RadImageNet

Extract numerical image features for research with models trained on RadImageNet.

Version 0.3.3 · Apple Silicon

Model card

Input
A 2D image.
Output
Numerical descriptions of the image and its regions for further analysis.
Models
ResNet50, DenseNet121, InceptionV3 and InceptionResNetV2.
Runs on
macOS 14.0 or later on Apple Silicon

Downloads and memory

Download size and peak memory use are not published for this version.

Before you run

The supplied models extract image features; they do not assign diagnostic labels.

For files containing several frames, only the first frame is used.

License and terms

Software: Apache-2.0. Model files have their own license terms.

Developer documentation on GitHub

Intended use

For research and education. Not for clinical diagnosis or treatment decisions. Outputs require human review.