相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Multidisciplinary Sciences
Zhongxiao Li et al.
Summary: This study developed an end-to-end deep learning architecture called ViT-WSI for brain tumor analysis, which can classify the major types and subtypes of primary brain tumors. By using gradient-based attribution analysis, ViT-WSI is able to discover histopathological features for diagnosis. Additionally, ViT-WSI has shown high predictive power for inferring the status of three glioma molecular markers directly from H&E-stained histopathological images.
Article
Engineering, Biomedical
Dhiraj Maji et al.
Summary: The study introduces a new deep learning generator architecture ARU-GD for automatic segmentation of brain tumors in MRI, which has the capability to guide the learning process of each decoder layer and generate better feature maps. The model outperformed popular deep learning models and achieved high scores on unseen high-grade glioma test data, demonstrating its effectiveness in brain tumor segmentation.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Information Systems
V. V. S. Sasank et al.
Summary: The article discusses the importance of brain tumor classification in improving treatment outcomes, proposing a novel and efficient strategy for classifying brain MRI images into four grades. The method involves preprocessing, segmenting, extracting features, and utilizing a Hybrid Deep Neural Network for classification. This technique is compared with existing methods to demonstrate its overall efficiency.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Interdisciplinary Applications
Dillip Ranjan Nayak et al.
Summary: In this study, a completely autonomous brain tumour segmentation approach based on deep neural networks (DNNs) is proposed, using a unique CNN architecture. The parameters of the CNN model are tuned using advanced optimization techniques, achieving accurate detection of tumour portions in MRI images.
Article
Mathematical & Computational Biology
Ebrahim Mohammed Senan et al.
Summary: Cancer, as a highly aggressive and destructive disease, reduces the average lifespan of patients. Misdiagnosed brain tumors result in ineffective treatment, lowering the chances of survival. This study explores the combination of deep learning and traditional machine learning techniques to aid in the accurate early diagnosis of brain tumors. The use of computer-aided diagnostic systems, specifically deep convolutional layers, demonstrates significant success in extracting distinguishing features. The results show that the hybrid technique of AlexNet and SVM achieves the highest accuracy, sensitivity, and specificity, emphasizing its potential importance in medical diagnosis.
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2022)
Article
Engineering, Biomedical
M. O. Khairandish et al.
Summary: This research paper proposes a hybrid model that combines Convolution Neural Network (CNN) and Support Vector Machine (SVM) for classifying Benign and Malignant brain tumors in MRI images. The hybrid model achieves an overall accuracy of 98.4959%, demonstrating improved effectiveness compared to previous models.
Article
Mathematical & Computational Biology
Sepideh Molaei et al.
Summary: This study proposes a comprehensive approach to diagnose benign and malignant brain tumors using magnetic resonance imaging data. The experimental results show that the proposed method achieves significant results in accuracy.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Mathematical & Computational Biology
Hareem Kibriya et al.
Summary: Brain tumors are difficult to detect and classify accurately. In this paper, a novel method based on deep feature fusion is proposed to improve the classification performance of brain tumors. By fusing the deep features obtained from different models, the proposed method achieves higher accuracy compared to existing systems. The method is trained and evaluated on a large dataset of magnetic resonance images.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Thanh Han-Trong et al.
Summary: This paper proposes a system that effectively identifies brain tumors on MRI images using artificial intelligence algorithms and ADAS optimization function. The system achieves this by normalizing MRI images, applying deep convolutional neural networks, and constructing predictive models using ADAS optimization function, resulting in F1-score values of over 94%.
APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING
(2022)
Article
Mathematical & Computational Biology
Tejas Shelatkar et al.
Summary: This study proposes a deep learning approach based on YOLOv5 model for the identification and classification of brain tumors using MRI scans. The model shows successful detection of brain tumors according to the testing results.
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
(2022)
Article
Computer Science, Hardware & Architecture
Ramdas Vankdothu et al.
Summary: Brain tumors are often diagnosed malignant tumors, and detecting and classifying them is challenging. This paper proposes an IoT computational system based on deep learning for detecting brain tumors in MRI images. The system combines CNN with LSTM to improve image classification performance. Experimental results demonstrate that the proposed model outperforms earlier CNN and RNN models in terms of accuracy.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Physics, Multidisciplinary
Mohammed Rasool et al.
Summary: This study introduced a new hybrid CNN-based architecture to classify three brain tumor types through MRI images. By combining the Google-Net model and SVM classifier, the recognition accuracy reached a high level.
Article
Computer Science, Information Systems
Prakash Mohan et al.
