The detection of new or enlarged white-matter lesions in multiple sclerosis is a vital task in the monitoring of patients undergoing disease-modifying treatment for multiple sclerosis. However, the definition of 'new or enlarged' is not fixed, and it is known that lesion-counting is highly subjective, with high degree of inter-and intra-rater variability. Automated methods for lesion quantification, if accurate enough, hold the potential to make the detection of new and enlarged lesions consistent and repeatable. However, the majority of lesion segmentation algorithms are not evaluated for their ability to separate radiologically progressive from radiologically stable patients, despite this being a pressing clinical use-case. In this paper we demonstrate that change in volumetric measurements of lesion load alone is not a good method for performing this separation, even for highly performing segmentation methods. Instead, we propose a method for identifying lesion changes of high certainty, and establish on an internal dataset of longitudinal multiple sclerosis cases that this method is able to separate progressive from stable timepoints with a very high level of discrimination (AUC = 0.999), while changes in lesion volume are much less able to perform this separation (AUC = 0.71). Validation of the method on a second external dataset confirms that the method is able to generalize beyond the setting in which it was trained, achieving an accuracy of 83 % in separating stable and progressive timepoints.Both lesion volume and lesion count have previously been shown to be, together with clinical covariates, strong predictors of disease course across a population. However, in this paper we demonstrate that for individual patients, changes in these measures are not an adequate means of establishing no evidence of disease activity. Meanwhile, directly detecting tissue which changes, with high confidence, from non-lesion to lesion is a feasible methodology for identifying radiologically active patients.

Segmentation of white matter lesions and deep grey matter structures is an important task in the quantification of magnetic resonance imaging in multiple sclerosis. In this paper we explore segmentation solutions based on convolutional neural networks (CNNs) for providing fast, reliable segmentations of lesions and grey-matter structures in multi-modal MR imaging, and the performance of these methods when applied to out-of-centre data. We trained two state-of-the-art fully convolutional CNN architectures on the 2016 MSSEG training dataset, which was annotated by seven independent human raters: a reference implementation of a 3D Unet, and a more recently proposed 3D-to-2D architecture (DeepSCAN). We then retrained those methods on a larger dataset from a single centre, with and without labels for other brain structures. We quantified changes in performance owing to dataset shift, and changes in performance by adding the additional brain-structure labels. We also compared performance with freely available reference methods. Both fully-convolutional CNN methods substantially outperform other approaches in the literature when trained and evaluated in cross-validation on the MSSEG dataset, showing agreement with human raters in the range of human inter-rater variability. Both architectures showed drops in performance when trained on single-centre data and tested on the MSSEG dataset. When trained with the addition of weak anatomical labels derived from Freesurfer, the performance of the 3D Unet degraded, while the performance of the DeepSCAN net improved. Overall, the DeepSCAN network predicting both lesion and anatomical labels was the best-performing network examined.

IntroductionVolumetric image analysis to detect progressive brain tissue loss in patients with multiple sclerosis (MS) has recently been suggested as a promising marker for “no evidence of disease activity.” Software packages for longitudinal whole-brain volume analysis in individual patients are already in clinical use; however, most of these methods have omitted region-based analysis. Here, we suggest a fully automatic analysis pipeline based on the free software packages FSL and FreeSurfer.Materials and methodsFifty-five T1-weighted magnetic resonance imaging (MRI) datasets of five patients with confirmed relapsing–remitting MS and mild to moderate disability were longitudinally analyzed compared to a morphometric reference database of 323 healthy controls (HCs). After lesion filling, the volumes of brain segmentations and morphometric parameters of cortical parcellations were automatically screened for global and regional abnormalities. Error margins and artifact probabilities of regional morphometric parameters were estimated. Linear models were fitted to the series of follow-up MRIs and checked for consistency with cross-sectional aging in HCs.ResultsAs compared to leave-one-out cross-validation in a subset of the control dataset, anomaly detection rates were highly elevated in MRIs of two patients. We detected progressive volume changes that were stronger than expected compared to normal aging in 4/5 patients. In individual patients, we also identified stronger than expected regional decreases of subcortical gray matter, of cortical thickness, and areas of reducing gray–white contrast over time.ConclusionStatistical comparison with a large normative database may provide complementary and rater independent quantitative information about regional morphological changes related to disease progression or drug-related disease modification in individual patients. Regional volume loss may also be detected in clinically stable patients.