This https://arxiv.org/abs/2111.15488 has been replaced.
link: https://scholar.google.com/scholar?q=a
Self-supervised learning for classifying paranasal anomalies in the maxillary sinus
Debayan Bhattacharya, Finn Behrendt, Benjamin Tobias Becker, Lennart Maack, Dirk Beyersdorff, Elina Petersen, Marvin Petersen, Bastian Cheng, Dennis Eggert, Christian Betz, Anna Sophie Hoffmann, Alexander Schlaefer
https://arxiv.org/abs/2404.18599 https://arxiv.org/pdf/2404.18599
arXiv:2404.18599v1 Announce Type: new
Abstract: Purpose: Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS).
Methods: Our approach uses a 3D Convolutional Autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D Convolutional Neural Network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images.
Results: The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an Area Under the Precision-Recall Curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and Masked Autoencoding using SparK at 0.75.
Conclusion: A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly
Higher-order topology protected by latent crystalline symmetries
L. Eek, M. R\"ontgen, A. Moustaj, C. Morais Smith
https://arxiv.org/abs/2405.02704 ht…
If you don't live in Georgia (or even in Athens), you may not know who Bill Paul was, but this obituary penned by his family gives some idea of how important he was to art in the state. The acquisitions he made for our collection and the exhibitions he organized truly opened the door for experimental and contemporary art. RIP. ❤️
https:…
Closing the Information Gap in Unidentified Anomalous Phenomena (UAP) Studies
Gretchen R. Stahlman
https://arxiv.org/abs/2403.15368 https://
As the Dad of a 21-week preemie who died, a 23-week preemie who lives, and as a 30-week preemie myself.
No: not if it means offering more traumatized parents more uncertain efforts to save ever smaller babies.
It is already soul-flaying to have an early preemie. Many die. How a 23-week preemie *or a 30-week preemie* fares is a dice toss.
(My attempt to elaborate on that was just too hard.)
Propagation, dissipation and breakdown in quantum anomalous Hall edge states probed by microwave edge plasmons
Torsten R\"oper, Hugo Thomas, Daniel Rosenbach, Anjana Uday, Gertjan Lippertz, Anne Denis, Pascal Morfin, Alexey A. Taskin, Yoichi Ando, Erwann Bocquillon
https://arxiv.org/abs/2405.19983
This https://arxiv.org/abs/2303.06204 has been replaced.
initial toot: https://mastoxiv.page/@a…
This https://arxiv.org/abs/2303.06204 has been replaced.
initial toot: https://mastoxiv.page/@a…