Multiple sclerosis (MS) is characterized by the concomitant presence of focal areas of inflammation (lesions) and diffuse damage and neurodegeneration (atrophy). Lesions identification on magnetic resonance imaging is a key biomarker in MS diagnosis. Further, lesions and brain atrophy quantification is an important step in monitoring disease progression and evaluating treatment efficacy. However, several challenges need to be faced when dealing with these two biomarkers. For what concerns lesions, although several tools have been developed during the last years, automated segmentation is still an open challenge and no satisfactory solution has yet been found. Nextly, recent evidences suggested the presence of inflammation and neurodegeneration from the early phase of MS. However, the dynamics of accumulation of lesions and brain atrophy is not completely understood. Here, we have faced the two MS challenges strictly related to lesions. We first dealt with the technical difficulties of MS automated lesion segmentation by developing a novel artificial intelligence pipeline, named BIANCA-MS. Afterwards, by using whole brain and voxel-wise analyses, we have investigated whether inflammation and neurodegeneration were two causally related processes or two separate pathological mechanisms. Our experiments highlighted how BIANCA-MS achieved significantly higher degree of similarity to the manual segmentation compared to other widely used tools. Further, the consistency and reproducibility of performances achieved across different datasets proved BIANCA-MS robustness and flexibility. These findings suggested that BIANCA-MS is a promising tool for accurate and robust MS automated lesions segmentation. When investigating the spatio-temporal relationship between inflammation and neurodegeneration, our analyses were indicative of a not causal relationship where lesion changes and brain atrophy developed simultaneously over time, thus suggesting that these are two partially independent mechanisms. Further, our results suggested also the presence of a causal relationship where lesion volume changes were related to subsequent faster atrophy. These findings highlighted how the relationship between inflammation and neurodegeneration is not restricted to a single direction but is more probably the sum of different models that are not mutually exclusive and could coexist at the same time. The results achieved here provided crucial insights on the inter-role between inflammation and neurodegeneration, which in turn will broaden our understandings of underlying disease mechanisms and will allow the development of more targeted therapeutic strategies.

Facing the current challenges in multiple sclerosis lesions: from automated segmentation to assessing the role of inflammation in neurodegeneration / Giordano Gentile. - (2022).

Facing the current challenges in multiple sclerosis lesions: from automated segmentation to assessing the role of inflammation in neurodegeneration

Giordano Gentile
2022

Abstract

Multiple sclerosis (MS) is characterized by the concomitant presence of focal areas of inflammation (lesions) and diffuse damage and neurodegeneration (atrophy). Lesions identification on magnetic resonance imaging is a key biomarker in MS diagnosis. Further, lesions and brain atrophy quantification is an important step in monitoring disease progression and evaluating treatment efficacy. However, several challenges need to be faced when dealing with these two biomarkers. For what concerns lesions, although several tools have been developed during the last years, automated segmentation is still an open challenge and no satisfactory solution has yet been found. Nextly, recent evidences suggested the presence of inflammation and neurodegeneration from the early phase of MS. However, the dynamics of accumulation of lesions and brain atrophy is not completely understood. Here, we have faced the two MS challenges strictly related to lesions. We first dealt with the technical difficulties of MS automated lesion segmentation by developing a novel artificial intelligence pipeline, named BIANCA-MS. Afterwards, by using whole brain and voxel-wise analyses, we have investigated whether inflammation and neurodegeneration were two causally related processes or two separate pathological mechanisms. Our experiments highlighted how BIANCA-MS achieved significantly higher degree of similarity to the manual segmentation compared to other widely used tools. Further, the consistency and reproducibility of performances achieved across different datasets proved BIANCA-MS robustness and flexibility. These findings suggested that BIANCA-MS is a promising tool for accurate and robust MS automated lesions segmentation. When investigating the spatio-temporal relationship between inflammation and neurodegeneration, our analyses were indicative of a not causal relationship where lesion changes and brain atrophy developed simultaneously over time, thus suggesting that these are two partially independent mechanisms. Further, our results suggested also the presence of a causal relationship where lesion volume changes were related to subsequent faster atrophy. These findings highlighted how the relationship between inflammation and neurodegeneration is not restricted to a single direction but is more probably the sum of different models that are not mutually exclusive and could coexist at the same time. The results achieved here provided crucial insights on the inter-role between inflammation and neurodegeneration, which in turn will broaden our understandings of underlying disease mechanisms and will allow the development of more targeted therapeutic strategies.
2022
Nicola De Stefano
Giordano Gentile
File in questo prodotto:
File Dimensione Formato  
PHD_THESIS_GIORDANO_GENTILE.pdf

Open Access dal 15/04/2023

Tipologia: Tesi di dottorato
Licenza: Open Access
Dimensione 3.8 MB
Formato Adobe PDF
3.8 MB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1265556
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact