1
|
Ouyang X, Matt A, Wang F, Gracheva E, Migunova E, Rajamani S, Dubrovsky EB, Zhou C. Attention LSTM U-Net model for Drosophila melanogaster heart tube segmentation in optical coherence microscopy images. BIOMEDICAL OPTICS EXPRESS 2024; 15:3639-3653. [PMID: 38867790 PMCID: PMC11166423 DOI: 10.1364/boe.523364] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/08/2024] [Revised: 04/22/2024] [Accepted: 04/28/2024] [Indexed: 06/14/2024]
Abstract
Optical coherence microscopy (OCM) imaging of the Drosophila melanogaster (fruit fly) heart tube has enabled the non-invasive characterization of fly heart physiology in vivo. OCM generates large volumes of data, making it necessary to automate image analysis. Deep-learning-based neural network models have been developed to improve the efficiency of fly heart image segmentation. However, image artifacts caused by sample motion or reflections reduce the accuracy of the analysis. To improve the precision and efficiency of image data analysis, we developed an Attention LSTM U-Net model (FlyNet3.0), which incorporates an attention learning mechanism to track the beating fly heart in OCM images. The new model has improved the intersection over union (IOU) compared to FlyNet2.0 + with reflection artifacts from 86% to 89% and with movement from 81% to 89%. We also extended the capabilities of OCM analysis through the introduction of an automated, in vivo heart wall thickness measurement method, which has been validated on a Drosophila model of cardiac hypertrophy. This work will enable the comprehensive, non-invasive characterization of fly heart physiology in a high-throughput manner.
Collapse
Affiliation(s)
- Xiangping Ouyang
- Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA
| | - Abigail Matt
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA
| | - Fei Wang
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA
| | - Elena Gracheva
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA
| | - Ekaterina Migunova
- Department of Biological Sciences, Fordham University, Bronx, NY 10458, USA
| | - Saathvika Rajamani
- Department of Biological Sciences, Fordham University, Bronx, NY 10458, USA
| | | | - Chao Zhou
- Department of Biomedical Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA
| |
Collapse
|
2
|
Fishman M, Matt A, Wang F, Gracheva E, Zhu J, Ouyang X, Komarov A, Wang Y, Liang H, Zhou C. A Drosophila heart optical coherence microscopy dataset for automatic video segmentation. Sci Data 2023; 10:886. [PMID: 38071220 PMCID: PMC10710430 DOI: 10.1038/s41597-023-02802-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2023] [Accepted: 11/30/2023] [Indexed: 12/18/2023] Open
Abstract
The heart of the fruit fly, Drosophila melanogaster, is a particularly suitable model for cardiac studies. Optical coherence microscopy (OCM) captures in vivo cross-sectional videos of the beating Drosophila heart for cardiac function quantification. To analyze those large-size multi-frame OCM recordings, human labelling has been employed, leading to low efficiency and poor reproducibility. Here, we introduce a robust and accurate automated Drosophila heart segmentation algorithm, called FlyNet 2.0+, which utilizes a long short-term memory (LSTM) convolutional neural network to leverage time series information in the videos, ensuring consistent, high-quality segmentation. We present a dataset of 213 Drosophila heart videos, equivalent to 604,000 cross-sectional images, containing all developmental stages and a wide range of beating patterns, including faster and slower than normal beating, arrhythmic beating, and periods of heart stop to capture these heart dynamics. Each video contains a corresponding ground truth mask. We expect this unique large dataset of the beating Drosophila heart in vivo will enable new deep learning approaches to efficiently characterize heart function to advance cardiac research.
Collapse
Affiliation(s)
- Matthew Fishman
- Washington University in St. Louis, Department of Computer Science and Engineering, St. Louis, MO, 63130, USA
| | - Abigail Matt
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA
| | - Fei Wang
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA
| | - Elena Gracheva
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA
| | - Jiantao Zhu
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA
| | - Xiangping Ouyang
- Washington University in St. Louis, Department of Computer Science and Engineering, St. Louis, MO, 63130, USA
| | - Andrey Komarov
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA
| | - Yuxuan Wang
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA
| | - Hongwu Liang
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA
| | - Chao Zhou
- Washington University in St. Louis, Department of Biomedical Engineering, St. Louis, MO, 63130, USA.
| |
Collapse
|