Improvement of Brain Tumor Categorization using Deep Learning: A Comprehensive Investigation and Comparative Analysis DOI Open Access

T. Lakshmi Prasanthi,

N. Neelima

Procedia Computer Science, Journal Year: 2024, Volume and Issue: 233, P. 703 - 712

Published: Jan. 1, 2024

A brain tumor is a critically severe health disorder that requires an accurate and timely diagnosis for effective treatment. Advances in medical imaging deep learning methods have shown potential enhancing the identification categorization of cancers throughout years. In present research, our study compares accuracy eight different models classification tumors employing MRI data involve Densenet121, EfficientNet B7, InceptionResNetV2, Inception_V3, RestNet50V2, VGG16, VGG19, Xception. To further improve performance, we propose integrating hybrid technique. Efficient critical treatment patients, aims to achieve high recall, accuracy, F1-score this context. With precision 96.63%, innovative convolutional neural network (CNN) technique achieved outstanding results diagnosis. Also, investigates unique capabilities certain models, such as VGG19 their possibilities better glioma detection efficiency. Our results, particular, provide insight into possible uses frameworks, including integration techniques, imaging, offering approach increased identification.

Language: Английский

Deep learning based brain tumor segmentation: a survey DOI Creative Commons
Zhihua Liu, Lei Tong, Long Chen

et al.

Complex & Intelligent Systems, Journal Year: 2022, Volume and Issue: 9(1), P. 1001 - 1026

Published: July 9, 2022

Abstract Brain tumor segmentation is one of the most challenging problems in medical image analysis. The goal brain to generate accurate delineation regions. In recent years, deep learning methods have shown promising performance solving various computer vision problems, such as classification, object detection and semantic segmentation. A number based been applied achieved results. Considering remarkable breakthroughs made by state-of-the-art technologies, we provide this survey with a comprehensive study recently developed techniques. More than 150 scientific papers are selected discussed survey, extensively covering technical aspects network architecture design, under imbalanced conditions, multi-modality processes. We also insightful discussions for future development directions.

Language: Английский

Citations

214
Diagnosis of Diabetes Mellitus Using Gradient Boosting Machine (LightGBM) DOI Creative Commons
Derara Duba Rufo, Taye Girma Debelee, Achim Ibenthal

et al.

Diagnostics, Journal Year: 2021, Volume and Issue: 11(9), P. 1714 - 1714

Published: Sept. 19, 2021

Diabetes mellitus (DM) is a severe chronic disease that affects human health and has high prevalence worldwide. Research shown half of the diabetic people throughout world are unaware they have DM its complications increasing, which presents new research challenges opportunities. In this paper, we propose preemptive diagnosis method for diabetes to assist or complement early recognition in countries with low medical expert densities. data collected from Zewditu Memorial Hospital (ZMHDD) Addis Ababa, Ethiopia. Light Gradient Boosting Machine (LightGBM) one most recent successful findings gradient boosting framework uses tree-based learning algorithms. It computational complexity and, therefore, suited applications limited capacity regions such as Thus, study, apply principle LightGBM develop an accurate model diabetes. The experimental results show prepared dataset informative predict condition mellitus. With accuracy, AUC, sensitivity, specificity 98.1%, 99.9%, 96.3%, respectively, outperformed KNN, SVM, NB, Bagging, RF, XGBoost case ZMHDD dataset.

Language: Английский

Citations

199
Edge U-Net: Brain tumor segmentation using MRI based on deep U-Net model with boundary information DOI

Ahmed M. Gab Allah,

Amany Sarhan, Nada M. Elshennawy

et al.

