Sina Salsabili1, Marissa Lithopoulos2,3, Shreyas Sreeraman4, Arul Vadivel2, Bernard Thébaud2,3,5, Adrian D C Chan1,6,7, Eranga Ukwatta1,8. 1. Carleton University, Department of Systems and Computer Engineering, Ottawa, Ontario, Canada. 2. Ottawa Hospital Research Institute, Sinclair Centre for Regenerative Medicine, Ottawa, Ontario, Canada. 3. University of Ottawa, Department of Cellular and Molecular Medicine, Ottawa, Ontario, Canada. 4. McMaster University, Michael G. DeGroote School of Medicine, Hamilton, Ontario, Canada. 5. Children's Hospital of Eastern Ontario Research Institute, Ottawa, Ontario, Canada. 6. University of Ottawa, School of Human Kinetics, Ottawa, Canada. 7. Bruyère Research Institute, Ottawa, Ontario, Canada. 8. University of Guelph, School of Engineering, Guelph, Ontario, Canada.
Abstract
Purpose: The mean linear intercept (MLI) score is a common metric for quantification of injury in lung histopathology images. The automated estimation of the MLI score is a challenging task because it requires accurate segmentation of different biological components of the lung tissue. Therefore, the most widely used approaches for MLI quantification are based on manual/semi-automated assessment of lung histopathology images, which can be expensive and time-consuming. We describe a fully automated pipeline for MLI estimation, which is capable of producing results comparable to human raters. Approach: We use a convolutional neural network based on U-Net architecture to segment the diagnostically relevant tissue segments in the whole slide images (WSI) of the mouse lung tissue. The proposed method extracts multiple field-of-view (FOV) images from the tissue segments and screen the FOV images, rejecting images based on presence of certain biological structures (i.e., blood vessels and bronchi). We used color slicing and region growing for segmentation of different biological structures in each FOV image. Results: The proposed method was tested on ten WSIs from mice and compared against the scores provided by three human raters. In segmenting the relevant tissue segments, our method obtained a mean accuracy, Dice coefficient, and Hausdorff distance of 98.34%, 98.22%, and 109.68 μ m , respectively. Our proposed method yields a mean precision, recall, and F 1 -score of 93.37%, 83.47%, and 87.87%, respectively, in screening of FOV images. There was substantial agreement found between the proposed method and the manual scores (Fleiss Kappa score of 0.76). The mean difference between the calculated MLI score between the automated method and average rater's score was 2.33 ± 4.13 ( 4.25 % ± 5.67 % ). Conclusion: The proposed pipeline for automated calculation of the MLI score demonstrates high consistency and accuracy with human raters and can be a potential replacement for manual/semi-automated approaches in the field.
Purpose: The mean linear intercept (MLI) score is a common metric for quantification of injury in lung histopathology images. The automated estimation of the MLI score is a challenging task because it requires accurate segmentation of different biological components of the lung tissue. Therefore, the most widely used approaches for MLI quantification are based on manual/semi-automated assessment of lung histopathology images, which can be expensive and time-consuming. We describe a fully automated pipeline for MLI estimation, which is capable of producing results comparable to human raters. Approach: We use a convolutional neural network based on U-Net architecture to segment the diagnostically relevant tissue segments in the whole slide images (WSI) of the mouse lung tissue. The proposed method extracts multiple field-of-view (FOV) images from the tissue segments and screen the FOV images, rejecting images based on presence of certain biological structures (i.e., blood vessels and bronchi). We used color slicing and region growing for segmentation of different biological structures in each FOV image. Results: The proposed method was tested on ten WSIs from mice and compared against the scores provided by three human raters. In segmenting the relevant tissue segments, our method obtained a mean accuracy, Dice coefficient, and Hausdorff distance of 98.34%, 98.22%, and 109.68 μ m , respectively. Our proposed method yields a mean precision, recall, and F 1 -score of 93.37%, 83.47%, and 87.87%, respectively, in screening of FOV images. There was substantial agreement found between the proposed method and the manual scores (Fleiss Kappa score of 0.76). The mean difference between the calculated MLI score between the automated method and average rater's score was 2.33 ± 4.13 ( 4.25 % ± 5.67 % ). Conclusion: The proposed pipeline for automated calculation of the MLI score demonstrates high consistency and accuracy with human raters and can be a potential replacement for manual/semi-automated approaches in the field.
Authors: Sarah H Poggi; Carolyn Salafia; Sara Paiva; Nia J Leak; John C Pezzullo; Alessandro Ghidini Journal: Am J Perinatol Date: 2008-11-21 Impact factor: 1.862
Authors: John S Meyer; Consuelo Alvarez; Clara Milikowski; Neal Olson; Irma Russo; Jose Russo; Andrew Glass; Barbara A Zehnbauer; Karen Lister; Reza Parwaresch Journal: Mod Pathol Date: 2005-08 Impact factor: 7.842
Authors: Anthony E Rizzardi; Arthur T Johnson; Rachel Isaksson Vogel; Stefan E Pambuccian; Jonathan Henriksen; Amy Pn Skubitz; Gregory J Metzger; Stephen C Schmechel Journal: Diagn Pathol Date: 2012-06-20 Impact factor: 2.644
Authors: Alena Arlova; Chengcheng Jin; Abigail Wong-Rolle; Eric S Chen; Curtis Lisle; G Thomas Brown; Nathan Lay; Peter L Choyke; Baris Turkbey; Stephanie Harmon; Chen Zhao Journal: J Pathol Inform Date: 2022-01-20