2023 · 13 citations · 6 references
ComputingComputer ScienceRadiologyComputer VisionDiagnostic ImagingMachine LearningBrain TumorsCancer DetectionDeep LearningMedical Image AnalysisMedical ImagingTumor DetectionBrain Tumor DiagnosisConvolutional Neural Network DetectionConvolutional Neural NetworksDeep Learning-based ClassificationDeep Learning-based DiagnosisImage-based Tumor DetectionMagnetic Resonance Image FeaturesTumor Segmentation
Brain tumors constitute a grave medical condition necessitating precise and prompt diagnosis to ensure efficacious treatment. Convolutional Neural Networks (CNNs) exhibit promising potential in accurately detecting brain tumors from medical imagery. This paper introduces a CNN-grounded strategy for detecting brain tumors via Magnetic Resonance Imaging (MRI) scans. The method we propose encompasses preprocessing MRI scans to extricate pertinent features and segment the tumorafflicted region. These processed images subsequently fuel a CNN model, comprising multiple convolutional strata for feature extraction, coupled with pooling strata to curtail spatial dimensions. The derived features then traverse through a fully connected layer for classification. Our method's efficacy is assessed using an accessible repository of MRI scans featuring brain tumors. Our experiments reveal that the CNN model proposed attains a 95% accuracy rate, accompanied by a 93% sensitivity rate, and a 96% specificity rate in brain tumor detection. These findings underscore our method's proficiency in brain tumor detection employing CNNs.
6
Mahmoud Khaled Abd-Ellah, Ali Ismail Awad, Ashraf A. M. Khalaf et al. · EURASIP Journal on Image and Video Processing · 2018 · 168 citations · Full text
Medicine, Computer Science, Oncology +17