As a service to the medical imaging community, we have sought to compile a list of publicly available/accessible medical image databases for the development and analysis of medical image software and computer aided detection/diagnosis tools, as well as challenges performed on various modalities. If any databases/challenges are thought to be absent from this list, or the organizers of an unlisted database wish it to be included in this list, please contact to be added.
VIA Public Database Activities
Public Medical Image Databases
Unrestricted Access unless otherwise noted
Chest X-ray
- JSRT Digital Image Database. Digital Chest X-ray database with images containing lung nodules as well as negative cases, with ground truth location and diagnosis provided. JSRT Database Page
- SCR database: Segmentation in Chest Radiographs. Digital Chest X-ray database established to facilitate comparative studies on segmentation of the lung fields, the heart and the clavicles in standard posterior-anterior chest radiographs. Image Sciences Institute: SCR database
Computed Tomography (CT)
- LIDC - NCIA Collection - Lung Image Database Consortium. Image database with lung lesions marked by up to four radiologists. NCI-LIDC Information Page. Size information on this dataset is provided by the VIA group here: LIDC Nodule Size Report. The images and main documentation are available at the NCI Image Archive (NCIA).
- RIDER - NCIA Collection - Reference Image Database to Evaluate Response. Image archive of CT lung cancer patients followed during treatment. RIDER - White Paper The images and main documentation are available at the NCI Image Archive (NCIA).
- ECLAP public database of whole lung CT images An image database of wole-lung low-dose CT images of the chest with the locations of all nodules marked.
- Public Database to Address Drug Response An image database with small datasets of well documented CT images of the chest
Magnetic Resonance Images
- BrainWeb: Simulated Brain Database. Contains simulated, 3D MR data using normal and multiple sclerosis models with different acquisition parameters. BrainWeb: SBD
Mammography
- DDSM: Digital Database for Screening Mammography. Contains a large number of cases with both normal and abnormal findings (and associated ground truth). USF DDSM Homepage
- Mini-MIAS (Mammographic Image Analysis Society). Contains cases with and location information of the abnormality. Mini-MIAS
Retinopathy
- DIARETDB1 - Standard Diabetic Retinopathy Database. Database for benchmarking diabetic retinopathy detection from digital images. Offers a standardized testing protocol. Website
- DRIVE: Digital Retinal Images for Vessel Extraction. Database established to facilitate comparative studies on segmentation of blood vessels in retinal images. Website
Virtual Colonoscopy
- NCIA Collection: Virtual Colongraphy - Database for colonic polyp detection from CT with MS Access relational database file to aid in case selection found at NCIA Collections Page.
*This collection is made available from the Walter Reed Army Medical Center Virtual Colonoscopy Collection in collaboration with National Cancer Institute, NIH: please note the citation requirements on the NCIA collections page.
Multimodality
- Standardized Evaluation Methodology for 2D-3D Registration Database. Contains multi-modality datasets, centers of rotation, evaluation criteria, and starting positions for the evaluation of registration methods. Image Sciences Institute: Registration database
- NCIA Collection: PET/CT phantom scan collection. A resource for increased quantitative understanding of machine acquisition, analytic reproducibility and image processing. NCIA Collections Page
Medical Image Analysis Challenges
Limited Data Access unless otherwise noted, see individual challenge for details
Computed Tomography (CT)
- EXACT09. Challenge for the automated extraction of airways from CT data. EXACT09 Homepage
- ANODE09 Study. Challenge for the CAD detection of lung lesions from whole-lung CT data. ANODE09 Homepage
- BIOCHANGE 2008 PILOT. Challenge for the evaluation of change measurement algorithm. BIOCHANGE 2008 Pilot Homepage *Note: Uses publicly accessible NCIA-RIDER and FDA phantom data.
- VOLCANO'09 Nodule Change Challenge the evaluation of size change in pulmonary nodules.
- Coronary Artery Algorithm Evaluation Framework. Challenge based on the extraction of coronary artery centerlines from CTA data. Home Page
- Liver Tumor Segmentation 08. Challenge based on the segmentation of liver lesions from contrast enhanced CT. Challenge Homepage
Magnetic Resonance Images
- MS lesion segmentation challenge 08. Challenge for the segmentation of brain lesions from MR imagery. MSseg08 Homepage
- CAUSE07 - Caudate Segmentation Evaluation 2007. Challenge for the segmentation of the caudate nucleus from brain MRI scans. CAUSE07 Homepage
Retinopathy
- ROC-Retinopathy Online Challenge. Challenge based on detecting microaneurysms and dot hemorrhages for diabetic retinopathy screening. The ROC Website
VIA Group Public Databases
Documented image databases are essential for the development of
quantitative image analysis tools especially for tasks of
computer-aided diagnosis (CAD). In collaboration with the ELCAP
group we have established two public image databases that contain
lung CT images in the DICOM format together with documentation
of abnormalities by radiologists. Please access the links below
for more details:
|
ECLAP public database of whole lung CT images |
| Public Database to Address Drug Response |
| VOLCANO'09 Nodule Change Challenge |
| LIDC database size index list |
In addition to the databases shown above the VIA and ELCAP groups have made contributions to The National Cancer Institute (NCI) efforts to provide public image databases. In particular we have contributed to the Lung Image Database Consortium (LIDC), the Image Database Resource Initiative (IDRI) and the Reference Image Database to Evaluate Response (RIDER) projects. The public databases for these projects can be accessed through the "National Cancer Imaging Archive"