Segmentation deep learning ALgorithm based on MONai toolbox: single and multi-label segmentation software developed by QIMP team-Vienna.

Winning Solution for Vesuvius Challenge First Title. Custom MiniUNETR 3D architecture for ink detection in carbonized scrolls.

This project compares the performance of UNet, ResUNet, SegResNet, and UNETR architectures on the 2017 LiTS dataset for liver tumor segmentation. We evaluate segmentation accuracy using the DICE score to identify key factors for effective tumor segmentation.

This repository demonstrates the utilization of UNETR for brain tumor segmentation.

Multiclass Image Segmentation on Human Face Segmentation in TensorFlow

Human Hair Segmentation using the UNETR (U-Net Transformers) in TensorFlow

AI Toolkit for Healthcare Imaging in Keras 3

Abdomen 3D Segmentation Using UNETR: Tool for segmenting abdominal organs using the UNETR model. Combines Transformers with CNNs for precise 3D segmentation. Dive into medical imaging! 🏥✨🔍

GUNETR_pplus: Gradient enhanced UNETR_pplus with MSD liver segmentation

GUNETR_pplus: Gradient enhanced UNETR_pplus with tumor segmentation

Implementation of transformer-based 3d segmentation model

Custom deep learning model for 3D medical image segmentation, enhancing the UNETR architecture with lightweight attention gates on its skip connections. This proof-of-concept aimed to improve how the model combines features from different resolution levels. Experiments on MRI scans suggest this could be effective with larger training setups.

Implementation of knowledge distillation on a Mixture of Experts based UNETR to scale up a model horizontally and scale it down with KD.

Machine Learning for Medical Image Processing. Project done for Charité, the university hospital of Berlin. The aim was to segment coronary arteries and then extract a graph from it, in order to aid detection of coronary artery disease (CAD).