Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system (CNS) affecting more than half a million persons in Europe, with prevalence rate of 83 per 100 000 with higher rates in northern countries. Today, conventional MRI is widely used for disease diagnosis, patient follow-up, monitoring of therapies, and more generally for the understanding of the natural history of MS. One of the major challenges in using MRI for MS is the segmentation of lesions whose number and appearance are crucial indicators for diagnostic and treatment follow-up. To cope with inter- and intra-observer variability and remove the burden of manual segmentation from the clinicians, a large number of techniques have been proposed in the literature towards automatically segmenting MS lesions.
The literature is however very scarce on the delineation and detection of new MS lesions on T2/FLAIR, i.e. lesions that appear at a new time point. This marker is however even more crucial than the total number and volume of lesions, as the accumulation of new lesions allows clinicians to assess if a given anti-inflammatory disease modifying drug (DMD) works for the patient. As of now, the only efficient indicator of drug efficacy is indeed the absence of new T2 lesions within the CNS. Automating the detection of these new lesions would therefore be a major advance for evaluating the patient disease activity. Recent advances in segmentation methods, in particular with the recent achievements of machine learning classification methods, now open the way to tackle this automatic detection problem and provide clinicians with this very valuable information for treatment adaptation. We have therefore organized, in conjunction with MICCAI 2021, the MSSEG-2 MS lesion detection challenge on this topic and now propose to authors from the community an opportunity to submit their methods to this research topic.
We welcome research articles contributions to this research topic that are aimed at developing methods for multiple sclerosis new lesions detection and segmentation from magnetic resonance images of the brain. Examples of research directions include but are not limited to:
- Machine learning (random forests, deep learning, …)
- Tissue classification methods
- Longitudinal analysis methods
- Cross-sectional methods applied to several time points
Pr Michel Dojat is the co-founder of Pixyl, an artificial intelligence company based in Grenoble having products for MS segmentation. Other guest editors do not have any competing interest.
Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system (CNS) affecting more than half a million persons in Europe, with prevalence rate of 83 per 100 000 with higher rates in northern countries. Today, conventional MRI is widely used for disease diagnosis, patient follow-up, monitoring of therapies, and more generally for the understanding of the natural history of MS. One of the major challenges in using MRI for MS is the segmentation of lesions whose number and appearance are crucial indicators for diagnostic and treatment follow-up. To cope with inter- and intra-observer variability and remove the burden of manual segmentation from the clinicians, a large number of techniques have been proposed in the literature towards automatically segmenting MS lesions.
The literature is however very scarce on the delineation and detection of new MS lesions on T2/FLAIR, i.e. lesions that appear at a new time point. This marker is however even more crucial than the total number and volume of lesions, as the accumulation of new lesions allows clinicians to assess if a given anti-inflammatory disease modifying drug (DMD) works for the patient. As of now, the only efficient indicator of drug efficacy is indeed the absence of new T2 lesions within the CNS. Automating the detection of these new lesions would therefore be a major advance for evaluating the patient disease activity. Recent advances in segmentation methods, in particular with the recent achievements of machine learning classification methods, now open the way to tackle this automatic detection problem and provide clinicians with this very valuable information for treatment adaptation. We have therefore organized, in conjunction with MICCAI 2021, the MSSEG-2 MS lesion detection challenge on this topic and now propose to authors from the community an opportunity to submit their methods to this research topic.
We welcome research articles contributions to this research topic that are aimed at developing methods for multiple sclerosis new lesions detection and segmentation from magnetic resonance images of the brain. Examples of research directions include but are not limited to:
- Machine learning (random forests, deep learning, …)
- Tissue classification methods
- Longitudinal analysis methods
- Cross-sectional methods applied to several time points
Pr Michel Dojat is the co-founder of Pixyl, an artificial intelligence company based in Grenoble having products for MS segmentation. Other guest editors do not have any competing interest.