Dataset Information

Deep learning assisted quantitative assessment of histopathological markers of Alzheimer's disease and cerebral amyloid angiopathy.

ABSTRACT: Traditionally, analysis of neuropathological markers in neurodegenerative diseases has relied on visual assessments of stained sections. Resulting semiquantitative scores often vary between individual raters and research centers, limiting statistical approaches. To overcome these issues, we have developed six deep learning-based models, that identify some of the most characteristic markers of Alzheimer's disease (AD) and cerebral amyloid angiopathy (CAA). The deep learning-based models are trained to differentially detect parenchymal amyloid β (Aβ)-plaques, vascular Aβ-deposition, iron and calcium deposition, reactive astrocytes, microglia, as well as fibrin extravasation. The models were trained on digitized histopathological slides from brains of patients with AD and CAA, using a workflow that allows neuropathology experts to train convolutional neural networks (CNNs) on a cloud-based graphical interface. Validation of all models indicated a very good to excellent performance compared to three independent expert human raters. Furthermore, the Aβ and iron models were consistent with previously acquired semiquantitative scores in the same dataset and allowed the use of more complex statistical approaches. For example, linear mixed effects models could be used to confirm the previously described relationship between leptomeningeal CAA severity and cortical iron accumulation. A similar approach enabled us to explore the association between neuroinflammation and disparate Aβ pathologies. The presented workflow is easy for researchers with pathological expertise to implement and is customizable for additional histopathological markers. The implementation of deep learning-assisted analyses of histopathological slides is likely to promote standardization of the assessment of neuropathological markers across research centers, which will allow specific pathophysiological questions in neurodegenerative disease to be addressed in a harmonized way and on a larger scale.

SUBMITTER: Perosa V

PROVIDER: S-EPMC8380352 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Alzheimer's disease (AD) is characterized by amyloid beta (A?) deposits as plaques in the parenchyma and in the walls of cortical and leptomeningeal blood vessels of the brain called cerebral amyloid angiopathy (CAA). It is suggested that CAA type-1, which refers to amyloid deposition in both capillaries and larger vessels, adds to the symptomatic manifestation of AD and correlates with disease severity. Currently, CAA cannot be diagnosed pre-mortem and disease mechanisms involved in CAA are elusive. To obtain insight in the disease mechanism of CAA and to identify marker proteins specifically associated with CAA we performed a laser dissection microscopy assisted mass spectrometry analysis of post-mortem human brain tissue of (I) AD cases with only amyloid deposits in the brain parenchyma and no vascular related amyloid, (II) AD cases with severe CAA type-1 and no or low numbers of parenchymal amyloid deposits and (III) cognitively healthy controls without amyloid deposits. By contrasting the quantitative proteomics data between the three groups, 29 potential CAA-selective proteins were identified. A selection of these proteins was analysed by immunoblotting and immunohistochemistry to confirm regulation and to determine protein localization and their relation to brain pathology. In addition, specificity of these markers in relation to other small vessel diseases including prion CAA, CADASIL, CARASAL and hypertension related small vessel disease was assessed using immunohistochemistry.Increased levels of clusterin (CLU), apolipoprotein E (APOE) and serum amyloid P-component (APCS) were observed in AD cases with CAA. In addition, we identified norrin (NDP) and collagen alpha-2(VI) (COL6A2) as highly selective markers that are clearly present in CAA yet virtually absent in relation to parenchymal amyloid plaque pathology. NDP showed the highest specificity to CAA when compared to other small vessel diseases. The specific changes in the proteome of CAA provide new insight in the pathogenesis and yields valuable selective biomarkers for the diagnosis of CAA.

Dataset Information

Deep learning assisted quantitative assessment of histopathological markers of Alzheimer's disease and cerebral amyloid angiopathy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets