Useful functions and pipelines for brain tumor segmentation.

Optimized U-Net for Brain Tumor Segmentation

Brain Segmentation

We segmented the Brain tumor using Brats dataset and as we know it is in 3D format we used the slicing method in which we slice the images in 2D form according to its 3 axis and then giving the model for training then combining waits to segment brain tumor. We used UNET model for training our dataset.

Multimodal Brain Tumor Segmentation Boosted by Monomodal Normal Brain Images

Implementation of the Mean Teacher method for brain lesion segmentation based on DeepMedic, from paper published in IPMI 2019

Medical Image Analysis(UCAS 2024 Spring)

LHU-Net: A Light Hybrid U-Net for Cost-efficient, High-performance Volumetric Medical Image Segmentation

Brain Tumor Segmentation Pipeline for BraTS Challenge

Interactive Brain Tumor Segmentation with FocalClick and CDNet

[MIDL 2023] MMCFormer: Missing Modality Compensation Transformer for Brain Tumor Segmentation

Code for automated brain tumor segmentation from MRI scans using CNNs with attention mechanisms, deep supervision, and Swin-Transformers. Based on my Master's dissertation project at Brunel University, it features 3 deep learning models, showcasing integration of advanced techniques in medical image analysis.

[MICCAI 2022 Best Paper Finalist] Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi Supervised Segmentation

Official BraTS 2023 Segmentation Performance Metrics

A modular, 3D unet built in keras for 3D medical image segmentation. Also includes useful classes for extracting and training on 3D patches for data augmentation or memory efficiency.

Official and maintained implementation of the paper "OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data" [BMVC 2021].

Creating a U-Net In PyTorch to segment the BraTS 2020 dataset