Quantification of multiple sclerosis lesion load and brain tissue volumetry using multiparameter MRI: methodology and reproducibility

Lesion Volume Quantification Using Two Convolutional Neural Networks in MRIs of Multiple Sclerosis Patients

Background: Multiple sclerosis (MS) is a neurologic disease of the central nervous system which affects almost three million people worldwide. MS is characterized by a demyelination process that leads to brain lesions, allowing these affected areas to be visualized with magnetic resonance imaging (MRI). Deep learning techniques, especially computational algorithms based on convolutional neural networks (CNNs), have become a frequently used algorithm that performs feature self-learning and enables segmentation of structures in the image useful for quantitative analysis of MRIs, including quantitative analysis of MS. To obtain quantitative information about lesion volume, it is important to perform proper image preprocessing and accurate segmentation. Therefore, we propose a method for volumetric quantification of lesions on MRIs of MS patients using automatic segmentation of the brain and lesions by two CNNs. Methods: We used CNNs at two different moments: the first to perform brain extraction, and the second for lesion segmentation. This study includes four independent MRI datasets: one for training the brain segmentation models, two for training the lesion segmentation model, and one for testing. Results: The proposed brain detection architecture using binary cross-entropy as the loss function achieved a 0.9786 Dice coefficient, 0.9969 accuracy, 0.9851 precision, 0.9851 sensitivity, and 0.9985 specificity. In the second proposed framework for brain lesion segmentation, we obtained a 0.8893 Dice coefficient, 0.9996 accuracy, 0.9376 precision, 0.8609 sensitivity, and 0.9999 specificity. After quantifying the lesion volume of all patients from the test group using our proposed method, we obtained a mean value of 17,582 mm3. Conclusions: We concluded that the proposed algorithm achieved accurate lesion detection and segmentation with reproducibility corresponding to state-of-the-art software tools and manual segmentation. We believe that this quantification method can add value to treatment monitoring and routine clinical evaluation of MS patients.

Differential impact of lacunes and microvascular lesions on poststroke depression

BACKGROUND AND PURPOSE

Previous studies have postulated that poststroke depression (PSD) might be related to cumulative vascular brain pathology rather than to the location and severity of a single macroinfarct. We performed a detailed analysis of all types of microvascular lesions and lacunes in 41 prospectively documented and consecutively autopsied stroke cases.

METHODS

Only cases with first-onset depression <2 years after stroke were considered as PSD in the present series. Diagnosis of depression was established prospectively using DSM-IV criteria for major depression. Neuropathological evaluation included bilateral semiquantitative assessment of microvascular ischemic pathology and lacunes; statistical analysis included Fisher exact test, Mann-Whitney U test, and regression models.

RESULTS

Macroinfarct site was not related to the occurrence of PSD for any of the locations studied. Thalamic and basal ganglia lacunes occurred significantly more often in PSD cases. Higher lacune scores in basal ganglia, thalamus, and deep white matter were associated with an increased PSD risk. In contrast, microinfarct and diffuse or periventricular demyelination scores were not increased in PSD. The combined lacune score (thalamic plus basal ganglia plus deep white matter) explained 25% of the variability of PSD occurrence.

CONCLUSIONS

The cumulative vascular burden resulting from chronic accumulation of lacunar infarcts within the thalamus, basal ganglia, and deep white matter may be more important than single infarcts in the prediction of PSD.

Volume and shape in feature space on adaptive FCM in MRI segmentation

Intensity non-uniformity (bias field) correction, contextual constraints over spatial intensity distribution and non-spherical cluster's shape in the feature space are incorporated into the fuzzy c-means (FCM) for segmentation of three-dimensional multi-spectral MR images. The bias field is modeled by a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of either intensity or membership are added into the FCM cost functions. Since the feature space is not isotropic, distance measures, other than the Euclidean distance, are used to account for the shape and volumetric effects of clusters in the feature space. The performance of segmentation is improved by combining the adaptive FCM scheme with the criteria used in Gustafson-Kessel (G-K) and Gath-Geva (G-G) algorithms through the inclusion of the cluster scatter measure. The performance of this integrated approach is quantitatively evaluated on normal MR brain images using the similarity measures. The improvement in the quality of segmentation obtained with our method is also demonstrated by comparing our results with those produced by FSL (FMRIB Software Library), a software package that is commonly used for tissue classification.

Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images

An integrated approach for multi-spectral segmentation of MR images is presented. This method is based on the fuzzy c-means (FCM) and includes bias field correction and contextual constraints over spatial intensity distribution and accounts for the non-spherical cluster's shape in the feature space. The bias field is modeled as a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of intensity are added into the FCM cost functions. To reduce the computational complexity, the contextual regularizations are separated from the clustering iterations. Since the feature space is not isotropic, distance measure adopted in Gustafson-Kessel (G-K) algorithm is used instead of the Euclidean distance, to account for the non-spherical shape of the clusters in the feature space. These algorithms are quantitatively evaluated on MR brain images using the similarity measures.

Cerebrovascular effects of hemodialysis in chronic kidney disease

Patients with end-stage renal disease (ESRD) undergoing hemodialysis are known to suffer cognitive deficits and stroke of unknown etiology. It has been suspected that the treatment itself may contribute to the syndrome by unknown mechanisms, which we investigated in this study. End-stage renal disease patients on hemodialysis (n=19) or peritoneal dialysis (PD, n=5) were compared with 14 healthy controls. Subjects participated in magnetic resonance imaging (MRI) measurements of cerebral atrophy, cerebral blood flow (CBF) arterial spin labeled-MRI (ASL-MRI), quantitative Doppler blood flow through the internal carotid artery, and cerebral oxymetry. The Doppler and oxymetry procedures were also performed at the beginning and end of a single hemodialysis session. End-stage renal disease patients on hemodialysis showed significant cerebral atrophy, associated with longer hemodialysis duration and cognitive deficits, including focal bilateral lesions in the caudate nucleus and midbrain. Cerebral oxygenation was extremely low before dialysis (rSO(2) 41+/-13, compared with 70+/-2 in controls, P<0.02) and improved only slightly after dialysis. Carotid blood flow was also very low at the start of dialysis (115+/-28 mL/sec, versus 193+/-56 in controls, P<0.005) but normalized at the end of the session (181 mL/sec). The PD patients showed intermediate values, between the hemodialysis and controls. Notably, duration of hemodialysis treatment predicted global gray-matter volume (r=-0.74), change of blood flow during dialysis (r=-0.65), and baseline rSO(2) (r=-0.65). The findings suggest that ESRD patients on hemodialysis suffer low CBF during the interdialytic cycle. Coupled with low cerebral oxygenation levels and atherosclerosis, this may contribute significantly to the etiology of the observed cerebral atrophy, cognitive deficits, and high stroke prevalence.