top of page

AbdomenAtlas 1.0

Status: Released [JHU WSE News]

1.5 million

2D CT images

5,195

3D CT volumes

9

annotated structures

76

hospitals

AbdomenAtlas 1.0
Watch Now

AbdomenAtlas 1.1

Status: Beta test

Dataset

3.0 million

2D CT images

9,262

3D CT volumes

25

annotated structures

138

hospitals

AbdomenAtlas 1.1
Watch Now

BodyMaps

Internal use only; open for collaboration

icon.png

12.5 million

2D CT images

30,619

3D CT volumes

142

annotated structures

145

hospitals

BodyMaps provide a three-dimensional digital atlas of the human body, conceptually similar to Google Maps but focusing on human anatomy. BodyMaps offer three unique features: First, semantic segmentation of anatomical structures, such as the cardiovascular system, skeleton, muscles, and gastrointestinal tract. Second, tumor screening across various structures, including lungs, abdomen, brain, bones, heart, and blood vessels. Third, supporting multiple clinical tasks, such as image registration, disease quantification, tumor stage estimation, report generation, etc. The BodyMaps Project has now contributed a total of 30,619 computed tomography (CT) volumes with detailed, per-voxel annotations of 142 anatomical structures and associated tumors. This dataset has already attracted 50+ leading research teams worldwide, driving innovation from classical methods (U-Net and its variants) to cutting-edge Foundation Models.

In 2009, before the advent of ImageNet, it was challenging to develop artificial intelligence (AI) algorithms that are robust to different domains using a small or even medium size of labeled data. The same situation, we believe, that presents in medical image analysis today, which is in dire need of its own ImageNet moment, where a large amount of data is available, where high-quality annotations are performed, where multiple domains (hospitals) are covered, where the dataset is attached to a widely recognized challenge. The BodyMaps Project presents unprecedented data and annotation scales with over 4.3 million organ/tumor masks and 12.5 million annotated images that are taken from 145 hospitals across 19 countries and manually inspected by expert radiologists.

jhu-shield-hero.jpg

Board of Directors
Alan L. Yuille, PhD
Wenxuan Li
Zongwei Zhou, PhD
Xiaoxi Chen, MD

Core Contributors
Chongyu Qu
Pedro R. A. S. Bassi
Tiezheng Zhang
Yucheng Tang, PhD

Technology Supports
Yu-Cheng Chou
Qi Chen
Yixiong Chen
Yuxiang Lai
Yaoyao Liu, PhD
Mingxu Liu
Xinrui Zou

Medical Trainees
Huimin Xue
Haoqi Han
Xiaorui Lin
Yutong Tang
Yining Cao
Yujiu Ma
Hualin Qiao

Special Thanks to Public Datasets
Pancreas-CT (2015) [website]
LiTS (2019) [website]
KiTS (2023) [website]
AbdomenCT-1K (2023) [website]
CT-ORG (2020) [website]
CHAOS (2018) [website]
MSD-CT (2021) [website]
BTCV (2015) [website]
AMOS (2022) [website]
WORD (2021) [website]
FLARE (2022) [website]
Abdominal Trauma Det (2023) [website]

Collaborators
Yucheng Tang, PhD (NVIDIA)
Yang Yang, PhD (University of California, San Francisco)
Kang Wang, MD, PhD (University of California, San Francisco)
Mehmet Can Yavuz, PhD (University of California, San Francisco)
Jianning Li, PhD (University Hospital Essen)
Alberto Santamaria-Pang, PhD (Microsoft)
Ho Hin Lee, PhD (Microsoft)
Alejandro Martin-Gomez, PhD (Johns Hopkins University)

Challenges: Towards 3D Atlas of Human Body
IEEE International Symposium on Biomedical Imaging (ISBI'24)
Medical Image Computing and Computer Assisted Intervention (MICCAI'24)

Become Part of the Body Maps Project?
Contact: Zongwei Zhou <zzhou82@jh.edu>

bottom of page