CNN-based Approach for Enhancing Brain Tumor Image Classification Accuracy

International journal of engineering. Transactions B: Applications, Год журнала: 2024, Номер 37(5), С. 984 - 996

Опубликована: Янв. 1, 2024

Brain tumors are one of the deadliest diseases in world. This disease can attack anyone regardless gender or certain age groups. The diagnosis brain is carried out by manually identifying images resulting from Computerized Tomography Scan Magnetic Resonance Imaging, making it possible for diagnostic errors to occur. In addition, be made using biopsy techniques. technique very accurate but takes a long time, around 10 15 days and involves lot equipment medical personnel. Based on this, machine learning technology needed which classify based produced MRI. research aims increase accuracy previous classification so that do not occur tumors. method used this Convolutional Neural Network AlexNet Google Net architectures. results obtained an 98% architecture 96% GoogleNet. result higher when compared with research. finding reduce computational burden during model training. help physicians diagnose quickly accurately.

Язык: Английский

---

Segmenting the Lesion Area of Brain Tumor using Convolutional Neural Networks and Fuzzy K-Means Clustering

International journal of engineering. Transactions B: Applications, Год журнала: 2023, Номер 36(8), С. 1556 - 1568

Опубликована: Янв. 1, 2023

Brain tumor Segmentation is one of the most crucial methods medical image processing. Non-automatic segmentations are broadly used in clinical diagnosis and medication. However, this kind segmentation does not have accuracy images, especially terms brain tumors, it provides a low level reliability. The primary objective paper to develop methodology for segmentation. In paper, combination Convolutional Neural Network Fuzzy K-means algorithm has been presented segment lesion area tumor. It contains three phases, Image preprocessing reduce computational complexity, Attribute extraction selection Segmentation. At first, database images pre-processed using adaptive filters wavelet transform order recover from noise state complexity. Then feature performed by proposed deep neural network. Finally, processed through K-Means region separately. innovation article related implementation network with optimal parameters, identification features removal unrelated repetitive aim observing subset that describe problem well minimal reduction efficiency. This results reduced sets, storage data collection resources during operation, overall limit requirements. approach verified on BRATS dataset produces 98.64%, sensitivity 100% specificity 99%.

Язык: Английский

---

Optimizing Brain Tumor Recognition with Ensemble support Vector-based Local Coati Algorithm and CNN Feature Extraction

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Янв. 16, 2024

Abstract Nowadays, brain tumor (BT) recognition has become a common phenomenon in the healthcare industry. In medical system,BT identification and classification can take significant part diagnostics considerations of patients. BT is characterized as an abnormal mass tissue which cells proliferate unexpectedly with no control over cell proliferation. recent years, improvements machine learning (ML), particularly deep (DL) procedures, have shown potential for mechanizing improving these undertakings by utilizing imaging information. Also, we examine difficulties probabilities this field, including information shortage, model interpretability, moral contemplations. To overcome challenges Ensemble support Vector-based Local Coati (ESV-LC) Algorithm employed to identify classify disease For optimal classification, features need be extracted achieved employing Convolutional Neural network (CNN). accurately BT, Support Vector Machine (ESVM) involved, enhances performance, hyperparameter tuning performed through Search Optimization. The Brain Tumor Image Dataset Figshare dataset are utilized identification. performance metrics like Accuracy, Precision, Sensitivity, Specificity, F1-score evaluated, where accuracy achieves value 98.3%, sensitivity 97.6%, precision 97.7%, specificity 98.1%, 96.7% respectively.

Язык: Английский

---

Survey of Brain Tumor Image Segmentation Using Artificial Intelligence Techniques

International Research Journal of Innovations in Engineering and Technology, Год журнала: 2023, Номер 07(12), С. 2581 - 3048

Опубликована: Янв. 1, 2023

A brain tumor is an abnormal tissue mass resulting from cell growth.Brain tumors often reduce the length of a person's life and may cause death in advanced cases.Physician teams rely on early detection accurate placement by magnetic resonance imaging to assess tumor's pace accuracy.Treatment, as well determining causes injury cells, further aids reducing any potential problems patient could experience.Segmenting images taken important for neurosurgeons.It not easy matter requires high experience radiologists.Therefore, there need expert intelligent system segment part medication that expert, designed address this task.One most promising innovative approaches medical industry artificial intelligence.Automatically identifying aberrant region made possible application intelligence imaging, which dependent picture interpretation.The goal research provide brief survey automatic methods segmentation using methods, includes use machine learning deep include several including (CNN, RES NET, MOBILE NET etc) are applied field, identify obtain results images.

Язык: Английский

---