Efficient MedSAMs: Segment Anything in Medical Images on Laptop

Bewaard in:

Bibliografische gegevens
Gepubliceerd in:	arXiv.org (Dec 20, 2024), p. n/a
Hoofdauteur:	Ma, Jun
Andere auteurs:	Li, Feifei, Kim, Sumin, Asakereh, Reza, Bao-Hiep Le, Nguyen-Vu, Dang-Khoa, Pfefferle, Alexander, Muxin Wei, Gao, Ruochen, Lyu, Donghang, Yang, Songxiao, Purucker, Lennart, Marinov, Zdravko, Staring, Marius, Lu, Haisheng, Thuy Thanh Dao, Ye, Xincheng, Li, Zhi, Brugnara, Gianluca, Vollmuth, Philipp, Foltyn-Dumitru, Martha, Cho, Jaeyoung, Mustafa Ahmed Mahmutoglu, Bendszus, Martin, Pflüger, Irada, Rastogi, Aditya, Ni, Dong, Yang, Xin, Zhou, Guang-Quan, Wang, Kaini, Heller, Nicholas, Papanikolopoulos, Nikolaos, Weight, Christopher, Tong, Yubing, Udupa, Jayaram K, Patrick, Cahill J, Wang, Yaqi, Zhang, Yifan, Contijoch, Francisco, McVeigh, Elliot, Ye, Xin, He, Shucheng, Haase, Robert, Pinetz, Thomas, Radbruch, Alexander, Krause, Inga, Kobler, Erich, He, Jian, Tang, Yucheng, Yang, Haichun, Huo, Yuankai, Luo, Gongning, Kaisar Kushibar, Amankulov, Jandos, Dias Toleshbayev, Mukhamejan, Amangeldi, Egger, Jan, Pepe, Antonio, Gsaxner, Christina, Luijten, Gijs, Fujita, Shohei, Kikuchi, Tomohiro, Wiestler, Benedikt, Kirschke, Jan S, de la Rosa, Ezequiel, Bolelli, Federico, Lumetti, Luca, Grana, Costantino, Xie, Kunpeng, Wu, Guomin, Puladi, Behrus, Martín-Isla, Carlos, Lekadir, Karim, Campello, Victor M, Shao, Wei, Brisbane, Wayne, Jiang, Hongxu, Hao, Wei, Wu, Yuan, Li, Shuangle, Zhou, Yuyin, Wang, Bo
Gepubliceerd in:	Cornell University Library, arXiv.org
Onderwerpen:	Algorithms Source code Reproducibility Image segmentation Open source software Medical imaging
Online toegang:	Citation/Abstract Full text outside of ProQuest
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!

Omschrijving
Samenvatting:	Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications.
ISSN:	2331-8422
Bron:	Engineering Database