Optical Coherence Tomography in the Differential Diagnosis of Patients with Multiple Sclerosis and Patients with MRI Nonspecific White Matter Lesions

[Optical coherence tomography in the diagnosis of multiple sclerosis]

Multiple sclerosis (MS) is a chronic autoimmune-inflammatory and neurodegenerative disease.

PURPOSE

This study explores the main structural changes in patients with MS and their relationships with the activity and type of disease course.

MATERIAL AND METHODS

This prospective study included 159 patients (318 eyes) with an established diagnosis of MS: group (44 eyes; 13.84%) - relapsing-remitting type MS (RRMS) lasting up to 1 year without a history of optic neuritis (ON); group 2 (30 eyes; 9.43%) - RRMS up to 1 year with ON; group 3 (56 eyes; 17.61%) - RRMS lasting from 1 to 10 years without ON; group 4 (38 eyes; 11.95%) - RRMS from 1 to 10 years with ON; group 5 (49 eyes; 15.41%) - RRMS >10 years without ON; group 6 (37 eyes; 11.63%) - RRMS >10 years with ON; group 7 (34 eyes; 10.69%) - secondary progressive multiple sclerosis (SPMS) without ON; group 8 (30 eyes; 9.43%) - SPMS with ON. Patients underwent standard ophthalmological examinations, including optical coherence tomography.

RESULTS

A decrease in structural parameters was diagnosed, progressing with the duration of the disease and the presence of ON: the minimum values of mGCL+IPL (65.83±9.14 μm) and mSNFL (76.37±14.77 μm) were detected in the group with SPMS with ON. High inverse correlations of EDSS with mGCL+IPL and mRNFL were demonstrated, with maximum in the group with the longest duration of MS without ON (-0.48 and -0.52 (p=0.01), respectively).

CONCLUSION

Changes in the thickness of the structural parameters of the retina, measured by OCT, can be considered as a predictor of the course of MS.

Artificial intelligence model driven by transfer learning for image-based medical diagnosis

Artificial intelligent (AI) systems for clinical-decision support are an important tool in clinical routine. It has become a crucial diagnostic tool with adequate reliability and interpretability in disease diagnosis and monitoring. Undoubtedly, these models are faced with insufficient data challenges for training, which often directly determines the model’s performance. In order word, insufficient data for model training leads to inefficiency in the model built. To overcome this problem, we propose an AI-driven model by transfer learning in accurate diagnosis for medical decision support. Our approach leverages the shortage of data with a pretrained model by training the neural network with a fraction of the new dataset. For this purpose, we utilized the VGG19 network as the backbone network to support our model in integrating known features with the newly learned features for accurate diagnosis and decision making. Integrating this trained model speeds up the training phase and improve the performance of the proposed model. Experimental results show that the proposed model is effective and efficient in diagnosing different medical diseases. As such, we anticipated that this diagnosis tool will ultimately aid in facilitating early treatment of these treatable diseases, which will improve clinical out-comes.