Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosis
Multiple sclerosis (MS) falls within the spectrum of central nervous system (CNS) demyelinating diseases that may lead to permanent neurological disability. Fundamental to the diagnosis and clinical surveillance is magnetic resonance imaging (MRI) that allows for the identification of T2-hyperintens...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-12-01
|
| Series: | Journal of Central Nervous System Disease |
| Online Access: | https://doi.org/10.1177/11795735241310138 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558648337203200 |
|---|---|
| author | Darin T. Okuda Christine Lebrun-Frénay |
| author_facet | Darin T. Okuda Christine Lebrun-Frénay |
| author_sort | Darin T. Okuda |
| collection | DOAJ |
| description | Multiple sclerosis (MS) falls within the spectrum of central nervous system (CNS) demyelinating diseases that may lead to permanent neurological disability. Fundamental to the diagnosis and clinical surveillance is magnetic resonance imaging (MRI) that allows for the identification of T2-hyperintensities associated with autoimmune injury that demonstrate distinct spatial distribution patterns. Here, we describe the clinical experience of a 31-year-old, right-handed, White man seen in consultation at The University of Texas Southwestern Medical Center in Dallas, Texas, following complaints of headaches that began after head trauma related to military service. Imaging data spanning over 10 years are provided. All MRI data are currently presented in black and white with grayscale values within voxels associated with a single variable, intensity. We transformed these grayscale values into color using generative artificial intelligence (AI). As color allows for the inclusion of three variables: hue, lightness (intensity), and saturation, we hypothesized that additional details may be learned beyond those currently provided with the existing conventional approach of grayscale interpretation. We identified differences in lesion colors that remained consistent from the two MRI timepoints studied. In addition, quantitative R1, R2, and proton density voxel values appeared consistent with the color scheme generated by the AI system. With advancing AI methods and capabilities along with the additional data that color provides in comparison to grayscale, new insights into the biology of disease may be possible. Modifying what we measure in people with chronic conditions and how we present the data may be of greater value than conventional approaches typically used in the study, education, and care of people with MS and other neurological conditions. |
| format | Article |
| id | doaj-art-99a596a682984880a5ad6094a85c0ed4 |
| institution | Kabale University |
| issn | 1179-5735 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Journal of Central Nervous System Disease |
| spelling | doaj-art-99a596a682984880a5ad6094a85c0ed42025-01-06T07:03:27ZengSAGE PublishingJournal of Central Nervous System Disease1179-57352025-12-011710.1177/11795735241310138Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosisDarin T. OkudaChristine Lebrun-FrénayMultiple sclerosis (MS) falls within the spectrum of central nervous system (CNS) demyelinating diseases that may lead to permanent neurological disability. Fundamental to the diagnosis and clinical surveillance is magnetic resonance imaging (MRI) that allows for the identification of T2-hyperintensities associated with autoimmune injury that demonstrate distinct spatial distribution patterns. Here, we describe the clinical experience of a 31-year-old, right-handed, White man seen in consultation at The University of Texas Southwestern Medical Center in Dallas, Texas, following complaints of headaches that began after head trauma related to military service. Imaging data spanning over 10 years are provided. All MRI data are currently presented in black and white with grayscale values within voxels associated with a single variable, intensity. We transformed these grayscale values into color using generative artificial intelligence (AI). As color allows for the inclusion of three variables: hue, lightness (intensity), and saturation, we hypothesized that additional details may be learned beyond those currently provided with the existing conventional approach of grayscale interpretation. We identified differences in lesion colors that remained consistent from the two MRI timepoints studied. In addition, quantitative R1, R2, and proton density voxel values appeared consistent with the color scheme generated by the AI system. With advancing AI methods and capabilities along with the additional data that color provides in comparison to grayscale, new insights into the biology of disease may be possible. Modifying what we measure in people with chronic conditions and how we present the data may be of greater value than conventional approaches typically used in the study, education, and care of people with MS and other neurological conditions.https://doi.org/10.1177/11795735241310138 |
| spellingShingle | Darin T. Okuda Christine Lebrun-Frénay Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosis Journal of Central Nervous System Disease |
| title | Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosis |
| title_full | Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosis |
| title_fullStr | Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosis |
| title_full_unstemmed | Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosis |
| title_short | Transforming grayscale MRI images to color utilizing generative artificial intelligence to better understand multiple sclerosis |
| title_sort | transforming grayscale mri images to color utilizing generative artificial intelligence to better understand multiple sclerosis |
| url | https://doi.org/10.1177/11795735241310138 |
| work_keys_str_mv | AT darintokuda transforminggrayscalemriimagestocolorutilizinggenerativeartificialintelligencetobetterunderstandmultiplesclerosis AT christinelebrunfrenay transforminggrayscalemriimagestocolorutilizinggenerativeartificialintelligencetobetterunderstandmultiplesclerosis |