Back

SLOTMFound: Foundation-Based Diagnosis of Multiple Sclerosis Using Retinal SLO Imaging and OCT Thickness-maps

Esmailizadeh, R.; Aghababaei, A.; Mirzaei, S.; Arian, R.; Kafieh, R.

2025-07-15 neurology
10.1101/2025.07.14.25331522 medRxiv
Show abstract

Multiple Sclerosis (MS) is a chronic autoimmune disorder of the central nervous system that can lead to significant neurological disability. Retinal imaging--particularly Scanning Laser Ophthalmoscopy (SLO) and Optical Coherence Tomography (OCT)--provides valuable biomarkers for early MS diagnosis through non-invasive visualization of neurodegenerative changes. This study proposes a foundation-based bi-modal classification framework that integrates SLO images and OCT-derived retinal thickness maps for MS diagnosis. To facilitate this, we introduce two modality-specific foundation models--SLOFound and TMFound--fine-tuned from the RETFound-Fundus backbone using an independent dataset of 203 healthy eyes, acquired at Noor Ophthalmology Hospital with the Heidelberg Spectralis HRA+OCT system. This dataset, which contains only normal cases, was used exclusively for encoder adaptation and is entirely disjoint from the classification dataset. For the classification stage, we use a separate dataset comprising IR-SLO images from 32 MS patients and 70 healthy controls, collected at the Kashani Comprehensive MS Center in Isfahan, Iran. We first assess OCT-derived maps layer-wise and identify the Ganglion Cell-Inner Plexiform Layer (GCIPL) as the most informative for MS detection. All subsequent analyses utilize GCIPL thickness maps in conjunction with SLO images. Experimental evaluations on the MS classification dataset demonstrate that our foundation-based bi-modal model outperforms unimodal variants and a prior ResNet-based state-of-the-art model, achieving a classification accuracy of 97.37%, with perfect sensitivity (100%). These results highlight the effectiveness of leveraging pre-trained foundation models, even when fine-tuned on limited data, to build robust, efficient, and generalizable diagnostic tools for MS in medical imaging contexts where labeled datasets are often scarce.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Biomedical Optics Express
95 papers in training set
Top 0.1%
15.1%
2
Frontiers in Neurology
102 papers in training set
Top 0.3%
9.7%
3
Bioengineering
29 papers in training set
Top 0.1%
7.9%
4
npj Digital Medicine
118 papers in training set
Top 0.9%
6.3%
5
Communications Medicine
113 papers in training set
Top 0.4%
5.6%
6
PLOS Digital Health
106 papers in training set
Top 1%
5.2%
7
Scientific Reports
3612 papers in training set
Top 18%
5.2%
50% of probability mass above
8
PLOS ONE
5266 papers in training set
Top 31%
4.8%
9
IEEE Access
35 papers in training set
Top 0.2%
4.3%
10
Journal of Translational Medicine
57 papers in training set
Top 0.5%
2.1%
11
PLOS Computational Biology
1863 papers in training set
Top 14%
1.7%
12
Computational and Structural Biotechnology Journal
242 papers in training set
Top 4%
1.7%
13
Computers in Biology and Medicine
128 papers in training set
Top 2%
1.7%
14
Nature Communications
5641 papers in training set
Top 49%
1.3%
15
Scientific Data
209 papers in training set
Top 2%
1.3%
16
Multiple Sclerosis Journal
21 papers in training set
Top 0.1%
1.1%
17
Annals of Clinical and Translational Neurology
34 papers in training set
Top 0.8%
1.0%
18
IEEE Transactions on Biomedical Engineering
40 papers in training set
Top 0.9%
1.0%
19
Frontiers in Immunology
638 papers in training set
Top 9%
0.8%
20
Advanced Science
286 papers in training set
Top 9%
0.8%
21
Multiple Sclerosis and Related Disorders
15 papers in training set
Top 0.2%
0.8%
22
Translational Vision Science & Technology
39 papers in training set
Top 0.5%
0.8%
23
Human Brain Mapping
329 papers in training set
Top 4%
0.8%
24
Communications Biology
993 papers in training set
Top 30%
0.8%
25
Journal of Advanced Research
14 papers in training set
Top 0.4%
0.6%
26
Ophthalmology Science
22 papers in training set
Top 0.4%
0.6%
27
Eye
11 papers in training set
Top 0.3%
0.6%
28
GigaScience
212 papers in training set
Top 5%
0.6%