scholarly journals Automatic and unbiased segmentation and quantification of myofibers in skeletal muscle

2021 ◽  
Author(s):  
Ariel Waisman ◽  
Alessandra Norris ◽  
Martín Elías Costa ◽  
Daniel Kopinke
Keyword(s):  
Skeletal Muscle ◽  
Primary Cilia ◽  
Learning Algorithm ◽  
Fixed Tissue ◽  
Deep Learning Algorithm ◽  
Ability To Regenerate ◽  
Murine Skeletal Muscle ◽  
And Function ◽  
Injury Models ◽  
Imagej Plugin

ABSTRACTSkeletal muscle has the remarkable ability to regenerate. However, with age and disease muscle strength and function decline. Myofiber size, which is affected by injury and disease, is a critical measurement to assess muscle health. Here, we test and apply Cellpose, a recently developed deep learning algorithm, to automatically segment myofibers within murine skeletal muscle. We first show that tissue fixation is necessary to preserve cellular structures such as primary cilia, small cellular antennae, and adipocyte lipid droplets. However, fixation generates heterogeneous myofiber labeling, which impedes intensity-based segmentation. We demonstrate that Cellpose efficiently delineates thousands of individual myofibers outlined by a variety of markers, even within fixed tissue with highly uneven myofiber staining. We created a novel ImageJ plugin (LabelsToRois) that allows processing multiple Cellpose segmentation images in batch. The plugin also contains a semi-automatic erosion function to correct for the area bias introduced by the different stainings, identifying myofibers as accurately as human experts. We successfully applied our segmentation pipeline to uncover myofiber size differences between two different muscle injury models, cardiotoxin and glycerol. Thus, Cellpose combined with LabelsToRois allows for fast, unbiased, and reproducible myofiber quantification for a variety of staining and fixation conditions.

scholarly journals Automatic and unbiased segmentation and quantification of myofibers in skeletal muscle

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ariel Waisman ◽  
Alessandra Marie Norris ◽  
Martín Elías Costa ◽  
Daniel Kopinke
Keyword(s):  
Skeletal Muscle ◽  
Primary Cilia ◽  
Learning Algorithm ◽  
Fixed Tissue ◽  
Deep Learning Algorithm ◽  
Ability To Regenerate ◽  
Murine Skeletal Muscle ◽  
And Function ◽  
Injury Models ◽  
Imagej Plugin

AbstractSkeletal muscle has the remarkable ability to regenerate. However, with age and disease muscle strength and function decline. Myofiber size, which is affected by injury and disease, is a critical measurement to assess muscle health. Here, we test and apply Cellpose, a recently developed deep learning algorithm, to automatically segment myofibers within murine skeletal muscle. We first show that tissue fixation is necessary to preserve cellular structures such as primary cilia, small cellular antennae, and adipocyte lipid droplets. However, fixation generates heterogeneous myofiber labeling, which impedes intensity-based segmentation. We demonstrate that Cellpose efficiently delineates thousands of individual myofibers outlined by a variety of markers, even within fixed tissue with highly uneven myofiber staining. We created a novel ImageJ plugin (LabelsToRois) that allows processing of multiple Cellpose segmentation images in batch. The plugin also contains a semi-automatic erosion function to correct for the area bias introduced by the different stainings, thereby identifying myofibers as accurately as human experts. We successfully applied our segmentation pipeline to uncover myofiber regeneration differences between two different muscle injury models, cardiotoxin and glycerol. Thus, Cellpose combined with LabelsToRois allows for fast, unbiased, and reproducible myofiber quantification for a variety of staining and fixation conditions.

scholarly journals Accelerated brain aging and cerebral blood flow reduction in persons with HIV

2021 ◽  
Author(s):  
Kalen J Petersen ◽  
Nicholas Metcalf ◽  
Sarah Cooley ◽  
Dimitre Tomov ◽  
Florin Vaida ◽  
...  
Keyword(s):  
Blood Flow ◽  
Cerebral Blood Flow ◽  
Brain Aging ◽  
Learning Algorithm ◽  
Psychomotor Speed ◽  
Deep Learning Algorithm ◽  
Blood Flow Reduction ◽  
Brain Structure And Function ◽  
N 93 ◽  
And Function