Summary: This study aims to develop an automated model for the detection and classification of brain tumors based on deep learning using MRI data. The method involves preprocessing, segmentation, feature extraction, and classification, and incorporates advanced techniques and approaches to improve diagnostic performance.
Article
Mathematical & Computational Biology
Usman Zahid et al.
Summary: This work presents a fully automated design for brain tumor classification, achieving higher accuracy and reducing computational overhead through the use of deep learning features and optimization algorithms.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Ayesha Younis et al.
Summary: This study aims to use deep learning and neural network classification algorithms to help detect and intervene in brain tumors, proposing an effective method for brain tumor detection using the VGG 16 architecture and MRI images. The method outperforms conventional approaches and achieves high accuracy.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Analytical
Naeem Ullah et al.
Summary: Early detection of brain tumors is crucial for clinical practice and survival rate. Traditional manual detection methods have limitations, thus autonomous diagnostic tools are needed. This research presents a novel deep learning model, TumorResNet, which achieves superior performance in brain tumor detection.
Article
Medicine, General & Internal
Sarmad Maqsood et al.
Summary: Brain cancer is a significant clinical diagnosis issue in the healthcare system. This paper proposes an accurate method for brain tumor detection and classification.
MEDICINA-LITHUANIA
(2022)
Article
Computer Science, Software Engineering
Sasmitha Dasanayaka et al.
Summary: Tumour-Analyser is a web application that classifies brain tumours using MRI and whole slide imaging with DenseNet and ResNet models. It provides interpretability to overcome the black-box nature and lack of transparency in deep learning models.
Article
Computer Science, Information Systems
Hasnain Ali Shah et al.
Summary: A brain tumor is a disorder caused by the growth of abnormal brain cells. MRI images can be used to identify these tumors. The use of deep learning models, specifically the proposed EfficientNet-B0 model, can efficiently classify and detect brain tumor images, outperforming other state-of-the-art models in terms of multiple performance metrics.
Article
Engineering, Biomedical
Mohammad Ashraf Ottom et al.
Summary: This paper presents a novel framework for segmenting brain tumors in MR images using deep neural networks and data augmentation strategies. The experimental results demonstrate high performance of the proposed method in localizing and segmenting brain tumors in MR images.
IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE
(2022)
Article
Computer Science, Hardware & Architecture
Ozlem Polat et al.
Summary: This study proposes a solution for classifying brain tumors in MR images using transfer learning networks and tests the performance of various neural networks under different optimization algorithms. The results show that the proposed transfer learning methods can achieve high performance in classifying the most common brain tumors.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Anatomy & Morphology
Amjad Rehman Khan et al.
Summary: This article presents a deep learning approach for brain tumor classification in medical field using MRI data analysis, image segmentation, and fine-tuned VGG19 model classification. The proposed technique shows improved accuracy and efficiency compared to existing state-of-the-art approaches.
MICROSCOPY RESEARCH AND TECHNIQUE
(2021)
Article
Chemistry, Analytical
Muhammad Nasir Ullah et al.
Summary: An integrated front-end data acquisition circuit for a hybrid ultrasound-gamma probe was proposed, enabling simultaneous data acquisition from both systems with good performance.
Article
Medicine, General & Internal
Momina Masood et al.
Summary: This study proposes a method using custom Mask RCNN for precise classification and segmentation of brain tumors, trained via transfer learning. The model achieved higher accuracy on two benchmark datasets compared to traditional methods.
Review
Clinical Neurology
Abdelrhman Enayet
Summary: Brain tumors in the first two years of life present a challenging group mainly consisting of fetal/congenital tumors and infantile tumors. The main histopathologies include glial tumors, choroid plexus tumors, medulloblastoma, and other embryonal tumors, teratoma, and ependymoma. Management involves surgical excision as the mainline treatment, with chemotherapy for residual or malignant cases and the aim to delay radiotherapy beyond the age of three years. Aggressive behavior and limited management options highlight the need for individualized multidisciplinary approaches and future studies targeting underlying molecular biology for improved outcomes.
EGYPTIAN JOURNAL OF NEUROSURGERY
(2021)
Article
Engineering, Electrical & Electronic
Arshia Rehman et al.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2020)
Article
Engineering, Biomedical
Raheleh Hashemzehi et al.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2020)
Article
Computer Science, Information Systems
Zar Nawab Khan Swati et al.
Proceedings Paper
Engineering, Biomedical
Nyoman Abiwinanda et al.
WORLD CONGRESS ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING 2018, VOL 1
(2019)
Article
Engineering, Multidisciplinary
Ercan Avsar et al.
TEHNICKI GLASNIK-TECHNICAL JOURNAL
(2019)
