Machine learning quantification of amyloid deposits in histological images of ligamentum flavum

Abstract

Background: Wild-type transthyretin amyloidosis (ATTRwt) is an underdiagnosed and potentially fatal disease. Interestingly, ATTRwt deposits have been found to deposit in the ligamentum flavum (LF) of patients with lumbar spinal stenosis prior to the development of systemic and cardiac amyloidosis. In order to study this phenomenon and its possible relationship with LF thickening and systemic amyloidosis, a precise method of quantifying amyloid deposits in histological slides of LF is critical. However, such a method is currently unavailable. Here, we present a machine learning quantification method with Trainable Weka Segmentation (TWS) to assess amyloid deposition in histological slides of LF. Methods: Images of ligamentum flavum specimens stained with Congo red are obtained from spinal stenosis patients undergoing laminectomies and confirmed to be positive for ATTRwt. Amyloid deposits in these specimens are classified and quantified by TWS through training the algorithm via user-directed annotations on images of LF. TWS can also be automated through exposure to a set of training images with user-directed annotations, and then application to a set of new images without additional annotations. Additional methods of color thresholding and manual segmentation are also used on these images for comparison to TWS. Results: We develop the use of TWS in images of LF and demonstrate its potential for automated quantification. TWS is strongly correlated with manual segmentation in the training set of images with user-directed annotations (R = 0.98; p = 0.0033) as well as in the application set of images where TWS was automated (R = 0.94; p = 0.016). Color thresholding was weakly correlated with manual segmentation in the training set of images (R = 0.78; p = 0.12) and in the application set of images (R = 0.65; p = 0.23). Conclusion: TWS machine learning closely correlates with the gold standard comparator of manual segmentation and outperforms the color thresholding method. This novel machine learning method to quantify amyloid deposition in histological slides of ligamentum flavum is a precise, objective, accessible, high throughput, and powerful tool that will hopefully pave the way towards future research and clinical applications.

The relationship between wild-type transthyretin amyloid load and ligamentum flavum thickness in lumbar stenosis patients

“…Other publications assessing amyloid load through computational methods have used the color thresholding function in ImageJ, which we have previously shown to be suboptimal. 11 Our method utilizes powerful and 12 precise machine learning quantification to measure amyloid load, which outperforms color thresholding. While the results shown in this paper are statistically significant, our p-values were not as low as those in the study by Yanagisawa et al However, these p-values cannot be compared to each other as these are completely different studies.…”

The Relationship Between Wild-Type Transthyretin Amyloid Load and Ligamentum Flavum Thickness in Lumbar Stenosis Patients

“…Other publications assessing amyloid load through computational methods have used the color thresholding function in ImageJ, which we have previously shown to be suboptimal. 11 Our method utilizes powerful and All rights reserved. No reuse allowed without permission.…”

“…Amyloid deposits were quantified through the Trainable Weka Segmentation (TWS) plugin through Fiji/ImageJ as previously described. 11 This machine learning segmentation method utilized small sets of human-directed annotations to learn and recognize characteristics of amyloid deposits. Classes of interest were selected to include amyloid, glass slide, calcifications, and tissue (Figure 1A).…”

“…We have previously described this method as superior to existing methods that are subjective and non-reproducible. 11 Through exploring the relationship between amyloid load and LF thickness, we hope to elucidate the role that ATTRwt deposition in LF has in LF thickening and lumbar stenosis.…”