 |
|
|
USF Digital
Mammography Database
The Digital Database for Screening Mammography (DDSM) is a resource for use by
the mammographic image analysis research community. The primary purpose of the
database is to facilitate sound research in the development of computer
algorithms to aid in screening. Secondary purposes of the database may include
the development of algorithms to aid in the diagnosis and the development of
teaching or training aids. The database contains approximately 2,500 studies.
Each study includes two images of each breast, along with some associated
patient information (age at time of study, ACR breast density rating, subtlety
rating for abnormalities, ACR keyword description of abnormalities) and image
information (scanner, spatial resolution). Images containing suspicious areas
have associated pixel-level "ground truth" information about the locations and
types of suspicious regions. Also provided is software both for accessing the
mammogram and truth images and for calculating performance figures for
automated image analysis algorithms.
Mouse Brain Library
The MBL consists of high-resolution images and databases of brains from many
genetically-characterized strains of mice. There are numerous uses of the MBL,
but the developers' mission is to systematically map and characterize genes
that modulate architecture of the mammalian CNS (for a complete description of
projects refer to the
P20 Human Brain Project Award: Informatics Center for
Mouse Neurogenetics). MBL databases also include detailed information on
genomes of many strains of mice. The collection now consists of images from
approximately 800 brains and numerical data from just over 8000 mice. MBL can
be searched for cases by strain, age, sex, or body or brain weight. Images of
the slide collection are available at a series of resolutions. The base
resolution is 24.5 +/- 0.5 micrometer per pixel in the XY plane with a 150
micrometer interval between sections (300 micrometer on each slide, 2 slides
per case). Significantly higher resolution images of single sections (4.5
micrometer/pixel) have been acquired for over a hundred cases marked with a
blue "hi-res" button. They are now collecting 1 micrometer/pixel images for
specific parts of the brain - at present, the neocortex, hippocampus, and the
dorsal lateral geniculate nucleus. Very high resolution images (<0.2
micrometer/pixel) are available for C57BL/6J using the iScope, a web-controlled
microscope equipped with DIC optics.
RadiologyInfo
RadiologyInfo is designed to answer patient questions related to many radiologic procedures and therapies. It includes images from diagnostic radiology, interventional radiology and radiation therapy, has an alphabetical procedures list and galleries of images. There is access to descriptive material for radiologists to use in their waiting rooms.
CMU Computer Vision Test Images
The Computer Vision Homepage was established at Carnegie Mellon University in
1994 to provide a central location for World Wide Web links relating to
computer vision research. The emphasis of the Computer Vision Homepage is on
computer vision research rather than on commercial products. A comprehensive
set of links to publicly accessible Web sites with computer vision test images
is offered.
ECVNet Image
Data Bases List
This page contains pointers to sites offering public access to image
collections via the Internet. There you can find color and grayscale still
images, medical images, textures, sequences, stereo pairs, range images, etc.
MedPix™ Medical Image Database
MedPix™ is a fully web-enabled and cross-platform database, integrating images
and textual information. The primary "target audience" includes resident and
practicing physicians, medical students, graduate nursing students and other
post-graduate trainees. The material is organized by disease category, disease
location (organ system), and by patient profiles. The database can be searched
through multiple internal text search engines. In addition, search formulations
can be sent directly to PubMed, or to other outside search engines. Registered
users may browse the image database through a "slide sorter" module.
Contributed content may be copyrighted by the original author/contributor, and
is used with permission.
Gastrolab Endoscopy Pictures Archive
This Web site is an image library that will eventually contain pictures of
every disease that make visible changes in the digestive system. Most of the
endoscopic pictures are taken with Olympus videoendoscopes. The picture quality
in this library is not as good as in the original pictures - the original
quality would have made transmission times too long. In this image library
typical x-ray-findings in gastroenterologic diseases are illustrated. This
website is provided as a free service by The Wasa Workgroup on Intestinal
Disorders, GASTROLAB, Vasa, Finland.
The
Stanford Visible Female
The Stanford Visible Female is an Academic Project sponsored by the Division of
Anatomy and SUMMIT. Central to the project is a series of 95 photographed
cryosections of a reproductive-age female cadaveric pelvis acquired in 1993.
From these cross-sectional data, several research projects have arisen. These
range from 2D imaging correlations with independent MR data to 3D models
developed for anatomically accurate surgical simulation.
Visible Human
Project
Visible Human Project is creating complete, anatomically detailed,
three-dimensional representations of the male and female human body. The
current phase of the project is collecting transverse CT, MRI and cryosection
images of representative male and female cadavers at one millimeter intervals.
Includes an extensive collection of links to projects based upon the Visible
Human data.
NIDCR - Craniofacial and
Skeletal Diseases Branch
The NIDCR imaging Web page will allow the NIH research and clinical community
to collaborate on imaging studies through the Internet. All authorized users on
the NIH campus and abroad will be able to display and review the studies posted
on the imaging Web page with the NIH-developed imaging tool
Medical Image Processing, Analysis and Visualization (MIPAV).
< Previous | Next Section > Main |
