nnU-Net: Automated Design of Deep Learning Methods for Biomedical Image Segmentation | Paul Jäger
Biomedical imaging is a driver of scientific discovery and core component of medical care, currently stimulated by the field of deep learning. While semantic segmentation algorithms enable 3D image analysis and quantification in many applications, the design of respective specialised solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We propose nnU-Net, a deep learning framework that condenses the current domain knowledge and autonomously takes the key decisions required to transfer a basic architecture to different datasets and segmentation tasks. Without manual tuning, nnU-Net surpasses most specialised deep learning pipelines in 19 public international competitions and sets a new state of the art in the majority of the 49 tasks. The results demonstrate a vast hidden potential in the systematic adaptation of deep learning methods to different datasets. We make nnU-Net publicly available as an open-source tool that can effectively be used out-of-the-box, rendering state of the art segmentation accessible to non-experts and catalyzing scientific progress as a framework for automated method design.
https://www.dkfz.de/en/datascience/seminar/Jaeger.html
Видео nnU-Net: Automated Design of Deep Learning Methods for Biomedical Image Segmentation | Paul Jäger канала Computer Assisted Medical Interventions
https://www.dkfz.de/en/datascience/seminar/Jaeger.html
Видео nnU-Net: Automated Design of Deep Learning Methods for Biomedical Image Segmentation | Paul Jäger канала Computer Assisted Medical Interventions
Показать
Комментарии отсутствуют
Информация о видео
2 декабря 2020 г. 1:45:04
00:48:52
Другие видео канала
![Beyond the Patterns 29 - Fabian Isensee - nnU-Net: self-configuring deep learning image segmentation](https://i.ytimg.com/vi/C6tpnJRpt90/default.jpg)
![U-NET Paper Walkthrough](https://i.ytimg.com/vi/oLvmLJkmXuc/default.jpg)
![I Built An AI That Destroys Watermarks](https://i.ytimg.com/vi/Oq3FyfgawSc/default.jpg)
![nnU-Net : The no-new-Net for Automatic Segmentation](https://i.ytimg.com/vi/t6uFmH-mmF8/default.jpg)
![40000+ Data Science research papers with code | Latest Researchs | Machine Learning | Data Magic](https://i.ytimg.com/vi/DowJkAHnWwo/default.jpg)
![Discovering actionable interpretations from raw visual data: 2D to 3D | Andrea Vedaldi](https://i.ytimg.com/vi/vEWEEZ8n074/default.jpg)
![MICCAI 2021: Detecting When nnU-Net Models Fail Silently for Covid-19 Lung Lesion Segmentation](https://i.ytimg.com/vi/VjA_anxdABs/default.jpg)
![73 - Image Segmentation using U-Net - Part1 (What is U-net?)](https://i.ytimg.com/vi/azM57JuQpQI/default.jpg)
![Federated Learning for Healthcare – Collaborative AI without Sharing Patient Data | Nicola Rieke](https://i.ytimg.com/vi/xr_eJp3ctzw/default.jpg)
![Challenges @ MICCAI 2021 | Lena Maier-Hein & Annika Reinke](https://i.ytimg.com/vi/pACDviHdHMI/default.jpg)
![STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (ECCV'20)](https://i.ytimg.com/vi/E2Z-1HNO934/default.jpg)
![Paper Review Calls 011 -- U-Net: Convolutional Networks for Biomedical Image Segmentation](https://i.ytimg.com/vi/E1Y8HZcpm-I/default.jpg)
![MIT 6.S191 (2020): Introduction to Deep Learning](https://i.ytimg.com/vi/njKP3FqW3Sk/default.jpg)
![Yann LeCun - Power & Limits of Deep Learning](https://i.ytimg.com/vi/0tEhw5t6rhc/default.jpg)
![226 - U-Net vs Attention U-Net vs Attention Residual U-Net - should you care?](https://i.ytimg.com/vi/L5iV5BHkMzM/default.jpg)
![Bioimage Analysis 3: Segmentation (Anne Carpenter)](https://i.ytimg.com/vi/jLd2I2adQtw/default.jpg)
![Editing Faces using Artificial Intelligence](https://i.ytimg.com/vi/dCKbRCUyop8/default.jpg)
![Mask R-CNN Demo on Google Colab](https://i.ytimg.com/vi/l39TyxYH75E/default.jpg)
![Trustworthy machine learning in oncology | Florian Büttner](https://i.ytimg.com/vi/rCPz1o6mYko/default.jpg)
![Allen Cell Structure Segmenter Tutorial | Creating a new classic image segmentation workflow](https://i.ytimg.com/vi/Ynl_Yt9N8p4/default.jpg)