Search Constraints
Filtering by:
Creator
Sachse, Frank B.
Remove constraint Creator: Sachse, Frank B.
Keyword
cardiac
Remove constraint Keyword: cardiac
1 - 2 of 2
Number of results to display per page
Search Results
-
- Description:
- This dataset accompanies the research article entitled, "Etiology-Specific Remodeling in Ventricular Tissue of Heart Failure Patients and its Implications for Computational Modeling of Electrical Conduction," where we quantified fibrosis and performed electrophysiological simulation to investigate electrical propagation in etiologically varied heart failure tissue samples. Included are raw confocal microscopic images, data for extracting and processing the raw images and script to analyze fibrosis and generate meshes for simulation.
- Keyword:
- human, heart failure, cardiac, confocal microscopic images, simulation, and fibrosis
- Subject:
- cardiology
- Creator:
- Drakos, Stavros G., Sachse, Frank B., Kyriakopoulos, Christos P., Bragard, Jean, Greiner, Joachim, Chakkalakkal Sankarankutty, Aparna, Visker, Joseph R., and Shankar, Thirupura S.
- Owner:
- Aparna Sankarankutty
- Based Near Label Tesim:
- Salt Lake City, Utah, United States
- Language:
- English
- Date Uploaded:
- 06/08/2021
- Date Modified:
- 12/08/2023
- Date Created:
- 2019-01-01 to 2020-11-30
- License:
- CC BY NC - Allows others to use and share your data non-commercially and with attribution.
- Resource Type:
- Dataset
- Identifier:
- https://doi.org/10.7278/S50D-BPS8-R06S
-
- Description:
- Significance: Current medical imaging systems have many limitations for applications in cardiovascular diseases. New technologies may overcome these limitations. Particularly interesting are technologies for diagnosis of cardiac diseases, e.g. fibrosis, myocarditis, and transplant rejection. Aim: To introduce and assess a new optical system capable of assessing cardiac muscle tissue using light-scattering spectroscopy (LSS) in conjunction with machine learning. Approach: We applied an ovine model to investigate if the new LSS system is capable of estimating densities of cell nuclei in cardiac tissue. We measured the nuclear density using fluorescent labeling, confocal microscopy, and image processing. Spectra acquired from the same cardiac tissues were analyzed with spectral clustering and convolutional neural networks to assess feasibility and reliability of density quantification. Results: Spectral clustering revealed distinct groups of spectra correlated to ranges of nuclear density. Convolutional neural networks correctly classified 3 groups of spectra with low, medium, or high nuclear density with 95.00±11.77% (mean and standard deviation) accuracy. The analysis revealed sensitivity of the accuracy to wavelength range and subsampling of spectra. Conclusions: LSS and machine learning are capable of assessing nuclear density in cardiac tissues. The approach could be useful for diagnosis of cardiac diseases associated with an increase of nuclei.
- Keyword:
- machine learning, diagnosis, neural networks, medical imaging, nuclear density, spectroscopy, spectral imaging, and cardiac
- Subject:
- Cardiology
- Creator:
- Sachse, Frank B., Tiwari, Sarthak, Kaza, Aditya K., Cottle, Brian K., Knighton, Nathan, and Hitchcock, Robert W.
- Owner:
- Brian Cottle
- Based Near Label Tesim:
- Salt Lake City, UT, Utah, United States
- Language:
- English
- Date Uploaded:
- 05/11/2021
- Date Modified:
- 12/08/2023
- Date Created:
- 2019-01-01 to 2019-02-08 and 2020-07-21 to 2020-08-07
- License:
- CC BY NC - Allows others to use and share your data non-commercially and with attribution.
- Resource Type:
- Dataset
- Identifier:
- https://doi.org/10.7278/S50D-FV1Q-BYNS