Using AI to Color MRI Images for Better Understanding of Multiple Sclerosis
Author Information
Author(s): Darin T. Okuda, Christine Lebrun-Frenay
Primary Institution: The University of Texas Southwestern Medical Center
Hypothesis
Transforming grayscale MRI data to color may provide additional information related to lesions resulting from multiple sclerosis.
Conclusion
The study suggests that colorizing MRI images can enhance the understanding of multiple sclerosis by revealing details not visible in grayscale.
Supporting Evidence
- Colorizing MRI data may provide more intuitive data to the observer.
- Color differences in lesions were consistent over a 10-year period.
- Quantitative MRI values suggested a relationship between lesion color and degree of brain injury.
Takeaway
This study shows that changing MRI images from black and white to color can help doctors see more details about brain problems caused by multiple sclerosis.
Methodology
Grayscale MRI images were transformed to color using a deep learning network trained on a diverse image dataset.
Limitations
The study is based on a single case, which may limit the generalizability of the findings.
Participant Demographics
A 31-year-old, right-handed, White man.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website