Abstract Background Persons with HIV (PWH) are characterized by altered brain structure and function. As they attain normal lifespans, it has become crucial to understand potential interactions between HIV and aging. However, it remains unclear how brain aging varies with viral load (VL). Methods In this study, we compare MRI biomarkers amongst PWH with undetectable VL (UVL; ≤50 genomic copies/ml; n=230), PWH with detectable VL (DVL; >50 copies/ml; n=93), and HIV uninfected (HIV-) controls (n=206). To quantify gray matter cerebral blood flow (CBF), we utilized arterial spin labeling. To measure structural aging, we used a publicly available deep learning algorithm to estimate brain age from T1-weighted MRI. Cognitive performance was measured using a neuropsychological battery covering five domains. Results Associations between age and CBF varied with VL. Older PWH with DVL had reduced CBF vs. PWH with UVL (p=0.02). Structurally predicted brain aging was accelerated in PWH vs. HIV- controls regardless of VL (p<0.001). Overall, PWH had impaired learning, executive function, psychomotor speed, and language compared to HIV- controls. Structural brain aging was associated with reduced psychomotor speed (p<0.001). Conclusions Brain aging in HIV is multifaceted. CBF depends on age and current VL, and is improved by medication adherence. By contrast, structural aging is an indicator of cognitive function and reflects serostatus rather than current VL.

scholarly journals Myosin Heavy Chains IIa and IId Are Functionally Distinct in the Mouse

1998 ◽  
Vol 141 (4) ◽  
pp. 943-953 ◽  
Author(s):  
Carol A. Sartorius ◽  
Brian D. Lu ◽  
Leslie Acakpo-Satchivi ◽  
Renee P. Jacobsen ◽  
William C. Byrnes ◽  
...  
Keyword(s):  
Skeletal Muscle ◽  
Amino Acid Level ◽  
Spinal Curvature ◽  
Developmental Expression ◽  
Cross Sectional ◽  
Fast Myosin ◽  
Fast Myosin Heavy Chain ◽  
Fiber Number ◽  
Murine Skeletal Muscle ◽  
And Function

Myosin in adult murine skeletal muscle is composed primarily of three adult fast myosin heavy chain (MyHC) isoforms. These isoforms, MyHC-IIa, -IId, and -IIb, are >93% identical at the amino acid level and are broadly expressed in numerous muscles, and their genes are tightly linked. Mice with a null mutation in the MyHC-IId gene have phenotypes that include growth inhibition, muscle weakness, histological abnormalities, kyphosis (spinal curvature), and aberrant kinetics of muscle contraction and relaxation. Despite the lack of MyHC-IId, IId null mice have normal amounts of myosin in their muscles because of compensation by the MyHC-IIa gene. In each muscle examined from IId null mice, there was an increase in MyHC-IIa– containing fibers. MyHC-IIb content was unaffected in all muscles except the masseter, where its expression was extinguished in the IId null mice. Cross-sectional fiber areas, total muscle cross-sectional area, and total fiber number were affected in ways particular to each muscle. Developmental expression of adult MyHC genes remained unchanged in IId null mice. Despite this universal compensation of MyHC-IIa expression, IId null mice have severe phenotypes. We conclude that despite the similarity in sequence, MyHC-IIa and -IId have unique roles in the development and function of skeletal muscle.

scholarly journals Intramuscular VEGF activates an SDF1-dependent progenitor cell cascade and an SDF1-independent muscle paracrine cascade for cardiac repair

2011 ◽  
Vol 301 (6) ◽  
pp. H2422-H2432 ◽  
Author(s):  
David Zisa ◽  
Arsalan Shabbir ◽  
Michalis Mastri ◽  
Tyler Taylor ◽  
Ilija Aleksic ◽  
...  
Keyword(s):  
Skeletal Muscle ◽  
Progenitor Cells ◽  
Progenitor Cell ◽  
Cardiac Repair ◽  
Trophic Factors ◽  
Therapeutic Modality ◽  
Ability To Regenerate ◽  
Organ Repair ◽  
Hamster Heart ◽  
And Function

