CellViT is a Vision Transformer, for automated instance segmentation of cell nuclei in H&E-stained tissue images, achieving state-of-the-art performance on the challenging PanNuke dataset through large-scale in-domain and out-of-domain pre-training of Vision Transformers.
The k-Radiomics project is aiming to enhance diagnosis and treatment for patients by utilizing MRI raw data.
Full Body Anatomy Segmentation
We present a method to create automated anatomy segmentation datasets using nnU-Net-based labeling and refinement, yielding a comprehensive CT scan dataset with voxel-level labels for 142 anatomical structures across 533 volumes, validated by experts and Deep Learning benchmarks.
Chest X-Ray Anatomy Segmentation
Chest X-Ray Anatomy Segmentation provides a way to generate fine-grained segmentations and extract understandable features of Chest X-Rays.
We released state-of-the-art German language models developed in a joint effort between the University of Florida, NVIDIA, and IKIM. The models range in size from 122M to 750M parameters.
KI Translation Essen (KITE)
KITE is a modern research infrastructure for the translation of artificial intelligence (AI) applications to the point-of-care (PoC). This project is funded by the European Union as part of the Union’s response to the COVID-19 pandemic.
Medical Applications with Disentanglement
👋 Welcome to the MICCAI MAD Workshop 2022.
RACOON: Building a nationwide radiological infrastructure for collaborative imaging research
Cranioplasty is the surgical process where a skull defect, caused by a brain tumor surgery or trauma, is repaired using a cranial implant, which must fit precisely against the borders of the skull defect as replacement to the removed cranial bone. AutoImplant aims at the automatic design of cranial implants with AI-based approaches.
Developing a Head Mounted Display Augmented Reality tool for Maxillofacial surgery guidance. Improving spatial awareness by real time alignment of virtual scans and real world patients.