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: Released

3.0 million

2D CT images

9,262

3D CT volumes

25

annotated structures

138

hospitals

AbdomenAtlas 1.1
Watch Now

AbdomenAtlas 2.0

Status: Beta-Test

email zzhou82@jh.edu to get early access

Dataset (TBA)

3.0 million

2D CT images

9,262

3D CT volumes

Lesions

annotated in the pancreas, liver, kidney, colon, esophagus, & uterus

8,562

lesion instances

fig_cancerverse.png

AbdomenAtlas 3.0

Status: Beta-Test

email zzhou82@jh.edu to get early access

Dataset (

3.0 million

2D CT images

9,262

3D CT volumes

1.2 million

tokens

structured

& narrative reports

fig_teaser.png

BodyMaps

Internal use only; open for collaboration

icon.png

20.5 million

2D CT images

54,803

3D CT volumes

136

body compositions

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 54,803 computed tomography (CT) volumes with detailed, per-voxel annotations of 136 body compositions 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 7.3 million organ/tumor masks and 20.5 million annotated images that are taken from 145 hospitals across 19 countries and manually inspected by expert radiologists.

​

136 body compositions: adrenal gland left · adrenal gland right · airway · aorta · atrial appendage left · autochthon left · autochthon right · bladder · bone · brachiocephalic trunk · brachiocephalic vein left · brachiocephalic vein right · brain · clavicula left · clavicula right · celiac trunk · colon · common bile duct · common carotid artery left · common carotid artery right · costal cartilages · duodenum · esophagus · femur left · femur right · gall bladder · gluteus maximus left · gluteus maximus right · gluteus mediusleft · gluteus medius right · gluteus minimus left · gluteus minimus right · heart · hepatic vessel · hip left · hip right · humerus left · humerus right · iliac artery left · iliac artery right · iliac vena left · iliac vena right · iliopsoas left · iliopsoas right · intestine · kidney left · kidney right · liver · liver segment 1 · liver segment 2 · liver segment 3 · liver segment 4 · liver segment 5 · liver segment 6 · liver segment 7 · liver segment 8 · lung left · lung lower left lobe · lung lower right lobe · lung middle right lobe · lung right · lung upper left lobe · lung upper right lobe · pancreas · pancreas body · pancreas head · pancreas tail · pancreatic duct · portal vein and splenic vein · postcava · prostate · pulmonary vein · rectum · rib left 1 · rib left 10 · rib left 11 · rib left 12 · rib left 2 · rib left 3 · rib left 4 · rib left 5 · rib left 6 · rib left 7 · rib left 8 · rib left 9 · rib right 1 · rib right 10 · rib right 11 · rib right 12 · rib right 2 · rib right 3 · rib right 4 · rib right 5 · rib right 6 · rib right 7 · rib right 8 · rib right 9 · sacrum · scapula left · scapula right · skull · spleen · spinal cord · sternum · stomach · subclavian artery left · subclavian artery right · superior mesenteric artery · superior vena cava · thyroid gland · trachea · veins · vertebrae C1 · vertebrae C2 · vertebrae C3 · vertebrae C4 · vertebrae C5 · vertebrae C6 · vertebrae C7 · vertebrae L1 · vertebrae L2 · vertebrae L3 · vertebrae L4 · vertebrae L5 · vertebrae S1 · vertebrae T1 · vertebrae T10 · vertebrae T11 · vertebrae T12 · vertebrae T2 · vertebrae T3 · vertebrae T4 · vertebrae T5 · vertebrae T6 · vertebrae T7 · vertebrae T8 · vertebrae T9

jhu-shield-hero.jpg

Board of Directors
Alan L. Yuille, PhD
Wenxuan Li
Pedro R. A. S. Bassi
Zongwei Zhou, PhD

Core Contributors
Xinze Zhou
Chongyu Qu
Xiaoxi Chen, MD
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)
Daguang Xu, PhD (NVIDIA)
Fabian Isensee, PhD (DKFZ)
Kai Ding, PhD (Johns Hopkins Medicine)
Heng Li, PhD (Johns Hopkins Medicine)
Yang Yang, PhD (University of California, San Francisco)
Kang Wang, MD, 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)
Szymon PÅ‚otka, PhD (University of Warsaw)

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 BodyMaps Project?
Contact: Zongwei Zhou <zzhou82@jh.edu>

bottom of page