The skeletal muscle is endowed with an impressive ability to regenerate after injury, and this ability is coupled to paracrine production of many trophic factors possessing cardiovascular benefits. Taking advantage of this humoral capacity of the muscle, we recently demonstrated an extracardiac therapeutic regimen based on intramuscular delivery of VEGF-A165 for repair of the failing hamster heart. This distal organ repair mechanism activates production from the injected hamstring of many trophic factors, among which stromal-derived factor-1 (SDF1) prominently mobilized multi-lineage progenitor cells expressing CXCR4 and their recruitment to the heart. The mobilized bone marrow progenitor cells express the cardiac transcription factors myocyte enhancer factor 2c and GATA4 and several major trophic factors, most notably IGF1 and VEGF. SDF1 blockade abrogated myocardial recruitment of CXCR4+ and c-kit+ progenitor cells with an insignificant effect on the hematopoietic progenitor lineage. The knockdown of cardiac progenitor cells led to deprivation of myocardial trophic factors, resulting in compromised cardiomyogenesis and angiogenesis. However, the VEGF-injected hamstring continued to synthesize cardioprotective factors, contributing to moderate myocardial tissue viability and function even in the presence of SDF1 blockade. These findings thus uncover two distinct but synergistic cardiac therapeutic mechanisms activated by intramuscular VEGF. Whereas the SDF1/CXCR4 axis activates the progenitor cell cascade and its trophic support of cardiomyogenesis intramuscularly, VEGF amplifies the skeletal muscle paracrine cascade capable of directly promoting myocardial survival independent of SDF1. Given that recent clinical trials of cardiac repair based on the use of marrow-mobilizing agents have been disappointing, the proposed dual therapeutic modality warrants further investigation.

PVsiRNAPred: Prediction of plant exclusive virus-derived small interfering RNAs by deep convolutional neural network

2019 ◽  
Vol 17 (06) ◽  
pp. 1950039
Author(s):  
Bifang He ◽  
Jian Huang ◽  
Heng Chen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Learning Algorithm ◽  
Permutation Test ◽  
Deep Convolutional Neural Network ◽  
Small Interfering Rnas ◽  
Sequence Composition ◽  
Deep Learning Algorithm ◽  
Testing Dataset ◽  
And Function

Plant exclusive virus-derived small interfering RNAs (vsiRNAs) regulate various biological processes, especially important in antiviral immunity. The identification of plant vsiRNAs is important for understanding the biogenesis and function mechanisms of vsiRNAs and further developing anti-viral plants. In this study, we extracted plant vsiRNA sequences from the PVsiRNAdb database. We then utilized deep convolutional neural network (CNN) to develop a deep learning algorithm for predicting plant vsiRNAs based on vsiRNA sequence composition, known as PVsiRNAPred. The key part of PVsiRNAPred is the CNN module, which automatically learns hierarchical representations of vsiRNA sequences related to vsiRNA profiles in plants. When evaluated using an independent testing dataset, the accuracy of the model was 65.70%, which was higher than those of five conventional machine learning method-based classifiers. In addition, PVsiRNAPred obtained a sensitivity of 67.11%, specificity of 64.26% and Matthews correlation coefficient (MCC) of 0.31, and the area under the receiver operating characteristic (ROC) curve (AUC) of PVsiRNAPred was 0.71 in the independent test. The permutation test with 1000 shuffles resulted in a [Formula: see text] value [Formula: see text]. The above results reveal that PVsiRNAPred has favorable generalization capabilities. We hope PVsiRNAPred, the first bioinformatics algorithm for predicting plant vsiRNAs, will allow efficient discovery of new vsiRNAs.

scholarly journals A rapid, nondestructive method for vascular network visualization

BioTechniques ◽  
2020 ◽  
Vol 69 (6) ◽  
pp. 443-449
Author(s):  
Austin Veith ◽  
Aaron B Baker
Keyword(s):  
Blood Vessel ◽  
Learning Algorithm ◽  
Three Dimensional ◽  
Nondestructive Method ◽  
Vascular Network ◽  
Micro Computed Tomography ◽  
Nondestructive Technique ◽  
Fixed Tissue ◽  
Animal Models Of Disease ◽  
Deep Learning Algorithm

