Varying pixel resolution significantly improves deep learning-based carotid plaque histology segmentation.

Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE

Original Publication: London : Nature Publishing Group, copyright 2011-

Deep Learning* ; Plaque, Atherosclerotic*/pathology ; Plaque, Atherosclerotic*/diagnostic imaging ; Carotid Arteries*/pathology ; Carotid Arteries*/diagnostic imaging; Humans ; Image Processing, Computer-Assisted/methods ; Carotid Artery Diseases/pathology ; Neural Networks, Computer ; Carotid Stenosis/pathology ; Carotid Stenosis/diagnostic imaging

Carotid plaques-the buildup of cholesterol, calcium, cellular debris, and fibrous tissues in carotid arteries-can rupture, release microemboli into the cerebral vasculature and cause strokes. The likelihood of a plaque rupturing is thought to be associated with its composition (i.e. lipid, calcium, hemorrhage and inflammatory cell content) and the mechanical properties of the plaque. Automating and digitizing histopathological images of these plaques into tissue specific (lipid and calcified) regions can help us compare histologic findings to in vivo imaging and thereby enable us to optimize medical treatments or interventions for patients based on the composition of plaques. Lack of public datasets and the hypocellular nature of plaques have made applying deep learning to this task difficult. To address this, we sampled 1944 regions of interests from 323 whole slide images and drastically varied their pixel resolution from [Formula: see text] to [Formula: see text] as we anticipated that varying the pixel resolution of histology images can provide neural networks more 'context' that pathologists also rely on. We were able to train Mask R-CNN using regions of interests with varied pixel resolution, with a [Formula: see text] increase in pixel accuracy versus training with patches. The model achieved F1 scores of [Formula: see text] for calcified regions, [Formula: see text] for lipid core with fibrinous material and cholesterol crystals, and [Formula: see text] for fibrous regions, as well as a pixel accuracy of [Formula: see text]. While the F1 score was not calculated for lumen, qualitative results illustrate the model's ability to predict lumen. Hemorrhage was excluded as a class since only one out of 34 carotid endarterectomy specimens had sufficient hemorrhage for annotation.
Competing Interests: Declarations. Competing Interest: Carol C. Mitchell: Elsevier, author textbook chapters, and W. L. Gore and Associates contracted research grants to University of Wisconsin-Madison, consulting Acoustic Range Estimates. Rest of the authors declare no competing interest.
(© 2024. The Author(s).)

J Cardiovasc Magn Reson. 2020 May 21;22(1):38. (PMID: 32434582)
Ultrasound Med Biol. 2020 Jun;46(6):1513-1532. (PMID: 32291105)
Magn Reson Imaging. 2003 Jun;21(5):465-74. (PMID: 12878255)
Circulation. 2006 May 16;113(19):2320-8. (PMID: 16651471)
Stroke. 2015 Aug;46(8):2124-8. (PMID: 26081843)
J Pathol Inform. 2022 Sep 27;13:100146. (PMID: 36268093)
Sci Rep. 2022 Sep 16;12(1):15600. (PMID: 36114214)
Ultrasound Med Biol. 2015 Mar;41(3):685-97. (PMID: 25619778)
Hematology Am Soc Hematol Educ Program. 2005;:436-41. (PMID: 16304416)
IEEE Trans Med Imaging. 2019 Apr;38(4):945-954. (PMID: 30334752)
PLoS One. 2017 Jun 1;12(6):e0177544. (PMID: 28570557)
AJNR Am J Neuroradiol. 2008 May;29(5):875-82. (PMID: 18272562)
Ultrasound Med Biol. 2017 Sep;43(9):1861-1867. (PMID: 28645797)
J Neuroimaging. 2016 Jul;26(4):406-13. (PMID: 26919134)
Clin Neuroradiol. 2021 Jun;31(2):295-306. (PMID: 33398451)
Stroke. 2005 Apr;36(4):741-5. (PMID: 15705933)
Circulation. 2004 Oct 12;110(15):2190-7. (PMID: 15466633)
Ultrasound Med Biol. 2017 Jan;43(1):129-137. (PMID: 27720278)

R01 HL147866 United States HL NHLBI NIH HHS; 1R01HL147866-01 United States NH NIH HHS

Date Created: 20250102 Date Completed: 20250102 Latest Revision: 20250105

20250105

PMC11696133

10.1038/s41598-024-83948-6

39747244