Integrating Color Deconvolution Thresholding and Weakly Supervised Learning for Automated Segmentation of Neurofibrillary Tangle and Neuropil Threads
(2023) Medical Imaging 2023: Digital and Computational Pathology In Progress in Biomedical Optics and Imaging - Proceedings of SPIE 12471.- Abstract
Abnormally phosphorylated tau proteins are known to be a major indicator of Alzheimer's Disease (AD) with strong association with memory loss and cognitive decline. Automated generation of pixel-wise accurate neurofibrillary tangles (NFTs) and neuropil threads (NTs) segmentation is a challenging task, due to lack of ground truth segmentation data of these abnormal tau pathology. This problem is most prominent in the case of segmenting NTs, where the small threadlike morphology makes pixel-wise labeling a laborious task and unrealistic for large-scale studies. Lack of ground truth data poses a significant limitation for many learning-based methods to generate accurate segmentations of NFTs and NTs. This work presents an automated... (More)
Abnormally phosphorylated tau proteins are known to be a major indicator of Alzheimer's Disease (AD) with strong association with memory loss and cognitive decline. Automated generation of pixel-wise accurate neurofibrillary tangles (NFTs) and neuropil threads (NTs) segmentation is a challenging task, due to lack of ground truth segmentation data of these abnormal tau pathology. This problem is most prominent in the case of segmenting NTs, where the small threadlike morphology makes pixel-wise labeling a laborious task and unrealistic for large-scale studies. Lack of ground truth data poses a significant limitation for many learning-based methods to generate accurate segmentations of NFTs and NTs. This work presents an automated pipeline for pixel level segmentation of NFTs and NTs that does not rely on ground truth segmentation data. The pipeline is composed of four main steps: (1) color deconvolution is used to separate histopathology images into staining channels (DAB, Hematoxylin, and Eosin), (2) Otsu's thresholding is used on the DAB stain channel to generate pixel level segmentation of abnormal tau proteins staining, (3) a weakly-supervised learning paradigm (WildCat), using only global descriptors of images, is used to generate density maps of potential regions of NFTs and NTs, and (4) density maps and segmentations are then integrated using connected component analysis to localize NFTs and NTs in the detected tau segmentations. Our results show high global classification accuracy for NFTs (Acc:0.96) and NTs (Acc:0.91), and statistically significant distinctions when evaluating the percent area occupied of the detected NTs relative to expert ratings of NTs severity. Qualitative assessment of the NFTs and NTs results showed accurate pixel-level segmentations of the NFTs, while modest performance for NTs.
(Less)
- author
- organization
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Color Deconvolution, Histopathology Images, Neurofibrillary Tangles, Neuropil Threads, Otsu's Thresholding, Segmentation, Weakly Supervised Learning
- host publication
- Medical Imaging 2023 : Digital and Computational Pathology - Digital and Computational Pathology
- series title
- Progress in Biomedical Optics and Imaging - Proceedings of SPIE
- editor
- Tomaszewski, John E. and Ward, Aaron D.
- volume
- 12471
- article number
- 1247103
- publisher
- SPIE
- conference name
- Medical Imaging 2023: Digital and Computational Pathology
- conference location
- San Diego, United States
- conference dates
- 2023-02-19 - 2023-02-23
- external identifiers
-
- scopus:85160539535
- ISSN
- 1605-7422
- ISBN
- 9781510660472
- DOI
- 10.1117/12.2651848
- language
- English
- LU publication?
- yes
- id
- e62a7f83-84d9-49f3-8e07-5260603905d6
- date added to LUP
- 2023-08-24 14:28:23
- date last changed
- 2024-02-19 23:32:17
@inproceedings{e62a7f83-84d9-49f3-8e07-5260603905d6, abstract = {{<p>Abnormally phosphorylated tau proteins are known to be a major indicator of Alzheimer's Disease (AD) with strong association with memory loss and cognitive decline. Automated generation of pixel-wise accurate neurofibrillary tangles (NFTs) and neuropil threads (NTs) segmentation is a challenging task, due to lack of ground truth segmentation data of these abnormal tau pathology. This problem is most prominent in the case of segmenting NTs, where the small threadlike morphology makes pixel-wise labeling a laborious task and unrealistic for large-scale studies. Lack of ground truth data poses a significant limitation for many learning-based methods to generate accurate segmentations of NFTs and NTs. This work presents an automated pipeline for pixel level segmentation of NFTs and NTs that does not rely on ground truth segmentation data. The pipeline is composed of four main steps: (1) color deconvolution is used to separate histopathology images into staining channels (DAB, Hematoxylin, and Eosin), (2) Otsu's thresholding is used on the DAB stain channel to generate pixel level segmentation of abnormal tau proteins staining, (3) a weakly-supervised learning paradigm (WildCat), using only global descriptors of images, is used to generate density maps of potential regions of NFTs and NTs, and (4) density maps and segmentations are then integrated using connected component analysis to localize NFTs and NTs in the detected tau segmentations. Our results show high global classification accuracy for NFTs (Acc:0.96) and NTs (Acc:0.91), and statistically significant distinctions when evaluating the percent area occupied of the detected NTs relative to expert ratings of NTs severity. Qualitative assessment of the NFTs and NTs results showed accurate pixel-level segmentations of the NFTs, while modest performance for NTs.</p>}}, author = {{Roh, Hyung S. and Irwin, David J. and López, Mónica Muñoz and de Onzoño Martin, Maria Mercedes Iñiguez and Ittyerah, Ranjit and Lim, Sydney and Bedard, Madigan L. and Robinson, John L. and Schuck, Theresa and Artacho-Pérula, Emilio and del Mar Arroyo Jiménez, María and Rabal, María Pilar Marcos and Romero, Francisco Javier Molina and Sánchez, Sandra Cebada and González, José Carlos Delgado and de la Rosa-Prieto, Carlos and Parada, Marta Córcoles and Lee, Edward B. and Ohm, Daniel T. and Wisse, Laura E.M. and Wolk, David A. and Gee, James C. and Insausti, Ricardo and Yushkevich, Paul A. and Chen, Min}}, booktitle = {{Medical Imaging 2023 : Digital and Computational Pathology}}, editor = {{Tomaszewski, John E. and Ward, Aaron D.}}, isbn = {{9781510660472}}, issn = {{1605-7422}}, keywords = {{Color Deconvolution; Histopathology Images; Neurofibrillary Tangles; Neuropil Threads; Otsu's Thresholding; Segmentation; Weakly Supervised Learning}}, language = {{eng}}, publisher = {{SPIE}}, series = {{Progress in Biomedical Optics and Imaging - Proceedings of SPIE}}, title = {{Integrating Color Deconvolution Thresholding and Weakly Supervised Learning for Automated Segmentation of Neurofibrillary Tangle and Neuropil Threads}}, url = {{http://dx.doi.org/10.1117/12.2651848}}, doi = {{10.1117/12.2651848}}, volume = {{12471}}, year = {{2023}}, }