Gregor Koehler (@GregorKoe) profile picture

PhD Student @mic_dkfz. Currently at WACV‘24

Joined April 2017
Photo by Gregor Koehler (@GregorKoe)Photo by Gregor Koehler (@GregorKoe)Photo by Gregor Koehler (@GregorKoe)Photo by Gregor Koehler (@GregorKoe)Photo by Gregor Koehler (@GregorKoe)
Gregor Koehler retweeted
🌟 Join us to explore RETFound, a Foundation Model for Ophthalmology, as featured in Nature, with Prof. @pearsekeane. Discover its impact on diverse clinical tasks. 🤖👁️ #AIinHealthcare #FoundationModels #HeidelbergAI 🔗 Details & Registration: heidelberg.ai/2024/02/06/pea…
1
7
1
13
1,656
Gregor Koehler retweeted
🌐 Join us for a Special Talk on AI and Infectious Disease Outbreak Prediction with Prof. Joacim Rocklöv, leading Germany's first AI lab in this field. Discover how AI can revolutionize disease surveillance and prediction! 🔗 Details & Registration: heidelberg.ai/2024/01/31/joa…
1
7
6
972
WACV 2024 has started! Really enjoyed the keynote by @dimadamen on egocentric video understanding. Those datasets seem really cool & worth exploring!
6
225
Gregor Koehler retweeted
Thanks a ton for awarding me the @PyTorch superhero award at the conference! It really made my day, and it was great seeing so many community members in real life. You all are amazing!
117
76
20
2,153
132,278
📢 Exciting News! 🎉 I'm thrilled to announce that I'll be presenting my paper "MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation" at #MICCAI2023. Join my oral presentation on Wednesday at 8:15 AM and the poster session at 9:30 AM (Poster W-05-080)
5
1
30
1,821
Gregor Koehler retweeted
💼 Packing for #ICCV2023 to present the M2T paper :) See you in Paris?
1/ Excited to share that our work on masked transformers for compression has been accepted at #ICCV2023! We show two things: a) how a simple transformer based architecture can lead to state-of-the-art image compression results: arxiv.org/abs/2304.07313
5
21
2,917
TotalSegmentator v2 is here: - 33 new classes - up to 32x faster runtime on CPU - improved label quality - larger training dataset (n=1559) - uses nnU-Net v2 Details: github.com/wasserth/TotalSeg…
4
30
4
142
11,829
Missed our latest heidelberg.ai talk on "Learning dynamical laws from data" by @k__niki? Now you can (re)watch the talk: youtu.be/zevj234NsBM Thanks again Niki for this really nice talk!
4
8
1,326
Gregor Koehler retweeted
🏆Congrats to Luca Deininger for receiving an award for the best oral presentation at this year's "14. Annual Scientific Symposium on Ultrahigh Field Magnetic Resonance"!🌟 #mri #machinelearning #segmentation
1
2
351
We published our dataset (doi.org/10.5281/zenodo.65561…) making it the largest openly available dataset of child brain MRIs aging 0 to 36 months.
3
45
149
15,799
Gregor Koehler retweeted
3/3 #MICCAI 2023 paper in early accept: “Transformer-driven Scaling of ConvNets for Medical Image Segmentation”. Check out the preprint here: arxiv.org/abs/2303.09975
1
2
1
13
3,255
Gregor Koehler retweeted
Here comes @MICCAI_Society 2023 early acceptance paper 1/3 on "Shape-based pose estimation for automatic standard views of the knee". Check out the preprint here: arxiv.org/abs/2305.16717
1
2
12
1,128
Gregor Koehler retweeted
Was in Germany yesterday to talk about compression and eat pretzels 🥨 Thanks to fraiburg.ai and @jkhfranke for hosting this, it was very exciting!
1
13
1,141
Gregor Koehler retweeted
This is HUGE. Google's new medical LLM, Med-PaLM 2, scored 86.5% on the medical exam MedQA 🤯 Not only that, but a panel of 15 human doctors preferred Med-PaLM 2's answers over real doctor answers across 1066 standardized questions. Does this mean that doctors are going to be replaced? No. But I am a believer that AI combined with human knowledge and experience would make the most powerful duo.
70
322
73
1,500
624,587
Still in a good mood while our future is currently being decided on by the @helmholtz_image reviewers next door😅.
2
5
1
48
3,307
Gregor Koehler retweeted
Shoutout to the legend who answers literally every single PyTorch question out there!
54
191
42
3,881
645,830
Excited to present some of our work @NeurIPSConf this week. Today at #MedNeurIPS, @TimRaedsch will talk about the importance of labeling instructions (arxiv.org/abs/2207.09899), and @annika_reinke1 will present #MetricsReloaded (arxiv.org/abs/2206.01653).
Gregor Koehler retweeted
Markus Bujotzek & Daniel Walther from MIC took part at @CodeWeekEU at @TECHNOSEUM and explained AI to kids and what it has to do with medical image computing - also adults were curious and asked a lot of questions! 🙂 #CodeWeek #YoungScientist
2
10
Gregor Koehler retweeted
New paper is out with participation from MIC @maierhein @KlausKades @GregorKoe @DataScienceDKFZ
Deep Learning–based Assessment of Oncologic Outcomes from Natural Language Processing of Structured Radiology Reports doi.org/10.1148/ryai.220055 @MatthiasAFink @uniklinik_hd @UKHD_radonc #NLP #MachineLearning #cancer #IJCAI2022
3
6
Gregor Koehler retweeted
What a performance! 🤯 @DKFZ_CAMI_lab & MIC cycled a total of 9.029,4 km for @STADTRADELN, more than half of entire @DKFZ. 5 people from our labs are in Top10 - kudos to all for this achievement. Keep up the spirit, for cancer prevention and a better climate! #Health #saveco2
1
2
12