| 1. |
- Brusini, Irene, et al.
(author)
-
Shape Information Improves the Cross-Cohort Performance of Deep Learning-Based Segmentation of the Hippocampus
- 2020
-
In: Frontiers in Neuroscience. - : Frontiers Media S.A.. - 1662-4548 .- 1662-453X. ; 14
-
Journal article (peer-reviewed)abstract
- Performing an accurate segmentation of the hippocampus from brain magnetic resonance images is a crucial task in neuroimaging research, since its structural integrity is strongly related to several neurodegenerative disorders, including Alzheimer's disease (AD). Some automatic segmentation tools are already being used, but, in recent years, new deep learning (DL)-based methods have been proven to be much more accurate in various medical image segmentation tasks. In this work, we propose a DL-based hippocampus segmentation framework that embeds statistical shape of the hippocampus as context information into the deep neural network (DNN). The inclusion of shape information is achieved with three main steps: (1) a U-Net-based segmentation, (2) a shape model estimation, and (3) a second U-Net-based segmentation which uses both the original input data and the fitted shape model. The trained DL architectures were tested on image data of three diagnostic groups [AD patients, subjects with mild cognitive impairment (MCI) and controls] from two cohorts (ADNI and AddNeuroMed). Both intra-cohort validation and cross-cohort validation were performed and compared with the conventional U-net architecture and some variations with other types of context information (i.e., autocontext and tissue-class context). Our results suggest that adding shape information can improve the segmentation accuracy in cross-cohort validation, i.e., when DNNs are trained on one cohort and applied to another. However, no significant benefit is observed in intra-cohort validation, i.e., training and testing DNNs on images from the same cohort. Moreover, compared to other types of context information, the use of shape context was shown to be the most successful in increasing the accuracy, while keeping the computational time in the order of a few minutes.
|
|
| 2. |
- Ekman, Urban, et al.
(author)
-
The MemClin project : a prospective multi memory clinics study targeting early stages of cognitive impairment
- 2020
-
In: BMC Geriatrics. - : BMC. - 1471-2318. ; 20
-
Journal article (peer-reviewed)abstract
- Background: There remains a lack of large-scale clinical studies of cognitive impairment that aim to increase diagnostic and prognostic accuracy as well as validate previous research findings. The MemClin project will amass large quantities of cross-disciplinary data allowing for the construction of robust models to improve diagnostic accuracy, expand our knowledge on differential diagnostics, strengthen longitudinal prognosis, and harmonise examination protocols across centres. The current article describes the Memory Clinic (MemClin) project's study-design, materials and methods, and patient characteristics. In addition, we present preliminary descriptive data from the ongoing data collection.Methods: Nine out of ten memory clinics in the greater Stockholm area, which largely use the same examination methods, are included. The data collection of patients with different stages of cognitive impairment and dementia is coordinated centrally allowing for efficient and secure large-scale database construction. The MemClin project rest directly on the memory clinics examinations with cognitive measures, health parameters, and biomarkers.Results: Currently, the MemClin project has informed consent from 1543 patients. Herein, we present preliminary data from 835 patients with confirmed cognitive diagnosis and neuropsychological test data available. Of those, 239 had dementia, 487 mild cognitive impairment (MCI), and 104 subjective cognitive impairment (SCI). In addition, we present descriptive data on visual ratings of brain atrophy and cerebrospinal fluid markers.Conclusions: Based on our current progress and preliminary data, the MemClin project has a high potential to provide a large-scale database of 1200-1500 new patients annually. This coordinated data collection will allow for the construction of improved diagnostic and prognostic models for neurodegenerative disorders and other cognitive conditions in their naturalistic setting.
|
|
