Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation
Autor: | René R. Sevag Packard, Yanan Fei, Dengfeng Kuang, Kyung In Baek, Tzung K. Hsiai, Zhaoqiang Wang, Mehrdad Roustaei, Varun Gudapati, Sibo Song, Ruiyuan Lin, C.-C. Jay Kuo, Yichen Ding, Chih-Chiang Chang |
---|---|
Rok vydání: | 2021 |
Předmět: |
Neural Networks
Artificial Intelligence and Image Processing principal component analysis Computer science Image Processing 0206 medical engineering Feature extraction Biomedical Engineering Bioengineering Image processing 02 engineering and technology Cardiovascular Machine learning computer.software_genre Fluorescence Article Edge detection Machine Learning Computer Computer-Assisted Image Processing Computer-Assisted Segmentation Electrical and Electronic Engineering Microscopy Image segmentation business.industry Heart Random forests Transforms 020601 biomedical engineering Kernel Heart Disease Networking and Information Technology R&D (NITRD) Microscopy Fluorescence cardiology Biomedical Imaging Neural Networks Computer Artificial intelligence Biomedical optical imaging business computer Algorithms Subspace topology |
Zdroj: | IEEE Trans Biomed Eng IEEE transactions on bio-medical engineering, vol 68, iss 1 |
ISSN: | 1558-2531 0018-9294 |
DOI: | 10.1109/tbme.2020.2991754 |
Popis: | Objective: Recent advances in light-sheet fluorescence microscopy (LSFM) enable 3-dimensional (3-D) imaging of cardiac architecture and mechanics in toto . However, segmentation of the cardiac trabecular network to quantify cardiac injury remains a challenge. Methods: We hereby employed “subspace approximation with augmented kernels (Saak) transform” for accurate and efficient quantification of the light-sheet image stacks following chemotherapy-treatment. We established a machine learning framework with augmented kernels based on the Karhunen-Loeve Transform (KLT) to preserve linearity and reversibility of rectification. Results: The Saak transform-based machine learning enhances computational efficiency and obviates iterative optimization of cost function needed for neural networks, minimizing the number of training datasets for segmentation in our scenario. The integration of forward and inverse Saak transforms can also serve as a light-weight module to filter adversarial perturbations and reconstruct estimated images, salvaging robustness of existing classification methods. The accuracy and robustness of the Saak transform are evident following the tests of dice similarity coefficients and various adversary perturbation algorithms, respectively. The addition of edge detection further allows for quantifying the surface area to volume ratio (SVR) of the myocardium in response to chemotherapy-induced cardiac remodeling. Conclusion: The combination of Saak transform, random forest, and edge detection augments segmentation efficiency by 20-fold as compared to manual processing. Significance: This new methodology establishes a robust framework for post light-sheet imaging processing, and creating a data-driven machine learning for automated quantification of cardiac ultra-structure. |
Databáze: | OpenAIRE |
Externí odkaz: |