Heartbeat Detection from Zebrafish Larvae Videos with Automatic Noise Elimination

• Main Authors: Chia-PinKang, 康家彬
• Other Authors: Tien-Hao Chang
• Format: Others
• Language: zh-TW
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/a4a34f

碩士 === 國立成功大學 === 電機工程學系 === 104 === Background: Zebrafish is a widely used model organism for studying heart development and cardiac-related pathogenesis. With the benefits of being able to survive without a functional circulation at larval stages, strong genetic similarity between zebrafish and mammals, prolific reproduction and optically transparent embryos, zebrafish is powerful in modeling mammalian cardiac physiology and pathology as well as in large-scale high throughput screening. An economical and convenient tool for rapid evaluation of fish cardiac function is still in need. There have been several image analysis methods to assess cardiac functions in zebrafish embryos, but they are still improvable to reduce manual intervention in the entire process. This work developed a fully automatic method to retrieve heartbeat rate, an important parameter to analyze cardiac function, from videos. It contains several algorithms to identify the heart region, to reduce video noise and to calculate heartbeat rates. Results: The proposed method was evaluated with 37 zebrafish embryo videos that were recording at three day post-fertilization. The heartbeat rate measured by the proposed method was similar to that determined by manual counting, indicated that the proposed method can accurately retrieved the heartbeat rate from zebrafish embryo videos. Conclusion: With the proposed method, researchers do not have to manually select a region of interest while analyzing videos. Moreover, many filters are designed to enhance the heartbeat function in videos, which can alleviate recording defects such as shifting and therefore reduce manual efforts while recording.