IC-P-139: Accurate automatic segmentation of white matter hyperintensities using a linear regression classifier

Introduction: Cerebral White matter hyperintensities(WMH) are frequent findings on MRI scan. They are well known to correlate with vascular cognitive impairment(VCI). However, controversies still remain about the relationship between WMH locations and cognitive function across studies. Hypothesis: Periventricular WMHs(PWH) rather than deep WMHs(DWH) are associated with cognitive decline in VCI. Methods: Fifty-nine subjects with WMHs on MRI were divided into three groups, normal control(NC), mild cognitive impairment(MCI) and vascular dementia(VaD), according to clinical manifestation and neuropsychological performance. WMH volumes were evaluated by Fazekas rating scale and segmental volumetric. Correlations between cognitive performance and WMH volumes were determined in virtue of Spearman correlation analysis. Receiver operator characteristic (ROC) curves were generated to define the classification cut-off value of WMH volumes for distinguishing VCI versus normal controls. Multiple linear regression analysis was used to predict cognitive performance with WMH volumes and locations after adjusting for sex ,age and education level. Results: Cognitive capacities were gradually declined from NC through MCI to VaD patients while WMH volumes and Fazekas scores altered oppositely. Both PWH and DWH volumes and Fazekas scores were correlated with cognitive performance, and moreover, WMH volumes were correlated with Fazekas scores. ROC analysis showed a cut-off value of PWH rather than DWH to distinguish VCI from NC(AUC=0.745 and 0.635, p =0.001 and 0.076, respectively). Linear regression analysis demonstrated that only PWH volumes were associated with cognitive performance( p < 0.001). Conclusion: Our study demonstrate that PWHs are independent predictors for vascular contribution in white matter lesions and suggest clinicians that PWH should be emphasized on evaluating vascular cognitive impairment related with white matter load.

Download Full-text

Segmentation of Cerebral Small Vessel Diseases-White Matter Hyperintensities Based on a Deep Learning System

Frontiers in Medicine ◽

10.3389/fmed.2021.681183 ◽

2021 ◽

Vol 8 ◽

Author(s):

Wei Shan ◽

Yunyun Duan ◽

Yu Zheng ◽

Zhenzhou Wu ◽

Shang Wei Chan ◽

...

Keyword(s):

Deep Learning ◽

White Matter ◽

White Matter Hyperintensities ◽

Automatic Segmentation ◽

Learning System ◽

Test Set ◽

Minor Revision ◽

Lesion Level ◽

External Test ◽

Cerebral Small Vessel Diseases

Objective: Reliable quantification of white matter hyperintensities (WHMs) resulting from cerebral small vessel diseases (CSVD) is essential for understanding their clinical impact. We aim to develop and clinically validate a deep learning system for automatic segmentation of CSVD-WMH from fluid-attenuated inversion recovery (FLAIR) imaging using large multicenter data.Method: A FLAIR imaging dataset of 1,156 patients diagnosed with CSVD associated WMH (median age, 54 years; 653 males) obtained between September 2018 and September 2019 from Beijing Tiantan Hospital was retrospectively analyzed in this study. Locations of CSVD-WMH on the FLAIR scans were manually marked by two experienced neurologists. Using the manually labeled data of 996 patients (development set), a U-shaped novel 2D convolutional neural network (CNN) architecture was trained for automatic segmentation of CSVD-WMH. The segmentation performance of the network was evaluated with per pixel and lesion level dice scores using an independent internal test set (n = 160) and a multi-center external test set (n = 90, three medical centers). The clinical suitability of the segmentation results, classified as acceptable, acceptable with minor revision, acceptable with major revision, and not acceptable, was analyzed by three independent neuroradiologists. The inter-neuroradiologists agreement rate was assessed by the Kendall-W test.Results: On the internal and external test sets, the proposed CNN architecture achieved per pixel and lesion level dice scores of 0.72 (external test set), and they were significantly better than the state-of-the-art deep learning architectures proposed for WMH segmentation. In the clinical evaluation, neuroradiologists observed the segmentation results for 95% of the patients were acceptable or acceptable with a minor revision.Conclusions: A deep learning system can be used for automated, objective, and clinically meaningful segmentation of CSVD-WMH with high accuracy.

Download Full-text

Investigating the Contribution of White Matter Hyperintensities and Cortical Thickness to Empathy in Neurodegenerative and Cerebrovascular Diseases

10.1101/2021.08.01.454640 ◽

2021 ◽

Author(s):

Miracle Ozzoude ◽

Brenda Varriano ◽

Derek Beaton ◽

Joel Ramirez ◽

Melissa F Holmes ◽

...

Keyword(s):

White Matter ◽

Cortical Thickness ◽

Brain Atrophy ◽

White Matter Hyperintensities ◽

Automatic Segmentation ◽

Cerebrovascular Diseases ◽

Cortical Atrophy ◽

Reactivity Index ◽

Empathy Deficits ◽

Longitudinal Effects

Introduction: Change in empathy is an increasingly recognised symptom of neurodegenerative diseases and contributes to caregiver burden and patient distress. Empathy impairment has been associated with brain atrophy but its relationship to white matter hyperintensities (WMH) is unknown. We aimed to investigate the relationships amongst WMH, brain atrophy, and empathy deficits in neurodegenerative and cerebrovascular diseases. Methods: 513 participants with Alzheimers Disease/Mild Cognitive Impairment, Amyotrophic Lateral Sclerosis, Frontotemporal Dementia (FTD), Parkinsons Disease, or Cerebrovascular Disease (CVD) were included. Empathy was assessed using the Interpersonal Reactivity Index. WMH were measured using a semi-automatic segmentation and FreeSurfer was used to measure cortical thickness. Results: A heterogeneous pattern of cortical thinning was found between groups, with FTD showing thinning in frontotemporal regions and CVD in left superior parietal, left insula, and left postcentral. Results from both univariate and multivariate analyses revealed that several variables were associated with empathy, particularly cortical thickness in the fronto-insulo-temporal and cingulate regions, sex(female), global cognition, and right parietal and occipital WMH. Conclusions: Our results suggest that cortical atrophy and WMH may be associated with empathy deficits in neurodegenerative and cerebrovascular diseases. Future work should consider investigating the longitudinal effects of WMH and atrophy on empathy deficits in neurodegenerative and cerebrovascular diseases.

Download Full-text