The quantitative analysis of blood vessel networks is an important component in many animal models of disease. We describe a nondestructive technique for blood vessel imaging that visualizes in situ vasculature in harvested tissues. The method allows for further analysis of the same tissues with histology and other methods that can be performed on fixed tissue. Consequently, it can easily be incorporated upstream to analysis methods to augment these with a three-dimensional reconstruction of the vascular network in the tissues to be analyzed. The method combines iodine-enhanced micro-computed tomography with a deep learning algorithm to segment vasculature within tissues. The procedure is relatively simple and can provide insight into complex changes in the vascular structure in the tissues.

Deep Learning Algorithm for Image Classification of Waveforms Obtained From Electrically Stimulated Hypoxic Skeletal Muscle Bundles

2020 ◽  
Author(s):  
Weston Upchurch ◽  
Alex Deakyne ◽  
David A. Ramirez ◽  
Paul A. Iaizzo
Keyword(s):  
Neural Network ◽  
Skeletal Muscle ◽  
Deep Learning ◽  
Emergency Treatment ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
Hypoxic Conditions ◽  
Deep Learning Algorithm ◽  
Compartmental Pressure

Abstract Acute compartment syndrome is a serious condition that requires urgent surgical treatment. While the current emergency treatment is straightforward — relieve intra-compartmental pressure via fasciotomy — the diagnosis is often a difficult one. A deep neural network is presented here that has been trained to detect whether isolated muscle bundles were exposed to hypoxic conditions and became ischemic.

scholarly journals Automated CT-derived skeletal muscle mass determination in lower hind limbs of mice using a 3D U-Net deep learning network

2020 ◽  
Vol 128 (1) ◽  
pp. 42-49 ◽  
Author(s):  
Brent van der Heyden ◽  
Wouter R. P. H. van de Worp ◽  
Ardy van Helvoort ◽  
Jan Theys ◽  
Annemie M. W. J. Schols ◽  
...  
Keyword(s):  
Skeletal Muscle ◽  
Deep Learning ◽  
Muscle Mass ◽  
Lower Limb ◽  
Skeletal Muscle Mass ◽  
Learning Algorithm ◽  
Limb Muscle ◽  
Mass Measurements ◽  
Deep Learning Algorithm ◽  
Muscle Complex

The loss of skeletal muscle mass is recognized as a complication of several chronic diseases and is associated with increased mortality and a decreased quality of life. Relevant and reliable animal models in which muscle wasting can be monitored noninvasively over time are instrumental to investigate and develop new therapies. In this work, we developed a fully automatic deep learning algorithm for segmentation of micro cone beam computed tomography images of the lower limb muscle complex in mice and subsequent muscle mass calculation. A deep learning algorithm was trained on manually segmented data from 32 mice. Muscle wet mass measurements were obtained from 47 mice and served as a data set for model validation and reverse model validation. The automatic algorithm performance was ~150 times faster than manual segmentation. Reverse validation of the algorithm showed high quantitative metrics (i.e., a Dice similarity coefficient of 0.93, a Hausdorff distance of 0.4 mm, and a center of mass displacement of 0.1 mm), substantiating the robustness and accuracy of the model. A high correlation ( R2 = 0.92) was obtained between the computed tomography-derived muscle mass measurements and the muscle wet masses. Longitudinal follow-up revealed time-dependent changes in muscle mass that separated control from lung tumor-bearing mice, which was confirmed as cachexia. In conclusion, this deep learning model for automated assessment of the lower limb muscle complex provides highly accurate noninvasive longitudinal evaluation of skeletal muscle mass. Furthermore, it facilitates the workflow and increases the amount of data derived from mouse studies while reducing the animal numbers. NEW & NOTEWORTHY This deep learning application enables highly accurate noninvasive longitudinal evaluation of skeletal muscle mass changes in mice with minimal requirement for operator involvement in the data analysis. It provides a unique opportunity to increase and analyze the amount of data derived from animal studies automatically while reducing animal numbers and analytical workload.

Sign in / Sign up

Export Citation Format

Share Document