Dataset Information

Digital pathology and image analysis for robust high-throughput quantitative assessment of Alzheimer disease neuropathologic changes.

ABSTRACT: Quantitative neuropathologic methods provide information that is important for both research and clinical applications. The technologic advancement of digital pathology and image analysis offers new solutions to enable valid quantification of pathologic severity that is reproducible between raters regardless of experience. Using an Aperio ScanScope XT and its accompanying image analysis software, we designed algorithms for quantitation of amyloid and tau pathologies on 65 ?-amyloid (6F/3D antibody) and 48 phospho-tau (PHF-1)-immunostained sections of human temporal neocortex. Quantitative digital pathologic data were compared with manual pathology counts. There were excellent correlations between manually counted and digitally analyzed neuropathologic parameters (R² = 0.56-0.72). Data were highly reproducible among 3 participants with varying degrees of expertise in neuropathology (intraclass correlation coefficient values, >0.910). Digital quantification also provided additional parameters, including average plaque area, which shows statistically significant differences when samples are stratified according to apolipoprotein E allele status (average plaque area, 380.9 ?m² in apolipoprotein E [Latin Small Letter Open E]4 carriers vs 274.4 ?m² for noncarriers; p < 0.001). Thus, digital pathology offers a rigorous and reproducible method for quantifying Alzheimer disease neuropathologic changes and may provide additional insights into morphologic characteristics that were previously more challenging to assess because of technical limitations.

SUBMITTER: Neltner JH

PROVIDER: S-EPMC3511606 | biostudies-literature | 2012 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Digital pathology and image analysis for robust high-throughput quantitative assessment of Alzheimer disease neuropathologic changes.

Neltner Janna Hackett JH Abner Erin Lynn EL Schmitt Frederick A FA Denison Stephanie Kay SK Anderson Sonya S Patel Ela E Nelson Peter T PT

Journal of neuropathology and experimental neurology 20121201 12

Quantitative neuropathologic methods provide information that is important for both research and clinical applications. The technologic advancement of digital pathology and image analysis offers new solutions to enable valid quantification of pathologic severity that is reproducible between raters regardless of experience. Using an Aperio ScanScope XT and its accompanying image analysis software, we designed algorithms for quantitation of amyloid and tau pathologies on 65 β-amyloid (6F/3D antibo ...[more]

PMID: 23147505

Similar Datasets

Project description:ImportancePositron emission tomography (PET) may increase the diagnostic accuracy and confirm the underlying neuropathologic changes of Alzheimer disease (AD).ObjectiveTo determine the accuracy of antemortem [18F]flortaucipir PET images for predicting the presence of AD-type tau pathology at autopsy.Design, setting, and participantsThis diagnostic study (A16 primary cohort) was conducted from October 2015 to June 2018 at 28 study sites (27 in US sites and 1 in Australia). Individuals with a terminal illness who were older than 50 years and had a projected life expectancy of less than 6 months were enrolled. All participants underwent [18F]flortaucipir PET imaging, and scans were interpreted by 5 independent nuclear medicine physicians or radiologists. Supplemental autopsy [18F]flortaucipir images and pathological samples were also collected from 16 historically collected cases. A second study (FR01 validation study) was conducted from March 26 to April 26, 2019, in which 5 new readers assessed the original PET images for comparison to autopsy.Main outcomes and measures[18F]flortaucipir PET images were visually assessed and compared with immunohistochemical tau pathology. An AD tau pattern of flortaucipir retention was assessed for correspondence with a postmortem B3-level (Braak stage V or VI) pathological pattern of tau accumulation and to the presence of amyloid-β plaques sufficient to meet the criteria for high levels of AD neuropathological change. Success was defined as having at least 3 of the 5 readers above the lower bounds of the 95% CI for both sensitivity and specificity of 50% or greater.ResultsA total of 156 patients were enrolled in the A16 study and underwent [18F]flortaucipir PET imaging. Of these, 73 died during the study, and valid autopsies were performed for 67 of these patients. Three autopsies were evaluated as test cases and removed from the primary cohort (n = 64). Of the 64 primary cohort patients, 34 (53%) were women and 62 (97%) were white; mean (SD) age was 82.5 (9.6) years; and 49 (77%) had dementia, 1 (2%) had mild cognitive impairment, and 14 (22%) had normal cognition. Prespecified success criteria were met for the A16 primary cohort. The flortaucipir PET scans predicted a B3 level of tau pathology, with sensitivity ranging from 92.3% (95% CI, 79.7%-97.3%) to 100.0% (95% CI, 91.0%-100.0%) and specificity ranging from 52.0% (95% CI, 33.5%-70.0%) to 92.0% (95% CI, 75.0%-97.8%). A high level of AD neuropathological change was predicted with sensitivity of 94.7% (95% CI, 82.7%-98.5%) to 100.0% (95% CI, 90.8%-100.0%) and specificity of 50.0% (95% CI, 32.1%-67.9%) to 92.3% (95% CI, 75.9%-97.9%). The FR01 validation study also met prespecified success criteria. Addition of the supplemental autopsy data set and 3 test cases, which comprised a total of 82 patients and autopsies for both the A16 and FR01 studies, resulted in improved specificity and comparable overall accuracy. Among the 156 enrolled participants, 14 (9%) experienced at least 1 treatment-emergent adverse event.Conclusions and relevanceThis study's findings suggest that PET imaging with [18F]flortaucipir could be used to identify the density and distribution of AD-type tau pathology and the presence of high levels of AD neuropathological change, supporting a neuropathological diagnosis of AD.

