1
|
Wang S, Song F, Qiao Q, Liu Y, Chen J, Ma J. A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes Vulnerability Data. Healthcare (Basel) 2022; 10:healthcare10061119. [PMID: 35742169 PMCID: PMC9223144 DOI: 10.3390/healthcare10061119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Revised: 06/08/2022] [Accepted: 06/13/2022] [Indexed: 11/16/2022] Open
Abstract
(1) Background: Poor adherence to management behaviors in Chinese Type 2 diabetes mellitus (T2DM) patients leads to an uncontrolled prognosis of diabetes, which results in significant economic costs for China. It is imperative to quickly locate vulnerability factors in the management behavior of patients with T2DM. (2) Methods: In this study, a thematic analysis of the collected interview materials was conducted to construct the themes of T2DM management vulnerability. We explored the applicability of the pre-trained models based on the evaluation metrics in text classification. (3) Results: We constructed 12 themes of vulnerability related to the health and well-being of people with T2DM in Tianjin. We considered that Bidirectional Encoder Representation from Transformers (BERT) performed better in this Natural Language Processing (NLP) task with a shorter completion time. With the splitting ratio of 6:3:1 and batch size of 64 for BERT, the test accuracy was 97.71%, the completion time was 10 min 24 s, and the macro-F1 score was 0.9752. (4) Conclusions: Our results proved the applicability of NLP techniques in this specific Chinese-language medical environment. We filled the knowledge gap in the application of NLP technologies in diabetes management. Our study provided strong support for using NLP techniques to rapidly locate vulnerability factors in T2DM management.
Collapse
|
2
|
Daeschler SC, Bourget MH, Derakhshan D, Sharma V, Asenov SI, Gordon T, Cohen-Adad J, Borschel GH. Rapid, automated nerve histomorphometry through open-source artificial intelligence. Sci Rep 2022; 12:5975. [PMID: 35396530 PMCID: PMC8993871 DOI: 10.1038/s41598-022-10066-6] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2021] [Accepted: 03/21/2022] [Indexed: 12/23/2022] Open
Abstract
We aimed to develop and validate a deep learning model for automated segmentation and histomorphometry of myelinated peripheral nerve fibers from light microscopic images. A convolutional neural network integrated in the AxonDeepSeg framework was trained for automated axon/myelin segmentation using a dataset of light-microscopic cross-sectional images of osmium tetroxide-stained rat nerves including various axonal regeneration stages. In a second dataset, accuracy of automated segmentation was determined against manual axon/myelin labels. Automated morphometry results, including axon diameter, myelin sheath thickness and g-ratio were compared against manual straight-line measurements and morphometrics extracted from manual labels with AxonDeepSeg as a reference standard. The neural network achieved high pixel-wise accuracy for nerve fiber segmentations with a mean (± standard deviation) ground truth overlap of 0.93 (± 0.03) for axons and 0.99 (± 0.01) for myelin sheaths, respectively. Nerve fibers were identified with a sensitivity of 0.99 and a precision of 0.97. For each nerve fiber, the myelin thickness, axon diameter, g-ratio, solidity, eccentricity, orientation, and individual x -and y-coordinates were determined automatically. Compared to manual morphometry, automated histomorphometry showed superior agreement with the reference standard while reducing the analysis time to below 2.5% of the time needed for manual morphometry. This open-source convolutional neural network provides rapid and accurate morphometry of entire peripheral nerve cross-sections. Given its easy applicability, it could contribute to significant time savings in biomedical research while extracting unprecedented amounts of objective morphologic information from large image datasets.
Collapse
Affiliation(s)
- Simeon Christian Daeschler
- SickKids Research Institute, Neuroscience and Mental Health Program, Hospital for Sick Children (SickKids), Toronto, ON, Canada.
