Tobin, W. Oliver

AbstractObjectiveIn this observational study on a cohort of biopsy‐proven central nervous system demyelinating disease consistent with MS, we examined the relationship between early‐active demyelinating lesion immunopattern (IP) with subsequent clinical course, radiographic progression, and cognitive function.MethodsSeventy‐five patients had at least one early‐active lesion on biopsy and were pathologically classified into three immunopatterns based on published criteria. The median time from biopsy at follow‐up was 11 years, median age at biopsy ‐ 41, EDSS ‐ 4.0. At last follow‐up, the median age was 50, EDSS ‐ 3.0. Clinical examination, cognitive assessment (CogState battery), and 3‐Tesla‐MRI (MPRAGE/FLAIR/T2/DIR/PSIR/DTI) were obtained.ResultsIP‐I was identified in 14/75 (19%), IP‐II was identified in 41/75 (56%), and IP‐III was identified in 18/75 (25%) patients. Patients did not differ significantly by immunopattern in clinical measures at onset or last follow‐up. The proportions of disease courses after a median of 11 years were similar across immunopatterns, relapsing–remitting being most common (63%), followed by monophasic (32%). No differences in volumetric or DTI measures were found. CogState performance was similar for most tasks. A slight yet statistically significant difference was identified for episodic memory scores, with IP‐III patients recalling one word less on average.InterpretationIn this study, immunopathological heterogeneity of early‐active MS lesions identified at biopsy does not correlate with different long‐term clinical, neuroimaging or cognitive outcomes. This could be explained by the fact that while active white matter lesions are pathological substrates for relapses, MS progression is driven by mechanisms converging across immunopatterns, regardless of pathogenic mechanisms driving the acute demyelinated plaque.

Abstract Missing MRI sequences are common in radiology due to differences in protocols, time constraints, and image artifacts. Missing sequences are a nuisance for subsequent algorithms, such as automated segmentation algorithms requiring multiple MRI sequences (e.g., HD-GLIO, which requires T2, T1, post-contrast T1 (T1c), and FLAIR). Accurate tumor segmentation is a fundamental step in extracting radiomics analysis to use, for example, to predict the IDH status of glioma or their overall survival. We validated a conditional (pix2pix) and super-resolution GAN (SOUP-GAN) for imputing MRI sequences on 285 adult glioma with complete MRI sequences available. We simulated missing T1 sequences and subsequently imputed them from T1c using pix2pix and from sagittal T1 using SOUP-GAN. Using HD-GLIO, we obtained the true segmentations from the complete MRI sequences. HD-GLIO was also used after replacing the original T1 sequence with the one imputed with pix2pix and SOUP-GAN. Thus, there were three sets of segmentations for each subject. We compared T2 and T1c radiomics features extracted with Pyradiomics using segmentations obtained with complete data with features extracted from segmentation obtained with the imputed T1 sequences using intraclass correlation coefficient (ICC) and Bland-Altman (BA) analysis. Median (interquartile range) ICC for shape features extracted from T2 and T1c were 0.82(0.76-0.92) using pix2pix and 0.89(0.86-0.94) using SOUP-GAN. Median ICC for first-order-statistics features were 0.90(0.83-0.93) for T2 and 0.90(0.88-0.92) for T1c using pix2pix, and 0.61(0.22-0.82) for T2 and 0.42(0.34-0.57) for T1c using SOUP-GAN. Median ICC for texture features were 0.86(0.82-0.87) for T2 and 0.87(0.79-0.90) for T1c using pix2pix, and 0.69(0.47-0.81) for T2 and 0.76(0.65-0.83) for T1c using SOUP-GAN. We show that T2 and T1c shape features (e.g., volumetric analysis) can be adequately extracted from segmentations obtained with an algorithm requiring multiple MRI sequences using T1 sequences imputed with GANs; however, the effect of imputation differed for first-order-statistics and texture features.