolutional methodology. this review paper, we discuss effective techniques datasets that are widely used publicly available. We also proposed survey of federated methodologies enhance global performance ensure privacy. A comprehensive literature suggested after studying more than 100 papers generalize multi-modality information. Finally, concentrated unsolved brain client-based model training strategy. Based review, future will understand path solve these issues.

Language: Английский

---

A Review Paper about Deep Learning for Medical Image Analysis

Computational and Mathematical Methods in Medicine, Journal Year: 2023, Volume and Issue: 2023(1)

Published: Jan. 1, 2023

Medical imaging refers to the process of obtaining images internal organs for therapeutic purposes such as discovering or studying diseases. The primary objective medical image analysis is improve efficacy clinical research and treatment options. Deep learning has revamped analysis, yielding excellent results in processing tasks registration, segmentation, feature extraction, classification. prime motivations this are availability computational resources resurgence deep convolutional neural networks. techniques good at observing hidden patterns supporting clinicians achieving diagnostic perfection. It proven be most effective method organ cancer detection, disease categorization, computer-assisted diagnosis. Many approaches have been published analyze various purposes. In paper, we review work exploiting current state-of-the-art processing. We begin survey by providing a synopsis works based on Second, discuss popular pretrained models general adversarial networks that aid improving networks' performance. Finally, ease direct evaluation, compile performance metrics focusing COVID-19 detection child bone age prediction.

Language: Английский

---

Deep learning for medical image segmentation: State-of-the-art advancements and challenges

Informatics in Medicine Unlocked, Journal Year: 2024, Volume and Issue: 47, P. 101504 - 101504

Published: Jan. 1, 2024

Image segmentation, a crucial process of dividing images into distinct parts or objects, has witnessed remarkable advancements with the emergence deep learning (DL) techniques. The use layers in neural networks, like object form recognition higher and basic edge identification lower layers, markedly improved quality accuracy image segmentation. Consequently, DL using picture segmentation become commonplace, video analysis, facial recognition, etc. Grasping applications, algorithms, current performance, challenges are for advancing DL-based medical However, there's lack studies delving latest state-of-the-art developments this field. Therefore, survey aimed to thoroughly explore most recent applications encompassing an in-depth analysis various commonly used datasets, pre-processing techniques algorithms. This study also investigated advancement done by analyzing their results experimental details. Finally, discussed future research directions Overall, provides comprehensive insight covering its application domains, model exploration, results, challenges, directions—a valuable resource multidisciplinary studies.

Language: Английский

---

Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches

Bioengineering, Journal Year: 2024, Volume and Issue: 11(10), P. 1034 - 1034

Published: Oct. 16, 2024

Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across wide range of clinical tasks. This review begins by offering comprehensive overview traditional techniques, including thresholding, edge-based methods, region-based approaches, clustering, graph-based segmentation. While these methods are computationally efficient interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus this is the transformative impact deep learning on We delve into prominent architectures such as Convolutional Neural Networks (CNNs), Fully (FCNs), U-Net, Recurrent (RNNs), Adversarial (GANs), Autoencoders (AEs). Each architecture analyzed terms its structural foundation specific application segmentation, illustrating how models have enhanced accuracy various contexts. Finally, examines integration with addressing limitations both approaches. These hybrid strategies offer improved performance, particularly challenging scenarios involving weak edges, noise, inconsistent intensities. By synthesizing recent advancements, provides detailed resource for researchers practitioners, valuable insights current landscape future directions

Language: Английский

---

ACU-Net: Attention-based convolutional U-Net model for segmenting brain tumors in fMRI images

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: Jan. 1, 2025

Objective Accurate segmentation of brain tumors in medical imaging is essential for diagnosis and treatment planning. Current techniques often struggle with capturing complex tumor features are computationally demanding, limiting their clinical application. This study introduces the attention-based convolutional U-Net (ACU-Net) model, designed to improve accuracy efficiency fMRI images by incorporating attention mechanisms that selectively highlight critical while preserving spatial context. Methods The ACU-Net model combines neural networks (CNNs) enhance feature extraction coherence. We evaluated on BraTS 2018 2020 datasets using rigorous data splitting training, validation, testing. Performance metrics, particularly Dice scores, were used assess across different regions, including whole (WT), core (TC), enhancing (ET) classes. Results demonstrated high accuracy, achieving scores 99.23%, 99.27%, 96.99% WT, TC, ET, respectively, dataset, 98.72%, 98.40%, 97.66% ET dataset. These results indicate effectively captures boundaries subregions precision, surpassing traditional approaches. Conclusion shows significant potential planning providing precise efficient images. integration within a CNN architecture proves beneficial identifying structures, suggesting can be valuable tool applications.

Language: Английский

---

Deep Learning in Cancer Diagnosis and Prognosis Prediction: A Minireview on Challenges, Recent Trends, and Future Directions

Computational and Mathematical Methods in Medicine, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 28

Published: Oct. 31, 2021

Deep learning (DL) is a branch of machine and artificial intelligence that has been applied to many areas in different domains such as health care drug design. Cancer prognosis estimates the ultimate fate cancer subject provides survival estimation subjects. An accurate timely diagnostic prognostic decision will greatly benefit DL emerged technology choice due availability high computational resources. The main components standard computer-aided design (CAD) system are preprocessing, feature recognition, extraction selection, categorization, performance assessment. Reduction costs associated with sequencing systems offers myriad opportunities for building precise models diagnosis prediction. In this survey, we provided summary current works where helped determine best prediction tasks. generic model requiring minimal data manipulations achieves better results while working enormous volumes data. Aims scrutinize influence using histopathology images, present state-of-the-art methods, give directions future researchers refine existing methods.

Language: Английский

---

Diagnosis of brain diseases in fusion of neuroimaging modalities using deep learning: A review

Information Fusion, Journal Year: 2022, Volume and Issue: 93, P. 85 - 117

Published: Dec. 14, 2022

Language: Английский

---