Zobrazeno 1 - 10
of 2 733
pro vyhledávání: '"Mascagni, A."'
Autor:
Nwoye, Chinedu Innocent, Bose, Rupak, Elgohary, Kareem, Arboit, Lorenzo, Carlino, Giorgio, Lavanchy, Joël L., Mascagni, Pietro, Padoy, Nicolas
Acquiring surgical data for research and development is significantly hindered by high annotation costs and practical and ethical constraints. Utilizing synthetically generated images could offer a valuable alternative. In this work, we explore adapt
Externí odkaz:
http://arxiv.org/abs/2407.09230
CycleSAM: One-Shot Surgical Scene Segmentation using Cycle-Consistent Feature Matching to Prompt SAM
The recently introduced Segment-Anything Model (SAM) has the potential to greatly accelerate the development of segmentation models. However, directly applying SAM to surgical images has key limitations including (1) the requirement of image-specific
Externí odkaz:
http://arxiv.org/abs/2407.06795
Autor:
Satyanaik, Siddhant, Murali, Aditya, Alapatt, Deepak, Wang, Xin, Mascagni, Pietro, Padoy, Nicolas
Purpose: Advances in deep learning have resulted in effective models for surgical video analysis; however, these models often fail to generalize across medical centers due to domain shift caused by variations in surgical workflow, camera setups, and
Externí odkaz:
http://arxiv.org/abs/2403.06953
Autor:
Murali, Aditya, Alapatt, Deepak, Mascagni, Pietro, Vardazaryan, Armine, Garcia, Alain, Okamoto, Nariaki, Costamagna, Guido, Mutter, Didier, Marescaux, Jacques, Dallemagne, Bernard, Padoy, Nicolas
This technical report provides a detailed overview of Endoscapes, a dataset of laparoscopic cholecystectomy (LC) videos with highly intricate annotations targeted at automated assessment of the Critical View of Safety (CVS). Endoscapes comprises 201
Externí odkaz:
http://arxiv.org/abs/2312.12429
Autor:
Mazellier, Jean-Paul, Boujon, Antoine, Bour-Lang, Méline, Erharhd, Maël, Waechter, Julien, Wernert, Emilie, Mascagni, Pietro, Padoy, Nicolas
This technical report presents MOSaiC 3.6.2, a web-based collaborative platform designed for the annotation and evaluation of medical videos. MOSaiC is engineered to facilitate video-based assessment and accelerate surgical data science projects. We
Externí odkaz:
http://arxiv.org/abs/2312.08593
Autor:
Murali, Aditya, Alapatt, Deepak, Mascagni, Pietro, Vardazaryan, Armine, Garcia, Alain, Okamoto, Nariaki, Mutter, Didier, Padoy, Nicolas
Recently, spatiotemporal graphs have emerged as a concise and elegant manner of representing video clips in an object-centric fashion, and have shown to be useful for downstream tasks such as action recognition. In this work, we investigate the use o
Externí odkaz:
http://arxiv.org/abs/2312.06829
Autor:
Alapatt, Deepak, Murali, Aditya, Srivastav, Vinkle, Mascagni, Pietro, Consortium, AI4SafeChole, Padoy, Nicolas
Purpose: General consensus amongst researchers and industry points to a lack of large, representative annotated datasets as the biggest obstacle to progress in the field of surgical data science. Self-supervised learning represents a solution to part
Externí odkaz:
http://arxiv.org/abs/2312.05968
Autor:
Sergio De Filippis, Antonio Vita, Alessandro Cuomo, Emanuela Amici, Valeria Giovanetti, Ginevra Lombardozzi, Simone Pardossi, Luca Altieri, Andrea Cicale, Marisa Dosoli, Alessandro Galluzzo, Elena Invernizzi, Paola Rodigari, Patrizia Mascagni, Claudia Santini, Nathalie Falsetto, Marta Antonia Manes, Marco Micillo, Andrea Fagiolini
Publikováno v:
Annals of General Psychiatry, Vol 23, Iss 1, Pp 1-12 (2024)
Abstract Background Although second-generation antipsychotics (SGAs) have proven to be effective therapeutic options for patients with schizophrenia, there is a notable lack of evidence on patients’ subjective perspectives regarding their well-bein
Externí odkaz:
https://doaj.org/article/1bba7e7e59764909985dab1e06d47d47
Publikováno v:
The Journal of Economic Perspectives, 2024 Jan 01. 38(1), 107-132.
Externí odkaz:
https://www.jstor.org/stable/27282176
Autor:
Yuan, Kun, Srivastav, Vinkle, Yu, Tong, Lavanchy, Joel L., Mascagni, Pietro, Navab, Nassir, Padoy, Nicolas
Recent advancements in surgical computer vision have been driven by vision-only models, which lack language semantics, relying on manually annotated videos to predict fixed object categories. This limits their generalizability to unseen surgical proc
Externí odkaz:
http://arxiv.org/abs/2307.15220