| | - Marie-Hélène Bourget
- NeuroPoly Laboratory, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
| | | | - Vasudev Sharma
- NeuroPoly Laboratory, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada.,University of Toronto, Toronto, ON, Canada
| | - Stoyan Ivaylov Asenov
- NeuroPoly Laboratory, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
| | - Tessa Gordon
- SickKids Research Institute, Neuroscience and Mental Health Program, Hospital for Sick Children (SickKids), Toronto, ON, Canada.,Division of Plastic and Reconstructive Surgery, the Hospital for Sick Children, Toronto, ON, Canada
| | - Julien Cohen-Adad
- NeuroPoly Laboratory, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada.,Functional Neuroimaging Unit, CRIUGM, University of Montreal, Montreal, QC, Canada.,Mila - Quebec AI Institute, Montreal, QC, Canada
| | - Gregory Howard Borschel
- SickKids Research Institute, Neuroscience and Mental Health Program, Hospital for Sick Children (SickKids), Toronto, ON, Canada.,University of Toronto, Toronto, ON, Canada.,Division of Plastic and Reconstructive Surgery, the Hospital for Sick Children, Toronto, ON, Canada.,Indiana University School of Medicine, Indianapolis, IN, USA
| |
Collapse
|
3
|
Plebani E, Biscola NP, Havton LA, Rajwa B, Shemonti AS, Jaffey D, Powley T, Keast JR, Lu KH, Dundar MM. High-throughput segmentation of unmyelinated axons by deep learning. Sci Rep 2022; 12:1198. [PMID: 35075171 PMCID: PMC8786854 DOI: 10.1038/s41598-022-04854-3] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2021] [Accepted: 12/31/2021] [Indexed: 12/31/2022] Open
Abstract
Axonal characterizations of connectomes in healthy and disease phenotypes are surprisingly incomplete and biased because unmyelinated axons, the most prevalent type of fibers in the nervous system, have largely been ignored as their quantitative assessment quickly becomes unmanageable as the number of axons increases. Herein, we introduce the first prototype of a high-throughput processing pipeline for automated segmentation of unmyelinated fibers. Our team has used transmission electron microscopy images of vagus and pelvic nerves in rats. All unmyelinated axons in these images are individually annotated and used as labeled data to train and validate a deep instance segmentation network. We investigate the effect of different training strategies on the overall segmentation accuracy of the network. We extensively validate the segmentation algorithm as a stand-alone segmentation tool as well as in an expert-in-the-loop hybrid segmentation setting with preliminary, albeit remarkably encouraging results. Our algorithm achieves an instance-level [Formula: see text] score of between 0.7 and 0.9 on various test images in the stand-alone mode and reduces expert annotation labor by 80% in the hybrid setting. We hope that this new high-throughput segmentation pipeline will enable quick and accurate characterization of unmyelinated fibers at scale and become instrumental in significantly advancing our understanding of connectomes in both the peripheral and the central nervous systems.
Collapse
Affiliation(s)
- Emanuele Plebani
- Department of Computer and Information Sciences, Indiana University, Purdue University, Indianapolis, IN, 46202, USA
| | - Natalia P Biscola
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
| | - Leif A Havton
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
- Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA
- James J. Peters Department of Veterans Affairs Medical Center, Bronx, NY, 10468, USA
| | - Bartek Rajwa
- Bindley Bioscience Center, Purdue University, West Lafayette, IN, 47906, USA
| | | | - Deborah Jaffey
- Department of Psychological Sciences, Purdue University, West Lafayette, IN, 47907, USA
| | - Terry Powley
- Department of Psychological Sciences, Purdue University, West Lafayette, IN, 47907, USA
| | - Janet R Keast
- Department of Anatomy and Physiology, The University of Melbourne, Melbourne, VIC, 3010, Australia
| | - Kun-Han Lu
- Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, 47907, USA
| | - M Murat Dundar
- Department of Computer and Information Sciences, Indiana University, Purdue University, Indianapolis, IN, 46202, USA.
| |
Collapse
|
4
|
MyelTracer: A Semi-Automated Software for Myelin g-Ratio Quantification. eNeuro 2021; 8:ENEURO.0558-20.2021. [PMID: 34193510 PMCID: PMC8298095 DOI: 10.1523/eneuro.0558-20.2021] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2020] [Revised: 06/14/2021] [Accepted: 06/17/2021] [Indexed: 11/21/2022] Open
Abstract
In the central and peripheral nervous systems, the myelin sheath promotes neuronal signal transduction. The thickness of the myelin sheath changes during development and in disease conditions like multiple sclerosis. Such changes are routinely detected using electron microscopy through g-ratio quantification. While g-ratio is one of the most critical measurements in myelin studies, a major drawback is that g-ratio quantification is extremely laborious and time-consuming. Here, we report the development and validation of MyelTracer, an installable, stand-alone software for semi-automated g-ratio quantification based on the Open Computer Vision Library (OpenCV). Compared with manual g-ratio quantification, using MyelTracer produces consistent results across multiple tissues and animal ages, as well as in remyelination after optic nerve crush, and reduces total quantification time by 40-60%. With g-ratio measurements via MyelTracer, a known hypomyelination phenotype can be detected in a Williams syndrome mouse model. MyelTracer is easy to use and freely available for Windows and Mac OS X (https://github.com/HarrisonAllen/MyelTracer).
