Tootfinder

Learning to Stop: Reinforcement Learning for Efficient Patient-Level Echocardiographic Classification
Woo-Jin Cho Kim, Jorge Oliveira, Arian Beqiri, Alex Thorley, Jordan Strom, Jamie O'Driscoll, Rajan Sharma, Jeremy Slivnick, Roberto Lang, Alberto Gomez, Agisilaos Chartsias
https://arxiv.org/abs/2509.19694

Learning to Stop: Reinforcement Learning for Efficient Patient-Level Echocardiographic Classification
Guidelines for transthoracic echocardiographic examination recommend the acquisition of multiple video clips from different views of the heart, resulting in a large number of clips. Typically, automated methods, for instance disease classifiers, either use one clip or average predictions from all clips. Relying on one clip ignores complementary information available from other clips, while using all clips is computationally expensive and may be prohibitive for clinical adoption. To select the…

Galera, o governo disponibilizou duas consultas públicas sobre a tršgica “Lei Felca” (que nem tem nada a ver com o vídeo dele). É importante preenchermos para garantir que a lei seja aplicada da forma “menos pior” possível, sem permitir que as big techs recebam nossos dados, sem permitir que o governo liste os sites que acessamos e sem permitir que o Fediverso seja prejudicado. Exigir zero-knowledge (para os dois lados), exigir que sites independentes e sem fins lucrativos como o fediverso não sejam afetados, etc.
Notem que uma delas fecha jš agora dia 3 de novembro!

• https://brasilparticipativo.presidencia.gov.br/processes/idadeafericao
• https://www.gov.br/participamaisbrasil/ts-rev-ar2526

The fact that the public can’t be sure whether the John Bolton investigation is legitimate
highlights the current crisis of trust in federal law enforcement,
a crisis that has been exacerbated by the words and actions of Trump and members of his administration.
The F.B.I.’s history shows that public trust is easily lost and difficult to rebuild — a lesson that we may have to (re)learn.

Opinion | John Bolton, Trump and the Crisis of Trust in Federal Law Enforcement
If the F.B.I. is seen as a tool of retribution, it will come at the expense of its effectiveness in the long run.

#DaylightSavingTime & Health - A Systematic Review of Beneficial & Adverse Effects: https://www.medrxiv.org/content/10.1101/2025.03.17.25324086v2 -> "The apparent benefits of DST during summer months on mortality, DST-Offset on sleep duration and mortality, and Standard Time during winter months on sleep duration argue in favour of keeping transitions. If kept, adverse effects of transitions should be mitigated in individuals susceptible to myocardial infarction or exacerbations of disease" -> Zu Sinn und Unsinn - Uhrenumstellungen aus der Sicht der Chronobiologie und Epidemiologie: https://idw-online.de/de/news860363

Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
Tristan S. W. Stevens, Ois\'in Nolan, Ruud J. G. van Sloun
https://arxiv.org/abs/2508.17326 https://

Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing
Echocardiography plays a central role in cardiac imaging, offering dynamic views of the heart that are essential for diagnosis and monitoring. However, image quality can be significantly degraded by haze arising from multipath reverberations, particularly in difficult-to-image patients. In this work, we propose a semantic-guided, diffusion-based dehazing algorithm developed for the MICCAI Dehazing Echocardiography Challenge (DehazingEcho2025). Our method integrates a pixel-wise noise model, der…

No bookmark function on Bsky so posting here when I want it
https://bsky.app/profile/natefederman.bsky.social/post/3ljxtmqpejs2c

🇺🇦 #NowPlaying on KEXP's #MiddayShow
Fcukers:
🎵 I Like It Like That
#Fcukers
https://fcukers.bandcamp.com/track/i-like-it-like-that
https://open.spotify.com/track/70EG3KoKRu3jvsBlFVZYkJ

A DyL-Unet framework based on dynamic learning for Temporally Consistent Echocardiographic Segmentation
Jierui Qu, Jianchun Zhao
https://arxiv.org/abs/2509.19052 https://…

A DyL-Unet framework based on dynamic learning for Temporally Consistent Echocardiographic Segmentation
Accurate segmentation of cardiac anatomy in echocardiography is essential for cardiovascular diagnosis and treatment. Yet echocardiography is prone to deformation and speckle noise, causing frame-to-frame segmentation jitter. Even with high accuracy in single-frame segmentation, temporal instability can weaken functional estimates and impair clinical interpretability. To address these issues, we propose DyL-UNet, a dynamic learning-based temporal consistency U-Net segmentation architecture desi…

Anatomically Constrained Transformers for Cardiac Amyloidosis Classification
Alexander Thorley, Agis Chartsias, Jordan Strom, Roberto Lang, Jeremy Slivnick, Jamie O'Driscoll, Rajan Sharma, Dipak Kotecha, Jinming Duan, Alberto Gomez
https://arxiv.org/abs/2509.19691

Anatomically Constrained Transformers for Cardiac Amyloidosis Classification
Cardiac amyloidosis (CA) is a rare cardiomyopathy, with typical abnormalities in clinical measurements from echocardiograms such as reduced global longitudinal strain of the myocardium. An alternative approach for detecting CA is via neural networks, using video classification models such as convolutional neural networks. These models process entire video clips, but provide no assurance that classification is based on clinically relevant features known to be associated with CA. An alternative p…