@MatjesG
Joined September 2012
  • Tweets8
  • Following365
  • Followers17
.@MatjesG @chris_flath deepflash2 is a deep learning method to facilitate the segmentation of ambiguous bioimages nature.com/articles/s41467-0… #BiotechNatureComms

Deep learning-enabled segmentation of ambiguous bioimages with deepflash2

Nature Communications - The signal-to-noise ratio in bioimages is often low, which is problematic for segmentation. Here the authors report a deep learning method, deepflash2, to facilitate the...

nature.com
1
4
2
9
6,809
A huge thank you to everyone who supported @PSodmann and me on our #kaggle journey! We won the Innovation award and a #kaggle gold medal 🥇! I am working on an updated version of #deepflash2 and a paper! Stay tuned!
Universität Würzburg #UniWürzburg@Uni_WUE9 Jun 2021
Congratulations @PSodmann @MatjesG! They were awarded @kaggle @_hubmap innovation award, endowed with 10.000 US dollars! 🍾 With their #AI tool #deepflash2 microscopic images of tissue sections can now be analyzed much more easily. ➡️go.uniwue.de/deepflash2 #WisskommJMU
1
6
more replies
@Stonematz @tonigreif
1
1
@Adrian05775238
1
Matthias Griebel retweeted
Phil Sodmann@PSodmann11 May 2021
Replying to @MatjesG
@MatjesG and I just won our first Kaggle gold medal in the HuBMAP - Hacking the Kidney challenge with a solid 10th place. We wrote a notebook about our solution: kaggle.com/matjes/hubmap-dee…

HuBMAP deepflash2 [judge price]

Explore and run AI code with Kaggle Notebooks | Using data from HuBMAP - Hacking the Kidney

kaggle.com
1
2
6
Matthias Griebel retweeted
eLife - the journal@eLife4 Dec 2020
Training deep learning algorithms with the pooled knowledge of multiple experts improves the quality of bioimage analysis elifesciences.org/digests/59…

Learning to annotate

Combining deep learning models trained on multiple humans improves the analysis of fluorescence microscopy datasets.

elifesciences.org
8
2
33
Load more