2024 MIDI-B Challenge Workshop

If you’re interested in protecting patient privacy and preserving the research value of medical imaging data, attend the 2024 Medical Image De-Identification Benchmark (MIDI-B) Challenge Workshop. This event will feature the finalists from the MIDI-B Challenge, which NCI hosted in collaboration with Sage Bionetworks and the Medical Image Computing and Computer Assisted Interventions society (MICCAI 2024 annual meeting).

You’ll hear these top teams describe:

• the algorithms they used.
• the performance results they found from the de-identification of imaging data.

You’ll also learn about the MIDI-B Challenge design and the MIDI synthetic data set that participants used.

The goal of the MIDI-B Challenge was to benchmark image deidentification against a reference data set. The reference data set was a large and diverse set of standardized clinical images with synthetic identifiers. These images use the Digital Imaging and Communications in Medicine (DICOM) Standard. Following the DICOM Standard helps ensure medical imaging information is interoperable.