Collapse
|
5
|
Wong AL, Hricz N, Malapati H, von Guionneau N, Wong M, Harris T, Boudreau M, Cohen-Adad J, Tuffaha S. A simple and robust method for automating analysis of naïve and regenerating peripheral nerves. PLoS One 2021; 16:e0248323. [PMID: 34234376 PMCID: PMC8263263 DOI: 10.1371/journal.pone.0248323] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2021] [Accepted: 06/15/2021] [Indexed: 11/18/2022] Open
Abstract
BACKGROUND Manual axon histomorphometry (AH) is time- and resource-intensive, which has inspired many attempts at automation. However, there has been little investigation on implementation of automated programs for widespread use. Ideally such a program should be able to perform AH across imaging modalities and nerve states. AxonDeepSeg (ADS) is an open source deep learning program that has previously been validated in electron microscopy. We evaluated the robustness of ADS for peripheral nerve axonal histomorphometry in light micrographs prepared using two different methods. METHODS Axon histomorphometry using ADS and manual analysis (gold-standard) was performed on light micrographs of naïve or regenerating rat median nerve cross-sections prepared with either toluidine-resin or osmium-paraffin embedding protocols. The parameters of interest included axon count, axon diameter, myelin thickness, and g-ratio. RESULTS Manual and automatic ADS axon counts demonstrated good agreement in naïve nerves and moderate agreement on regenerating nerves. There were small but consistent differences in measured axon diameter, myelin thickness and g-ratio; however, absolute differences were small. Both methods appropriately identified differences between naïve and regenerating nerves. ADS was faster than manual axon analysis. CONCLUSIONS Without any algorithm retraining, ADS was able to appropriately identify critical differences between naïve and regenerating nerves and work with different sample preparation methods of peripheral nerve light micrographs. While there were differences between absolute values between manual and ADS, ADS performed consistently and required much less time. ADS is an accessible and robust tool for AH that can provide consistent analysis across protocols and nerve states.
Collapse
Affiliation(s)
- Alison L. Wong
- Department of Plastic and Reconstructive Surgery, Johns Hopkins University, Baltimore, MD, United States of America
| | - Nicholas Hricz
- Department of Plastic and Reconstructive Surgery, Johns Hopkins University, Baltimore, MD, United States of America
| | - Harsha Malapati
- Department of Plastic and Reconstructive Surgery, Johns Hopkins University, Baltimore, MD, United States of America
| | - Nicholas von Guionneau
- Department of Plastic and Reconstructive Surgery, Johns Hopkins University, Baltimore, MD, United States of America
| | - Michael Wong
- Department of Anesthesia, Dalhousie University Faculty of Medicine, Pain Management & Perioperative Medicine, Halifax, NS, Canada
| | - Thomas Harris
- Department of Plastic and Reconstructive Surgery, Johns Hopkins University, Baltimore, MD, United States of America
| | - Mathieu Boudreau
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
| | - Julien Cohen-Adad
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
| | - Sami Tuffaha
- Department of Plastic and Reconstructive Surgery, Johns Hopkins University, Baltimore, MD, United States of America
| |
Collapse
|
6
|
Myelin detection in fluorescence microscopy images using machine learning. J Neurosci Methods 2020; 346:108946. [PMID: 32931810 DOI: 10.1016/j.jneumeth.2020.108946] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2020] [Revised: 08/28/2020] [Accepted: 09/10/2020] [Indexed: 11/22/2022]
Abstract
BACKGROUND The myelin sheath produced by glial cells insulates the axons, and supports the function of the nervous system. Myelin sheath degeneration causes neurodegenerative disorders, such as multiple sclerosis (MS). There are no therapies for MS that promote remyelination. Drug discovery frequently involves screening thousands of compounds. However, this is not feasible for remyelination drugs, since myelin quantification is a manual labor-intensive endeavor. Therefore, the development of assistive software for expedited myelin detection is instrumental for MS drug discovery by enabling high-content image-based drug screens. NEW METHOD In this study, we developed a machine learning based expedited myelin detection approach in fluorescence microscopy images. Multi-channel three-dimensional microscopy images of a mouse stem cell-based myelination assay were labeled by experts. A spectro-spatial feature extraction method was introduced to represent local dependencies of voxels both in spatial and spectral domains. Feature extraction yielded two data set of over forty-seven thousand annotated images in total. RESULTS Myelin detection performances of 23 different supervised machine learning techniques including a customized-convolutional neural network (CNN), were assessed using various train/test split ratios of the data sets. The highest accuracy values of 98.84±0.09% and 98.46±0.11% were achieved by Boosted Trees and customized-CNN, respectively. COMPARISON WITH EXISTING METHODS Our approach can detect myelin in a common experimental setup. Myelin extending in any orientation in 3 dimensions is segmented from 3 channel z-stack fluorescence images. CONCLUSIONS Our results suggest that the proposed expedited myelin detection approach is a feasible and robust method for remyelination drug screening.
Collapse
|
7
|
Sui J, Liu M, Lee JH, Zhang J, Calhoun V. Deep learning methods and applications in neuroimaging. J Neurosci Methods 2020; 339:108718. [PMID: 32272117 DOI: 10.1016/j.jneumeth.2020.108718] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
Affiliation(s)
- Jing Sui
- National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China; University of Chinese Academy of Sciences, CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, 100049, China; Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, GA, 30303, USA.
| | - MingXia Liu
- Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, NC, USA
| | - Jong-Hwan Lee
- Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea
| | - Jun Zhang
- Department of Electrical and Computer Engineering (ECE), Duke University, Durham, NC, USA
| | - Vince Calhoun
- Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, and Emory University, Atlanta, GA, 30303, USA
| |
Collapse
|