Use of state of the art Convolutional neural network architectures including 3D UNet, 3D VNet and 2D UNets for Brain Tumor Segmentation and using segmented image features for Survival Prediction of patients through deep neural networks.
A brain MRI segmentation tool that provides accurate robust segmentation of problematic brain regions across the neurodegenerative spectrum. The methodology is generalisable to perform well with the typical variance in MRI acquisition parameters and other factors that influence image contrast.
TensorFlow implementation of our paper: "Automated detection of aggressive and indolent prostate cancer on magnetic resonance imaging [Medical Physics 2021]".
In this project I'm going to segment Tumor in MRI brain Images with a UNET which is based on Keras. The dataset is available online on Kaggle, and the algorithm provided 99% accuracy with a validation loss of 0.11 in just 10 epochs.
🧠 3D MEDICAL IMAGE SEGMENTATION 🧠 FDA VALIDATION PLAN 🧠 Curate a dataset of brain MRIs, train a segmentation on a CNN, and integrate this into a clinical network to quantify hippocampal volume for Alzheimer's progression 🧠