Journal
ACTA NEUROPATHOLOGICA COMMUNICATIONS
Volume 10, Issue 1, Pages -Publisher
BMC
DOI: 10.1186/s40478-022-01365-0
Keywords
Amyloid beta; Histopathology; Deep learning; Consensus; Expert annotators; Algorithms
Categories
Funding
- National Institute On Aging of the National Institutes of Health [P30 AG010129, P30 AG072972, AG 062517, P30 AG013854, K08 AG065463, P30 AG066468, P50 AG005133, P30 AG012300]
- McCune Foundation
- Winspear Family Center for Research on the Neuropathology of Alzheimer Disease
- University of California Office of the President [MRI-19-599956]
- Zuckerberg Initiative DAF, an advised fund of the Silicon Valley Community Foundation [2018-191905]
- California Department of Public Health Alzheimer's Disease Program [19-10611]
- 2019 California Budget Act
Ask authors/readers for more resources
This study presents a deep learning approach that incorporates the expertise of multiple pathologists to address the challenge of inconsistent labeling of pathologies. The results show significant improvements in pathology diagnosis using the consensus of two strategy in training deep learning models. In blind tests, the models labeled pathologies consistently with human experts.
Pathologists can label pathologies differently, making it challenging to yield consistent assessments in the absence of one ground truth. To address this problem, we present a deep learning (DL) approach that draws on a cohort of experts, weighs each contribution, and is robust to noisy labels. We collected 100,495 annotations on 20,099 candidate amyloid beta neuropathologies (cerebral amyloid angiopathy (CAA), and cored and diffuse plaques) from three institutions, independently annotated by five experts. DL methods trained on a consensus-of-two strategy yielded 12.6-26% improvements by area under the precision recall curve (AUPRC) when compared to those that learned individualized annotations. This strategy surpassed individual-expert models, even when unfairly assessed on benchmarks favoring them. Moreover, ensembling over individual models was robust to hidden random annotators. In blind prospective tests of 52,555 subsequent expert-annotated images, the models labeled pathologies like their human counterparts (consensus model AUPRC = 0.74 cored; 0.69 CAA). This study demonstrates a means to combine multiple ground truths into a common-ground DL model that yields consistent diagnoses informed by multiple and potentially variable expert opinions.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available