Zobrazeno 1 - 10
of 87
pro vyhledávání: '"Goldenberg, Roman"'
Autor:
Intrator, Yotam, Kelner, Ori, Cohen, Regev, Goldenberg, Roman, Rivlin, Ehud, Freedman, Daniel
Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant information,
Externí odkaz:
http://arxiv.org/abs/2410.02914
Autor:
Shor, Joel, McNeil, Carson, Intrator, Yotam, Ledsam, Joseph R, Yamano, Hiro-o, Tsurumaru, Daisuke, Kayama, Hiroki, Hamabe, Atsushi, Ando, Koji, Ota, Mitsuhiko, Ogino, Haruei, Nakase, Hiroshi, Kobayashi, Kaho, Miyo, Masaaki, Oki, Eiji, Takemasa, Ichiro, Rivlin, Ehud, Goldenberg, Roman
$\textbf{Background}$: Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels. $\textbf{Met
Externí odkaz:
http://arxiv.org/abs/2403.09920
Autor:
Intrator, Yotam, Halfon, Matan, Goldenberg, Roman, Tsarfaty, Reut, Eyal, Matan, Rivlin, Ehud, Matias, Yossi, Aizenberg, Natalia
Large language models hold significant promise in multilingual applications. However, inherent biases stemming from predominantly English-centric pre-training have led to the widespread practice of pre-translation, i.e., translating non-English input
Externí odkaz:
http://arxiv.org/abs/2403.04792
Autor:
Shor, Joel, Yamano, Hiro-o, Tsurumaru, Daisuke, Intrator, Yotami, Kayama, Hiroki, Ledsam, Joe, Hamabe, Atsushi, Ando, Koji, Ota, Mitsuhiko, Ogino, Haruei, Nakase, Hiroshi, Kobayashi, Kaho, Oki, Eiji, Goldenberg, Roman, Rivlin, Ehud, Takemasa, Ichiro
$\textbf{Background and aims}$: Artificial Intelligence (AI) Computer-Aided Detection (CADe) is commonly used for polyp detection, but data seen in clinical settings can differ from model training. Few studies evaluate how well CADe detectors perform
Externí odkaz:
http://arxiv.org/abs/2312.06833
Autor:
Hirsch, Roy, Caron, Mathilde, Cohen, Regev, Livne, Amir, Shapiro, Ron, Golany, Tomer, Goldenberg, Roman, Freedman, Daniel, Rivlin, Ehud
Publikováno v:
MICCAI 2023
Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As such, it might have a pivotal role to play in biomedicine where annotating data requires a highly speci
Externí odkaz:
http://arxiv.org/abs/2308.12394
Publikováno v:
MICCAI 2023
Computer-aided polyp detection (CADe) is becoming a standard, integral part of any modern colonoscopy system. A typical colonoscopy CADe detects a polyp in a single frame and does not track it through the video sequence. Yet, many downstream tasks in
Externí odkaz:
http://arxiv.org/abs/2306.08591
Publikováno v:
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Following the successful debut of polyp detection and characterization, more advanced automation tools are being developed for colonoscopy. The new automation tasks, such as quality metrics or report generation, require understanding of the procedure
Externí odkaz:
http://arxiv.org/abs/2306.06960
Publikováno v:
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Colonoscopy is the standard of care technique for detecting and removing polyps for the prevention of colorectal cancer. Nevertheless, gastroenterologists (GI) routinely miss approximately 25% of polyps during colonoscopies. These misses are highly o
Externí odkaz:
http://arxiv.org/abs/2305.10090
Autor:
Shor, Joel, Bi, Ruyue Agnes, Venugopalan, Subhashini, Ibara, Steven, Goldenberg, Roman, Rivlin, Ehud
Publikováno v:
Clinical NLP Workshop, ACL 2023
Automatic Speech Recognition (ASR) in medical contexts has the potential to save time, cut costs, increase report accuracy, and reduce physician burnout. However, the healthcare industry has been slower to adopt this technology, in part due to the im
Externí odkaz:
http://arxiv.org/abs/2303.05737
We propose a two-stage unsupervised approach for parsing videos into phases. We use motion cues to divide the video into coarse segments. Noisy segment labels are then used to weakly supervise an appearance-based classifier. We show the effectiveness
Externí odkaz:
http://arxiv.org/abs/2210.10594