mri-classification

Deep learning for brain tumor MRI: detection (99.4%) and 4-class typing (94.75%) via EfficientNet transfer learning + Grad-CAM.

Deep Multimodal Guidance for Medical Image Classification: https://arxiv.org/pdf/2203.05683.pdf

This repository introduces a short project about Transfer Learning for Classification of MRI Images.

MRI modality(T1, T2, FLAIR) classification model with modified ResNet-50. Hanyang univ. dep. of biomedical engineering graduation project.

Machine learning model that is able to detect and classify brain tumors in MRI scans

Brain Tumor MRI Classification is an end‑to‑end deep learning project that trains multiple models (ResNet50, VGG16, a custom CNN, SVM, and Random Forest) to automatically detect and classify brain tumors from MRI scans into four classes: glioma, meningioma, pituitary, and no tumor.

Brain tumor classification from MRI images using NVIDIA TAO Toolkit.

Brain Pathology Using Deep Learning

A Flask-based web app for brain tumour classification from MRI scans using pre-trained deep learning models. Supports Glioma, Meningioma, Pituitary, and No Tumor detection with model selection and confidence scoring.

Knee bone and cartilage segmentation in 3D MRI

MRI image classifier and diagnostic analysis tool for medical imaging processing.

AI-based system for brain tumor classification from MRI images with integrated explainability and uncertainty estimation. Provides interpretable predictions using Grad-CAM and generates structured clinical insights through an LLM-powered pipeline.

Deep learning system for Alzheimer's disease detection from brain MRI scans using transfer learning with pre-trained CNNs (MobileNet, VGG, InceptionV3), classifies into 3 stages (AD/CI/CN)

Enhanced MRI Brain Tumor Detection using a Hybrid Deep Learning + Machine Learning model. Combines MobileNetV2 & SVM to classify tumors (Glioma, Meningioma, Pituitary, No Tumor) from contrast MRI. Achieves ~93% accuracy via transfer learning & augmentation.

AI-assisted medical imaging tool: A deep learning Computer Vision model built to detect brain tumors from MRI scans with high clinical precision.

A full MRI-based brain tumor classification system built with Random Forests and Flask. It recognizes normal, glioma, meningioma, and pituitary tumor images and allows users to upload external scans for instant prediction and analysis.

Automating medical diagnosis support: A machine learning pipeline and web interface that analyzes 3D brain MRI scans to accurately distinguish between Multiple Sclerosis and Cerebral Small Vessel Disease.

Hybrid Quantum–Classical Neural Network (QCNN) for automated brain tumour detection using MRI images. Combines EfficientNet-B0 feature extraction with a 4-qubit PennyLane quantum layer and includes a Gradio-based prediction interface.

Hybrid Quantum–Classical model for brain tumor classification using Quantum FiLM modulation and ResNet-18. Supports multi-class MRI tumor detection with quantum circuit integration.

Attention-based Deep Learning Approaches in Brain Tumor Image Analysis: A Mini Review