EUVIMEDEUVIMED entdecken
Multizentrische Studie

AbdomenAtlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking

Wenxuan Li, Chongyu Qu, Xiaoxi Chen, Pedro R A S Bassi, Yijia Shi, Yuxiang Lai, Qian Yu, Huimin Xue, Yixiong Chen, Xiaorui Lin, Yutong Tang, Yining Cao und 9 weitere

Medical Image Analysis · 2024-10 · 97 · 103285

DOI: 10.1016/j.media.2024.103285 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Medical Image Analysis, 2024-10. Verfasst von Wenxuan Li und 20 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Johns Hopkins University, United States of America. Hauptthemen laut MEDLINE: Benchmarking, Algorithms, Tomography, X-Ray Computed, Radiography, Abdominal. Die Arbeit wurde bisher 70-mal zitiert (Crossref) und nennt 72 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce the largest abdominal CT dataset (termed AbdomenAtlas) of 20,460 three-dimensional CT volumes sourced from 112 hospitals across diverse populations, geographies, and facilities. AbdomenAtlas provides 673 K high-quality masks of anatomical structures in the abdominal region annotated by a team of 10 radiologists with the help of AI algorithms. We start by having expert radiologists manually annotate 22 anatomical structures in 5,246 CT volumes. Following this, a semi-automatic annotation procedure is performed for the remaining CT volumes, where radiologists revise the annotations predicted by AI, and in turn, AI improves its predictions by learning from revised annotations. Such a large-scale, detailed-annotated, and multi-center dataset is needed for two reasons. Firstly, AbdomenAtlas provides important resources for AI development at scale, branded as large pre-trained models, which can alleviate the annotation workload of expert radiologists to transfer to broader clinical applications. Secondly, AbdomenAtlas establishes a large-scale benchmark for evaluating AI algorithms-the more data we use to test the algorithms, the better we can guarantee reliable performance in complex clinical scenarios. An ISBI & MICCAI challenge named BodyMaps: Towards 3D Atlas of Human Body was launched using a subset of our AbdomenAtlas, aiming to stimulate AI innovation and to benchmark segmentation accuracy, inference efficiency, and domain generalizability. We hope our AbdomenAtlas can set the stage for larger-scale clinical trials and offer exceptional opportunities to practitioners in the medical imaging community. Codes, models, and datasets are available at https://www.zongweiz.com/dataset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BenchmarkingAlgorithmsTomography, X-Ray ComputedRadiography, AbdominalImaging, Three-DimensionalHumansDatasets as Topic

Stichwörter der Autor:innen

AnnotationBenchmarkDatasetTransfer Learning

Autor:innen und Institutionen

  • Department of Computer Science, Johns Hopkins University, United States of America.
  • Department of Bioengineering, University of Illinois Urbana-Champaign, United States of America.
  • Department of Computer Science, Johns Hopkins University, United States of America; Alma Mater Studiorum - University of Bologna, Italy; Center for Biomolecular Nanotechnologies, Istituto Italiano di Tecnologia, Italy.
  • LKS Faculty of Medicine, The University of Hong Kong, Hong Kong, China.
  • Department of Computer Science, Johns Hopkins University, United States of America; Department of Computer Science, Southeast University, China.
  • Department of Radiology, Southeast University Zhongda Hospital, China.

Zitieren

APA

Li, W., Qu, C., Chen, X., Bassi, P. R. A. S., Shi, Y., Lai, Y., Yu, Q., Xue, H., Chen, Y., Lin, X., Tang, Y., Cao, Y., Han, H., Zhang, Z., Liu, J., Zhang, T., Ma, Y., Wang, J., Zhang, G., …, & Zhou, Z. (2024). AbdomenAtlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking. Medical Image Analysis, 97, 103285. https://doi.org/10.1016/j.media.2024.103285

Vancouver

Li W, Qu C, Chen X, Bassi PRAS, Shi Y, Lai Y, et al. AbdomenAtlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking. Medical Image Analysis. 2024;97:103285. doi:10.1016/j.media.2024.103285

BibTeX
@article{Li2024,
  author = {Li, Wenxuan and Qu, Chongyu and Chen, Xiaoxi and Bassi, Pedro R A S and Shi, Yijia and Lai, Yuxiang and Yu, Qian and Xue, Huimin and Chen, Yixiong and Lin, Xiaorui and Tang, Yutong and Cao, Yining and Han, Haoqi and Zhang, Zheyuan and Liu, Jiawei and Zhang, Tiezheng and Ma, Yujiu and Wang, Jincheng and Zhang, Guang and Yuille, Alan and Zhou, Zongwei},
  title = {AbdomenAtlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking},
  journal = {Medical Image Analysis},
  year = {2024},
  volume = {97},
  pages = {103285},
  doi = {10.1016/j.media.2024.103285}
}
Kostenlos starten →