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

Author(s):  
Andy Y. Wang ◽  
Vaishnavi Sharma ◽  
Harleen Saini ◽  
Joseph N. Tingen ◽  
Alexandra Flores ◽  
...  

ABSTRACTBackgroundWild-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.MethodsImages 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.ResultsWe 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).ConclusionTWS 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.

2022 ◽  
Vol 13 ◽  
pp. 12
Author(s):  
Amandeep Godara ◽  
Andy Y. Wang ◽  
Knarik Arkun ◽  
Teresa Fogaren ◽  
Adnan S. Qamar ◽  
...  

Background: Amyloidosis is a protein misfolding disorder that leads to the deposition of beta-pleated sheets of a fibrillar derivative of various protein precursors. Identification of the type of precursor protein is integral in treatment decision-making. The presence of two different types of amyloid in the same patient is unusually rare, and there are no previous reports of two different types of amyloid deposition in the ligamentum flavum (LF) in the same patient. Case Description: Here, we describe two patients with spinal stenosis who underwent laminectomies and were found to have AL and ATTR amyloid deposits in the LF. Conclusion: As the spine is becoming recognized as a site for ATTRwt amyloid deposition, patients undergoing spinal decompression surgery may potentially benefit from evaluation for amyloidosis in the LF.


2020 ◽  
Author(s):  
Deng Bo ◽  
Fan Shao Hua ◽  
Feng Xin Bing ◽  
Zhenghua Hong

Abstract Background: To analyze the relational factors influencing the formation of cauda equina redundant nerve roots (RNRs) of the lumbar spinal stenosis.Methods: A retrospective study of 116 patients with lumbar spinal stenosis were treated in our department from January 2016 to June 2019. Magnetic resonance imaging (MRI) was performed to observe the shape and morphology of the redundant nerve roots of the cauda equina.We divided patient into (RNRs) group and non-RNRs( NRNRs) group based on the presence or absence of RNRs on sagittal T2-weighted MR. We analyzed the demographic characteristics, preoperative back pain visual analogue scale (VAS) scores ,preoperative leg pain VAS scores, and preoperative Oswestry disability index(ODI) scores, and also analyzed the rate of spondylolisthesis and ligamentum flavum hypertrophy. Simultaneously,the inter-vertebral height, intervertebral foramen height, inter-vertebral height +vertebral height, median sagittal diameter at the inter-vertebral space level(DIW-MSD),median sagittal diameter at the pedicel level(DV-MSD),ROM of the stenotic segment, were statistically analyzed for clinical and radiological significance.Results : Of a total 116 total patients,there were no statistically significant differences in either gender [RNRs group (n = 42, 18/24 female) and NRNR group (n = 74, 38/36 female)], age, BMI index, preoperative back pain VAS score , preoperative leg pain VAS score and preoperative ODI score(p> 0.05);however, there were statistically significant differences regard to the duration of symptoms and the rate of spondylolisthesis and ligamentum flavum hypertrophy (p<0.05);the inter-vertebral height,Intervertebral foramen height, inter-vertebral height+vertebral height, DIW-MSD ,ROM of the stenotic segment were also significantly different between the group (p<0.05).Conclusions:The inter-vertebral height, inter-vertebral foramen height, inter-vertebral height + vertebral height, DIW-MSD and ROM of the stenotic segment were the crucial factors related to RNRs in lumbar spinal stenosis.


1995 ◽  
Vol 30 (6) ◽  
pp. 1551
Author(s):  
Dae Moo Shim ◽  
Sang Soo Kim ◽  
In Yong Choi ◽  
Jae Yong Song ◽  
Hyung Bae Moon

2017 ◽  
Vol 11 (1) ◽  
pp. 71-74 ◽  
Author(s):  
Idiris Altun ◽  
Kasım Zafer Yüksel

<sec><title>Study Design</title><p>Histopathological analyses were performed in ligamentum flavum (LF) hypertrophy patients with lumbar spinal stenosis (LSS) and lumbar disc herniation (LDH).</p></sec><sec><title>Purpose</title><p>The aim of the present study was to evaluate histopathological changes in LF patients with LSS and LDH.</p></sec><sec><title>Overview of Literature</title><p>LSS is the most common spinal disorder in elderly patients. This condition causes lower back and leg pain and paresis, and occurs as a result of degenerative changes in the lumbar spine, including bulging of the intervertebral discs, bony proliferation of the facet joints, and LF thickening; among these, LF thickening is considered a major contributor to the development of LSS.</p></sec><sec><title>Methods</title><p>A total of 71 patients operated with the surgical indications of LSS and LDH were included. LF samples were obtained from 31 patients who underwent decompressive laminectomy for symptomatic degenerative LSS (stenotic group) and from 40 patients who underwent lumbar discectomy for LDH (discectomy group). LF materials were examined histopathologically, and other specimens were examined for collagen content, elastic fiber number and array, and presence of calcification.</p></sec><sec><title>Results</title><p>The stenotic and discectomy groups did not differ with regard to mean collagen concentration or mean elastic fiber number (p=0.430 and p=0.457, respectively). Mean elastic fiber alignment was 2.36±0.99 in the stenotic group and 1.38±0.54 in the discectomy group (<italic>p</italic>&lt;0.001). Mean calcification was 0.39±0.50 in the stenotic group, whereas calcification was not detected (0.00±0.00) in the discectomy group; a statistically significant difference was detected (<italic>p</italic>&lt;0.001) between groups.</p></sec><sec><title>Conclusions</title><p>LF hypertrophy in spinal stenosis may occur as a result of elastic fiber misalignment along with the development of calcification over time. Further studies determining the pathogenesis of LSS are needed.</p></sec>


PROTEOMICS ◽  
2015 ◽  
Vol 15 (9) ◽  
pp. 1622-1630 ◽  
Author(s):  
Masahiro Kamita ◽  
Taiki Mori ◽  
Yoshihito Sakai ◽  
Sadayuki Ito ◽  
Masahiro Gomi ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document