Tectonic infarct analysis: A computational tool for automated whole-brain infarct analysis from TTC-stained tissue

Briana A Santo; Shiau-Sing K Ciecierska; S Mostafa Mousavi Janbeh Sarayi; TaJania D Jenkins; Ammad A Baig; Andre Monteiro; Carmon Koenigsknecht; Donald Pionessa; Liza Gutierrez; Robert M King; Matthew Gounis; Adnan H Siddiqui; Vincent M Tutino

doi:10.1016/j.heliyon.2023.e14837

Tectonic infarct analysis: A computational tool for automated whole-brain infarct analysis from TTC-stained tissue

Heliyon. 2023 Mar 24;9(4):e14837. doi: 10.1016/j.heliyon.2023.e14837. eCollection 2023 Apr.

Authors

Briana A Santo^{1

2}, Shiau-Sing K Ciecierska¹, S Mostafa Mousavi Janbeh Sarayi¹, TaJania D Jenkins^{1

2}, Ammad A Baig^{1

3}, Andre Monteiro^{1

3}, Carmon Koenigsknecht^{1

3}, Donald Pionessa^{1

3}, Liza Gutierrez^{1

3}, Robert M King⁴, Matthew Gounis⁴, Adnan H Siddiqui^{1

3}, Vincent M Tutino^{1

2

3

5}

Affiliations

¹ Canon Stroke and Vascular Research Center, Buffalo, NY, USA.
² Department of Pathology and Anatomical Sciences, Buffalo, NY, USA.
³ Department of Neurosurgery, Buffalo, NY, USA.
⁴ Department of Radiology, University of Massachusetts Chan Medical School, USA.
⁵ Department of Biomedical Engineering, University at Buffalo, Buffalo, NY, USA.

Abstract

Background: Infarct volume measured from 2,3,5-triphenyltetrazolium chloride (TTC)-stained brain slices is critical to in vivo stroke models. In this study, we developed an interactive, tunable, software that automatically computes whole-brain infarct metrics from serial TTC-stained brain sections.

Methods: Three rat ischemic stroke cohorts were used in this study (Total n = 91 rats; Cohort 1 n = 21, Cohort 2 n = 40, Cohort 3 n = 30). For each, brains were serially-sliced, stained with TTC and scanned on both anterior and posterior sides. Ground truth annotation and infarct morphometric analysis (e.g., brain-V_brain, infarct-V_infarct, and non-infarct-V_non-infarct volumes) were completed by domain experts. We used Cohort 1 for brain and infarct segmentation model development (n = 3 training cases with 36 slices [18 anterior and posterior faces], n = 18 testing cases with 218 slices [109 anterior and posterior faces]), as well as infarct morphometrics automation. The infarct quantification pipeline and pre-trained model were packaged as a standalone software and applied to Cohort 2, an internal validation dataset. Finally, software and model trainability were tested as a use-case with Cohort 3, a dataset from a separate institute.

Results: Both high segmentation and statistically significant quantification performance (correlation between manual and software) were observed across all datasets. Segmentation performance: Cohort 1 brain accuracy = 0.95/f1-score = 0.90, infarct accuracy = 0.96/f1-score = 0.89; Cohort 2 brain accuracy = 0.97/f1-score = 0.90, infarct accuracy = 0.97/f1-score = 0.80; Cohort 3 brain accuracy = 0.96/f1-score = 0.92, infarct accuracy = 0.95/f1-score = 0.82. Infarct quantification (cohort average): V_brain (ρ = 0.87, p < 0.001), V_infarct (0.92, p < 0.001), V_non-infarct (0.80, p < 0.001), %infarct (0.87, p = 0.001), and infarct:non-infact ratio (ρ = 0.92, p < 0.001).

Conclusion: Tectonic Infarct Analysis software offers a robust and adaptable approach for rapid TTC-based stroke assessment.

Keywords: Acute ischemic stroke; Brain infarct; Digital pathology; Middle cerebral artery occlusion model; Software; TTC staining.