Project description:Automatic skull-stripping or brain extraction of magnetic resonance (MR) images is often a fundamental step in many neuroimage processing pipelines. The accuracy of subsequent image processing relies on the accuracy of the skull-stripping. Although many automated stripping methods have been proposed in the past, it is still an active area of research particularly in the context of brain pathology. Most stripping methods are validated on T1-w MR images of normal brains, especially because high resolution T1-w sequences are widely acquired and ground truth manual brain mask segmentations are publicly available for normal brains. However, different MR acquisition protocols can provide complementary information about the brain tissues, which can be exploited for better distinction between brain, cerebrospinal fluid, and unwanted tissues such as skull, dura, marrow, or fat. This is especially true in the presence of pathology, where hemorrhages or other types of lesions can have similar intensities as skull in a T1-w image. In this paper, we propose a sparse patch based Multi-cONtrast brain STRipping method (MONSTR),2 where non-local patch information from one or more atlases, which contain multiple MR sequences and reference delineations of brain masks, are combined to generate a target brain mask. We compared MONSTR with four state-of-the-art, publicly available methods: BEaST, SPECTRE, ROBEX, and OptiBET. We evaluated the performance of these methods on 6 datasets consisting of both healthy subjects and patients with various pathologies. Three datasets (ADNI, MRBrainS, NAMIC) are publicly available, consisting of 44 healthy volunteers and 10 patients with schizophrenia. Other three in-house datasets, comprising 87 subjects in total, consisted of patients with mild to severe traumatic brain injury, brain tumors, and various movement disorders. A combination of T1-w, T2-w were used to skull-strip these datasets. We show significant improvement in stripping over the competing methods on both healthy and pathological brains. We also show that our multi-contrast framework is robust and maintains accurate performance across different types of acquisitions and scanners, even when using normal brains as atlases to strip pathological brains, demonstrating that our algorithm is applicable even when reference segmentations of pathological brains are not available to be used as atlases.

Project description:Data quality is increasingly recognized as one of the most important confounding factors in brain imaging research. It is particularly important for studies of brain development, where age is systematically related to in-scanner motion and data quality. Prior work has demonstrated that in-scanner head motion biases estimates of structural neuroimaging measures. However, objective measures of data quality are not available for most structural brain images. Here we sought to identify quantitative measures of data quality for T1-weighted volumes, describe how these measures relate to cortical thickness, and delineate how this in turn may bias inference regarding associations with age in youth. Three highly-trained raters provided manual ratings of 1840 raw T1-weighted volumes. These images included a training set of 1065 images from Philadelphia Neurodevelopmental Cohort (PNC), a test set of 533 images from the PNC, as well as an external test set of 242 adults acquired on a different scanner. Manual ratings were compared to automated quality measures provided by the Preprocessed Connectomes Project's Quality Assurance Protocol (QAP), as well as FreeSurfer's Euler number, which summarizes the topological complexity of the reconstructed cortical surface. Results revealed that the Euler number was consistently correlated with manual ratings across samples. Furthermore, the Euler number could be used to identify images scored "unusable" by human raters with a high degree of accuracy (AUC: 0.98-0.99), and out-performed proxy measures from functional timeseries acquired in the same scanning session. The Euler number also was significantly related to cortical thickness in a regionally heterogeneous pattern that was consistent across datasets and replicated prior results. Finally, data quality both inflated and obscured associations with age during adolescence. Taken together, these results indicate that reliable measures of data quality can be automatically derived from T1-weighted volumes, and that failing to control for data quality can systematically bias the results of studies of brain maturation.

Project description:For a method to be widely adopted in medical research or clinical practice, it needs to be reproducible so that clinicians and regulators can have confidence in its use. Machine learning and deep learning have a particular set of challenges around reproducibility. Small differences in the settings or the data used for training a model can lead to large differences in the outcomes of experiments. In this work, three top-performing algorithms from the Camelyon grand challenges are reproduced using only information presented in the associated papers and the results are then compared to those reported. Seemingly minor details were found to be critical to performance and yet their importance is difficult to appreciate until the actual reproduction is attempted. We observed that authors generally describe the key technical aspects of their models well but fail to maintain the same reporting standards when it comes to data preprocessing which is essential to reproducibility. As an important contribution of the present study and its findings, we introduce a reproducibility checklist that tabulates information that needs to be reported in histopathology ML-based work in order to make it reproducible. Author summary For a method to be used a lot in medical research or clinical practice, it needs to be able to be reproduced so that people can trust it. Machine learning and deep learning have some challenges around this. For example, small changes in how a model is trained can lead to significant changes in the results of experiments. This makes it essential that researchers report how they do things in enough detail for the results of their experiments to be reproducible. In this work, we looked at three different algorithms used for digital pathology image analysis. We tried to reproduce them using only the information reported in their papers. We confirmed that even minor details could be essential. Authors often do not report all the details needed to reproduce their work. We also created a checklist of things that need to be reported to help other researchers make their work reproducible.

Dataset Information

Digital pathology and image analysis for robust high-throughput quantitative assessment of Alzheimer disease neuropathologic changes.

Publications

Digital pathology and image analysis for robust high-throughput quantitative assessment of Alzheimer disease neuropathologic changes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets