Multi-Modal Brain Tumor Detection Using Deep Neural Network and Multiclass SVM

Medicina, Journal Year: 2022, Volume and Issue: 58(8), P. 1090 - 1090

Published: Aug. 12, 2022

Background and Objectives: Clinical diagnosis has become very significant in today's health system. The most serious disease the leading cause of mortality globally is brain cancer which a key research topic field medical imaging. examination prognosis tumors can be improved by an early precise based on magnetic resonance For computer-aided methods to assist radiologists proper detection tumors, imagery must detected, segmented, classified. Manual tumor monotonous error-prone procedure for radiologists; hence, it important implement automated method. As result, classification method presented. Materials Methods: proposed five steps. In first step, linear contrast stretching used determine edges source image. second custom 17-layered deep neural network architecture developed segmentation tumors. third modified MobileNetV2 feature extraction trained using transfer learning. fourth entropy-based controlled was along with multiclass support vector machine (M-SVM) best features selection. final M-SVM classification, identifies meningioma, glioma pituitary images. Results: demonstrated BraTS 2018 Figshare datasets. Experimental study shows that outperforms other both visually quantitatively, obtaining accuracy 97.47% 98.92%, respectively. Finally, we adopt eXplainable Artificial Intelligence (XAI) explain result. Conclusions: Our approach outperformed prior methods. These findings demonstrate obtained higher performance terms enhanced quantitative evaluation accuracy.

Language: Английский

---

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

---

Classifying Brain Tumors on Magnetic Resonance Imaging by Using Convolutional Neural Networks

Electronics, Journal Year: 2023, Volume and Issue: 12(4), P. 955 - 955

Published: Feb. 14, 2023

The study of neuroimaging is a very important tool in the diagnosis central nervous system tumors. This paper presents evaluation seven deep convolutional neural network (CNN) models for task brain tumor classification. A generic CNN model implemented and six pre-trained are studied. For this proposal, dataset utilized Msoud, which includes Fighshare, SARTAJ, Br35H datasets, containing 7023 MRI images. magnetic resonance imaging (MRI) belongs to four classes, three tumors, including Glioma, Meningioma, Pituitary, one class healthy brains. trained with input images several preprocessing strategies applied paper. evaluated Generic CNN, ResNet50, InceptionV3, InceptionResNetV2, Xception, MobileNetV2, EfficientNetB0. In comparison all models, best was obtained an average Accuracy 97.12%. development these techniques could help clinicians specializing early detection

Language: Английский

---

Application of Deep Neural Networks and Machine Learning algorithms for diagnosis of Brain tumour

2022 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), Journal Year: 2023, Volume and Issue: unknown, P. 106 - 111

Published: April 28, 2023

Brain tumours are regarded as a fatal condition that impacts the lives of so many people worldwide. The kind, location, and size brain tumour all affect how it will be treated. Hence, an automated diagnosis is needed for early detection. Convolutional neural networks (CNNs) have become increasingly desired in recent times tasks like these. In this work, we performed multi-class classification into different types over MRI scans. For these several convolutional used comparative analysis made better These include AlexNet, GoogleNet, VGG-19, Customized model, ensemble ML models. This certain parameters such optimization, learning Rate, count epochs, Loss. models gave promising results. were evaluated accuracy, F1-Score, Recall, Precision.

Language: Английский

---

Feature-enhanced deep learning technique with soft attention for MRI-based brain tumor classification

International Journal of Information Technology, Journal Year: 2024, Volume and Issue: 16(3), P. 1617 - 1626

Published: Jan. 20, 2024

Language: Английский

---

Brain tumor detection from images and comparison with transfer learning methods and 3-layer CNN

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Feb. 1, 2024

Abstract Health is very important for human life. In particular, the health of brain, which executive vital resource, important. Diagnosis provided by magnetic resonance imaging (MRI) devices, help decision makers in critical organs such as brain health. Images from these devices are a source big data artificial intelligence. This enables high performance image processing classification problems, subfield this study, we aim to classify tumors glioma, meningioma, and pituitary tumor MR images. Convolutional Neural Network (CNN) CNN-based inception-V3, EfficientNetB4, VGG19, transfer learning methods were used classification. F-score, recall, imprinting accuracy evaluate models. The best result was obtained with VGG16 98%, while F-score value same model 97%, Area Under Curve (AUC) 99%, recall precision 98%. CNN architecture models early diagnosis rapid treatment diseases.

Language: Английский

---

Advancements and Prospects of Machine Learning in Medical Diagnostics: Unveiling the Future of Diagnostic Precision

Archives of Computational Methods in Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: June 26, 2024

Language: Английский

---

Breast tumor localization and segmentation using machine learning techniques: Overview of datasets, findings, and methods

Computers in Biology and Medicine, Journal Year: 2022, Volume and Issue: 152, P. 106443 - 106443

Published: Dec. 19, 2022

Language: Английский

---

A model for multi-attack classification to improve intrusion detection performance using deep learning approaches

Measurement Sensors, Journal Year: 2023, Volume and Issue: 30, P. 100924 - 100924

Published: Oct. 21, 2023

This proposed model introduces novel deep learning methodologies. The objective here is to create a reliable intrusion detection mechanism help identify malicious attacks. Deep based solution framework developed consisting of three approaches. first approach Long-Short Term Memory Recurrent Neural Network (LSTM-RNN) with seven optimizer functions such as adamax, SGD, adagrad, adam, RMSprop, nadam and adadelta. evaluated on NSL-KDD dataset classified multi attack classification. has outperformed adamax in terms accuracy, rate low false alarm rate. results LSTM-RNN compared existing shallow machine models methodology (RNN), (LSTM-RNN), (DNN). are bench mark datasets KDD'99, NSL-KDD, UNSWNB15 datasets. self-learnt the features classifies classes multi-attack RNN, provide considerable performance other methods KDD'99 dataset.

Language: Английский

---

Grade Classification of Tumors from Brain Magnetic Resonance Images Using a Deep Learning Technique

Diagnostics, Journal Year: 2023, Volume and Issue: 13(6), P. 1153 - 1153

Published: March 17, 2023

To improve the accuracy of tumor identification, it is necessary to develop a reliable automated diagnostic method. In order precisely categorize brain tumors, researchers developed variety segmentation algorithms. Segmentation images generally recognized as one most challenging tasks in medical image processing. this article, novel detection and classification method was proposed. The proposed approach consisted many phases, including pre-processing MRI images, segmenting extracting features, classifying images. During portion an scan, adaptive filter utilized eliminate background noise. For feature extraction, local-binary grey level co-occurrence matrix (LBGLCM) used, for segmentation, enhanced fuzzy c-means clustering (EFCMC) used. After scan we used deep learning model classify into two groups: glioma normal. classifications were created using convolutional recurrent neural network (CRNN). technique improved from defined input dataset. scans REMBRANDT dataset, which 620 testing 2480 training sets, research. data demonstrate that newly outperformed its predecessors. CRNN strategy compared against BP, U-Net, ResNet, are three prevalent approaches currently being classification, system outcomes 98.17% accuracy, 91.34% specificity, 98.79% sensitivity.

Language: Английский

---