Expert Systems with Applications, Journal Year: 2022, Volume and Issue: 213, P. 118833 - 118833

Published: Sept. 22, 2022

Language: Английский

Citations

107
Brain Tumor Detection and Classification Using Intelligence Techniques: An Overview DOI Creative Commons
Shubhangi Solanki, Uday Pratap Singh, Siddharth Singh Chouhan

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 12870 - 12886

Published: Jan. 1, 2023

A tumor is carried on by rapid and uncontrolled cell growth in the brain. If it not treated initial phases, could prove fatal. Despite numerous significant efforts encouraging outcomes, accurate segmentation classification continue to be a challenge. Detection of brain tumors significantly complicated distinctions position, structure, proportions. The main disinterest this study stays offer investigators, comprehensive literature Magnetic Resonance (MR) imaging's ability identify tumors. Using computational intelligence statistical image processing techniques, research paper proposed several ways detect cancer This also shows an assessment matrix for specific system using particular systems dataset types. explains morphology tumors, accessible data sets, augmentation methods, component extraction, categorization among Deep Learning (DL), Transfer (TL), Machine (ML) models. Finally, our compiles all relevant material identification understanding including their benefits, drawbacks, advancements, upcoming trends.

Language: Английский

Citations

103
Brain Tumor Diagnosis Using Machine Learning, Convolutional Neural Networks, Capsule Neural Networks and Vision Transformers, Applied to MRI: A Survey DOI Creative Commons
Andronicus A. Akinyelu, Fulvio Zaccagna, James T. Grist

et al.

Journal of Imaging, Journal Year: 2022, Volume and Issue: 8(8), P. 205 - 205

Published: July 22, 2022

Management of brain tumors is based on clinical and radiological information with presumed grade dictating treatment. Hence, a non-invasive assessment tumor paramount importance to choose the best treatment plan. Convolutional Neural Networks (CNNs) represent one effective Deep Learning (DL)-based techniques that have been used for diagnosis. However, they are unable handle input modifications effectively. Capsule neural networks (CapsNets) novel type machine learning (ML) architecture was recently developed address drawbacks CNNs. CapsNets resistant rotations affine translations, which beneficial when processing medical imaging datasets. Moreover, Vision Transformers (ViT)-based solutions very proposed issue long-range dependency in This survey provides comprehensive overview classification segmentation techniques, focus ML-based, CNN-based, CapsNet-based, ViT-based techniques. The highlights fundamental contributions recent studies performance state-of-the-art we present an in-depth discussion crucial issues open challenges. We also identify some key limitations promising future research directions. envisage this shall serve as good springboard further study.

Language: Английский

Citations

80
A review on brain tumor segmentation based on deep learning methods with federated learning techniques DOI Creative Commons
Md. Faysal Ahamed, Md. Munawar Hossain, Md. Nahiduzzaman

et al.

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

Citations

46
Research on tumors segmentation based on image enhancement method DOI Creative Commons
Danyi Huang, Ziang Liu, Yizhou Li

et al.

Applied and Computational Engineering, Journal Year: 2024, Volume and Issue: 67(1), P. 334 - 340

Published: Aug. 14, 2024

One of the most effective ways to treat liver cancer is perform precise resection surgery, key step which includes digital image segmentation and its tumor. However, traditional parenchymal techniques often face several challenges in performing segmentation: lack precision, slow processing speed, computational burden. These shortcomings limit efficiency surgical planning execution. In this work, model initially describes detail a new enhancement algorithm that enhances features an by adaptively adjusting contrast brightness image. Then, deep learning-based network was introduced, specially trained on enhanced images optimize detection accuracy tumor regions. addition, multi-scale analysis have been incorporated into study, allowing analyze at different resolutions capture more nuanced features. presentation experimental results, study used 3Dircadb dataset test effectiveness proposed method. The results show compared with method, method using technology has significantly improved recall rate identification.

Language: Английский

Citations

24
Comparative analysis for accurate multi-classification of brain tumor based on significant deep learning models DOI
Mohamed S. Elhadidy,

Abdelrahman T. Elgohr,

Marwa El-Geneedy

et al.

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 188, P. 109872 - 109872

Published: Feb. 18, 2025

Language: Английский

Citations

3
A survey of image encryption algorithms based on chaotic system DOI
Pengfei Fang, Han Liu, Chengmao Wu

et al.

The Visual Computer, Journal Year: 2022, Volume and Issue: 39(5), P. 1975 - 2003

Published: April 7, 2022

Language: Английский

Citations

52
A new brain tumor diagnostic model: Selection of textural feature extraction algorithms and convolution neural network features with optimization algorithms DOI
Erdal Başaran

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 148, P. 105857 - 105857

Published: July 16, 2022

Language: Английский

Citations

43