PNH segmentation pipelines based on nipype

An AI-powered deep learning system using VGG16 transfer learning to classify brain tumors (glioma, meningioma, pituitary, no tumor) from MRI scans. Built with TensorFlow, deployed on Render with Flask.

BrainSuite's structural, diffusion, and functional MRI processing pipelines with QC functionalities.

3D Slicer extension for glioma response assessment according to the RANO 2.0 criteria

Code for multi-echo combination for QSM MRI

🧠 Detect brain tumors from MRI images using a CNN model! 📸 This project preprocesses images, trains a model with ~2065 augmented samples, and achieves high accuracy. Features ROC analysis & single-image prediction. Perfect for medical AI enthusiasts! 🚀

🧠 MRI-ViT DL System – an medical analysis platform with 🤖 Vision-Transformer (Tumor/No Tumor detection 🔍), 🖼️ automated image processing (CLAHE/Skull-stripping/Denoising 🛠️), 🎨 modern web interface (React/TypeScript/Vite ⚛️), 📊 real-time confidence metrics 📈 and ⚡ FastAPI backend (PyTorch/timm/OpenCV 🐍) for precise brain tumor diagnosis🧩.

Deep learning solution for brain tumor segmentation & classification using U-Net, Attention U-Net, and advanced CNNs on the BRISC 2025 dataset. PyTorch implementation.

🧠 TumorClassifier-RAW-vs-DIP – an advanced 🔬 medical imaging platform 🏥 with 🤖 AI-powered brain tumor classification 🧬 (MRI analysis 📊), 🔄 image preprocessing pipeline (RAW vs DIP comparison 📈), ⚡ Linear SVM classifier 🎯 for tumor detection, 📊 performance metrics visualization 📉, interactive web 🌐 interface for real-time predictions.

Parameter-efficient brain lesion segmentation using MedSAM and LoRA on the MICCAI WMH Challenge dataset.

MRI Swarm is an enterprise-grade system built with Swarms, the leading production-ready multi-agent framework. It coordinates a team of specialized medical imaging agents to analyze MRI scans, with each agent focusing on different aspects of interpretation to provide detailed and accurate analysis.

AI-powered clinical decision support system for Alzheimer's disease detection using Deep Learning, Explainable AI (Grad-CAM), and RAG-enhanced LLM. Full-stack application with React frontend and FastAPI backend.

A curated list of measures, tools, and references for MRI quality control (QC).

Deep Learning system for early detection of Mild Cognitive Impairment from brain MRI | ResNet50 + DenseNet121 | Published at RAET'26 National Conference

Deep learning research project utilizing CNN architectures for the classification of brain tumors from MRI scans.

🧠 Brain-Tumor-Detection 📷 is a project that uses machine learning and computer vision techniques to automatically detect brain tumors from MRI images. 🔍🤖

Converts breast MRI volumes (DICOM) into compact 64×64×64 micro-cubes with 3 channels (hybrid structure, denoised heterogeneity, and registered kinetics), packed with physical metadata for efficient Green-AI virtual risk phenotype profiling.

NeuroScanNet is a deep learning-based brain tumor classification model using EfficientNetB1 and Grad-CAM for high accuracy and interpretability. It classifies MRI scans into four tumor types with 98.85% accuracy.

3D Brain Tumor Segmentation using U-Net and MONAI on the BraTS 2020 dataset to optimize segmentation performance across multiple MRI modalities.

Clinical-grade brain tumor diagnostics powered by interpretable deep learning (ResNet-50 + Grad-CAM). Features 3D spatial mapping, BioMistral narratives, and high-fidelity reporting. Engineered for medical transparency. #NeuroOncology #DiagnosticAI