Matthias P

Postdoc @imed_tweets || Alumni @cir_lab @MedUni_Wien

[contextflow - A 4DMedical Company @contextflow_rad]

Automatic lung segmentation in CT is a critical part of image analysis. We developed an algorithm that yields high accuracy despite the presence of disease patterns.

In this whitepaper, we compare our algorithm with the established state-of-the-art. https://t.co/B6o0dMRv2s

[contextflow - A 4DMedical Company @contextflow_rad]

Our application for the @EUeic Accelerator equity investment program has been accepted! Our history with the #EIC goes back to 2020 when we received a €1.2M grant. The @EU_Commission is clearly committed to support European-born companies with cutting-edge innovation. Thank you!

[CIR Lab @cir_lab]

We are proud to announce the opening of the CD Lab for Machine Learning and Precision Imaging, with special thanks to Christian Doppler Forschungsgesellschaft, Federal Ministry Republic of Austria - Labour and Economy, @SiemensHealth, @MedUni_Wien and @univienna. @georg @HProsch

[CIR Lab @cir_lab]

77 mio years of cerebral cortex evolution reconstructed. New @cir_lab paper by E Schwartz, KH Nenning, @katjaQheuer, @NathanJeffery17 @OrnellaBertrand @R3RT0, G Kasprian, D Prayer, and @georg: https://t.co/Ez5EkN22mF in @NatureComms @MedUni_Wien @brainhackorg

[CIR Lab @cir_lab]

Come see a talk by Matthias Perkonigg: Continual Active Learning for Efficient Image Labeling while Image Characteristics Change - Session: RPS 2305, Jul 17, 09:30 - 10:30 #ECR2022 @MedUni_Wien @myESR @cir_lab @matthias_perk @HProsch @joh_hof @georg

[CIR Lab @cir_lab]

New paper by Sebastian Röhrich et al. Impact of a content-based image retrieval system on the interpretation of chest CTs of patients with diffuse parenchymal lung disease in European Radiology https://t.co/YC3SnWKuik @HProsch @georg @contextflow_rad @BigMedilytics

[Matthias P @matthias_perk]

Excited to join @contextflow_rad🥳

[contextflow - A 4DMedical Company @contextflow_rad]

Straight from the @cir_lab at @MedUni_Wien, Matthias Perkonigg joins team @contextflow_rad as a #MachineLearning Engineer. Matthias has co-authored numerous peer-reviewed publications with fellow team members already, so it's fitting that he join us officially! Welcome Matthias!

[CIR Lab @cir_lab]

Two open PhD positions at @cir_lab in machine learning & medical imaging: (1) linking imaging and epigenomics for treatment response prediction in breast cancer, and (2) detecting novel emerging respiratory diseases. Apply until May 1st @MedUni_Wien: https://t.co/gjRY7TrqBo

[Machine Learning for Biomedical Imaging @MELBAJournal]

New publication alert🔖⚠️: "Continual Active Learning Using Pseudo-Domains for Limited Labelling Resources and Changing Acquisition Characteristics." M Perkonigg @matthias_perk, J Hofmanninger, C Herold, H Prosch, G Langs @georg, @cir_lab - Free to read: https://t.co/DY2TocD5V5

[Matthias P @matthias_perk]

In our new paper published today @MELBAJournal
we propose a continual active learning method to keep machine learning models for #medicalimaging up to date while keeping the manual annotation effort low @cir_lab @georg @joh_hof
@HProsch https://t.co/xs8aGJCiBg

[Nature Communications @NatureComms]

.@matthias_perk, @georg, @joh_hof et al propose a continual learning approach for medical imaging models to deal with domain shifts occurring at unknown time points @cir_lab.

https://t.co/aha5FpNXdH

[MedUni Wien @MedUni_Wien]

This is how computer models stay up to date: researchers at #MedUniVienna are developing an #algorithm for a constantly changing #dynamicmemory. Find out more about the paper published in @naturecomms: https://t.co/Qr2sclc1CM

[Matthias P @matthias_perk]

https://t.co/damRwk3WU4

[Matthias P @matthias_perk]

Check out our new paper on continual learning with medical imaging published today in @NatureComms. @georg @joh_hof @HProsch @JimBrinkMD

[Matthias P @matthias_perk]

In this paper we show how to keep a machine learning model up to date under the influence of continuous progress of image acquisition technology or diagnostic procedures.

[Matthias P @matthias_perk]

Happy to present our work 'Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition' at #IPMI2021 starting today. Check out our poster teaser https://t.co/d0ZNWYTG7u and full paper https://t.co/uoXYOP8ENg @cir_lab @georg @joh_hof

[Georg Langs @georg]

how to forget the right thing? continuously training machine learning models in medical imaging. Today at #MICCAI2020 new paper by Johannes Hofmanninger, Matthias Perkonigg et al. on a dynamic memory approach:
https://t.co/KssGBy23Dl

@joh_hof @entenbaer @cir_lab
@MedUni_Wien

[Matthias P @matthias_perk]

@fepegar_ @MICCAI2020 happening to me as well

[CIR Lab @cir_lab]

Matthias Perkonigg presenting his work on unsupervised predictive pattern discovery in medical images at #medneurips #NeurIPSConf pdf:https://t.co/mBB9GVtBqk

[MISS @MI_SummerSchool]

MISS 2018 School Photo #miss2018 #favignana #medicalimaging #DeepLearning @ja_schnabel @robertocipolla @FilippoStanco @GMFarinella