RT @EurRadiology: 🥇 The most cited 2023 #EuropeanRadiologyExperimental article compared four #DeepLearning approaches trained on various da…
RT @EurRadiology: 🥇 The most cited 2023 #EuropeanRadiologyExperimental article compared four #DeepLearning approaches trained on various da…
🥇 The most cited 2023 #EuropeanRadiologyExperimental article compared four #DeepLearning approaches trained on various datasets related to lung segmentation, illustrating importance of data diversity. (@joh_hof et al., @georg, @contextflow_rad) Kudos! 🔗h
RT @contextflow_rad: Congratulations to Chief Scientist @georg, Head of R&D @joh_hof and Jeanny Pan from the Computational Imaging Research…
RT @contextflow_rad: Congratulations to Chief Scientist @georg, Head of R&D @joh_hof and Jeanny Pan from the Computational Imaging Research…
RT @contextflow_rad: Congratulations to Chief Scientist @georg, Head of R&D @joh_hof and Jeanny Pan from the Computational Imaging Research…
RT @contextflow_rad: Congratulations to Chief Scientist @georg, Head of R&D @joh_hof and Jeanny Pan from the Computational Imaging Research…
RT @contextflow_rad: Congratulations to Chief Scientist @georg, Head of R&D @joh_hof and Jeanny Pan from the Computational Imaging Research…
Congratulations to Chief Scientist @georg, Head of R&D @joh_hof and Jeanny Pan from the Computational Imaging Research Lab at the @MedUni_Wien for their "Most Cited Paper" award from @myESR! Read more about their lung segmentation work here https://t.
RT @EurRadiology: 🥇 And finally, our sincere congratulations to the most cited #EuropeanRadiologyExperimental article in 2022, which highli…
RT @joh_hof: Super happy and proud that we have created something that has been useful for so many and facilitates so much downstream resea…
RT @joh_hof: Super happy and proud that we have created something that has been useful for so many and facilitates so much downstream resea…
Super happy and proud that we have created something that has been useful for so many and facilitates so much downstream research 🙂
🥇 And finally, our sincere congratulations to the most cited #EuropeanRadiologyExperimental article in 2022, which highlights the importance of #data diversity when developing and training #DeepLearning models! 🎉 Well done to @joh_hof et al.! 🔗 https://t
RT @ESR_Journals: 🥇 The most downloaded #EurRadiolExp of 2021 (over 6,000 downloads!) showed that the accuracy and reliability of lung 🫁 se…
🎉😊
RT @cir_lab: Congratulations @joh_hof @HProsch et al in most downloaded paper of 2021 in European Radiology Experimental! @MedUni_Wien #ECR…
RT @cir_lab: Congratulations @joh_hof @HProsch et al in most downloaded paper of 2021 in European Radiology Experimental! @MedUni_Wien #ECR…
Congratulations @joh_hof @HProsch et al in most downloaded paper of 2021 in European Radiology Experimental! @MedUni_Wien #ECR2022 https://t.co/PjLRsfrLZ5
🥇 The most downloaded #EurRadiolExp of 2021 (over 6,000 downloads!) showed that the accuracy and reliability of lung 🫁 segmentation algorithms relies primarily on the diversity of the training data, highlighting data diversity. 🙌 Congratulations! https:/
“The accuracy and reliability of lung segmentation algorithms on demanding cases primarily relies on the diversity of the training data, highlighting the importance of data diversity compared to model choice”https://t.co/SMefb2SlRX @Neosoma_ai @Radiology_A
Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem ルーチンイメージングにおける自動肺セグメンテーションは、方法論の問題ではなく、主にデータの多様性の問題です arXiv: https://t.co/oXdr1V1NKq https://t.co/Q1ZtBdQ5fA
Yet another interesting article by @joh_hof et al.: https://t.co/yOrTdwPdDQ Shows that even for seemingly simple tasks we still have a long way to go. Also highlights the heterogeneity of disease definitions in public datasets (i.e. pleural space vs. lung)
[10/10] 📈 - Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem - 13 ⭐ - 📄 https://t.co/8OtUnLNzAV - 🔗 https://t.co/KhTfVkwm0l
RT @BrundageBot: Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. Johannes Hofmanning…
RT @BrundageBot: Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. Johannes Hofmanning…
General machine learning point that is routinely ignored: "Training data composition consistently has a bigger impact than algorithm choice on accuracy across test data sets" from https://t.co/jRROBvG7ZX, where basic approach outperformed complex new one
"Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem", Johannes H… https://t.co/g7Dx61gA1l
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. https://t.co/pvyECOqTWe
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. Johannes Hofmanninger, Florian Prayer, Jeanny Pan, Sebastian Rohrich, Helmut Prosch, and Georg Langs https://t.co/GrzTuZ25nN
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. Johannes Hofmanninger, Florian Prayer, Jeanny Pan, Sebastian Rohrich, Helmut Prosch, and Georg Langs https://t.co/kYi6wDX9TR
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem ルーチンイメージングにおける自動肺セグメンテーションは、方法論の問題ではなく、データの多様性の問題です arXiv: https://t.co/ILqKPRot8h https://t.co/JDZe0seDHQ
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. Johannes Hofmanninger, Florian Prayer, Jeanny Pan, Sebastian Rohrich, Helmut Prosch, and Georg Langs https://t.co/lNB273BrkR
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem - Johannes Hofmanninger https://t.co/o9u0QCp5j7
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. (arXiv:2001.11767v1 [eess.IV]) https://t.co/n8I1N6aVkd
Automatic lung segmentation in routine imaging is a data diversity problem, not a methodology problem. (arXiv:2001.11767v1 [eess.IV]) https://t.co/3gA5uw7Og2