Deep learning enables automated volumetric assessments of cardiac function in zebrafish

ABSTRACT Although the zebrafish embryo is a powerful animal model of human heart failure, the methods routinely employed to monitor cardiac function produce rough approximations that are susceptible to bias and inaccuracies. We developed and validated a deep learning-based image-analysis platform for automated extraction of volumetric parameters of cardiac function from dynamic light-sheet fluorescence microscopy (LSFM) images of embryonic zebrafish hearts. This platform, the Cardiac Functional Imaging Network (CFIN), automatically delivers rapid and accurate assessments of cardiac performance with greater sensitivity than current approaches. This article has an associated First Person interview with the first author of the paper. Summary: The authors present CFIN, a deep learning-based image-analysis platform to automatically analyze dynamic light-sheet fluorescence microscopy images and determine volumetric indices of cardiac function in embryonic zebrafish.

[1]  Ron Kikinis,et al.  Statistical validation of image segmentation quality based on a spatial overlap index. , 2004, Academic radiology.

[2]  Peng Fei,et al.  Automated Segmentation of Light-Sheet Fluorescent Imaging to Characterize Experimental Doxorubicin-Induced Cardiac Injury and Repair , 2017, Scientific Reports.

[3]  Benjamin Schmid,et al.  High-resolution reconstruction of the beating zebrafish heart , 2014, Nature Methods.

[4]  C. Nüsslein-Volhard,et al.  Mutations affecting pigmentation and shape of the adult zebrafish , 1996, Development Genes and Evolution.

[5]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Ben Glocker,et al.  Automated cardiovascular magnetic resonance image analysis with fully convolutional networks , 2017, Journal of Cardiovascular Magnetic Resonance.

[7]  Calum A MacRae,et al.  High-resolution cardiovascular function confirms functional orthology of myocardial contractility pathways in zebrafish. , 2010, Physiological genomics.

[8]  C.-C. Jay Kuo,et al.  Amendment history : Corrigendum ( August 2016 ) 4-Dimensional light-sheet microscopy to elucidate shear stress modulation of cardiac trabeculation , 2018 .

[9]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[10]  C.-C. Jay Kuo,et al.  Cardiac Light-Sheet Fluorescent Microscopy for Multi-Scale and Rapid Imaging of Architecture and Function , 2016, Scientific Reports.

[11]  Wolfgang Rottbauer,et al.  High-throughput assay for small molecules that modulate zebrafish embryonic heart rate , 2005, Nature chemical biology.

[12]  C. Nüsslein-Volhard,et al.  Mutations affecting the cardiovascular system and other internal organs in zebrafish. , 1996, Development.

[13]  D. Haber,et al.  Visnagin protects against doxorubicin-induced cardiomyopathy through modulation of mitochondrial malate dehydrogenase , 2014, Science Translational Medicine.

[14]  A. Benz,et al.  Induction of cardiac dysfunction in developing and adult zebrafish by chronic isoproterenol stimulation. , 2017, Journal of Molecular and Cellular Cardiology.

[15]  Hao Chen,et al.  3D deeply supervised network for automated segmentation of volumetric medical images , 2017, Medical Image Anal..

[16]  A. Schier,et al.  Mutations affecting the formation and function of the cardiovascular system in the zebrafish embryo. , 1996, Development.

[17]  Min-Ying Su,et al.  Automatic Breast and Fibroglandular Tissue Segmentation in Breast MRI Using Deep Learning by a Fully-Convolutional Residual Neural Network U-Net. , 2019, Academic radiology.

[18]  C.-C. Jay Kuo,et al.  Amendment history : Corrigendum ( August 2016 ) 4-Dimensional light-sheet microscopy to elucidate shear stress modulation of cardiac trabeculation , 2018 .

[19]  Huai-Jen Tsai,et al.  Functional Modulation of Cardiac Form through Regionally Confined Cell Shape Changes , 2007, PLoS biology.

[20]  M. Yacoub,et al.  Heart function and hemodynamic analysis for zebrafish embryos , 2017, Developmental dynamics : an official publication of the American Association of Anatomists.

[21]  M. Ekker,et al.  In vivo and in vitro assessment of cardiac β-adrenergic receptors in larval zebrafish (Danio rerio) , 2011, Journal of Experimental Biology.

[22]  Bram van Ginneken,et al.  Automatic classification of pulmonary peri-fissural nodules in computed tomography using an ensemble of 2D views and a convolutional neural network out-of-the-box , 2015, Medical Image Anal..

[23]  Diana Wald,et al.  Comparison of Segmentation Algorithms for the Zebrafish Heart in Fluorescent Microscopy Images , 2009, ISVC.

[24]  Raghuveer Parthasarathy,et al.  Performance of convolutional neural networks for identification of bacteria in 3D microscopy datasets , 2018 .

[25]  Christian A. Ross,et al.  Cardiac Transcriptome and Dilated Cardiomyopathy Genes in Zebrafish , 2015, Circulation. Cardiovascular genetics.

[26]  Chetana Sachidanandan,et al.  In vivo natriuretic peptide reporter assay identifies chemical modifiers of hypertrophic cardiomyopathy signalling. , 2012, Cardiovascular research.

[27]  Xiaolei Xu,et al.  Quantifying cardiac functions in embryonic and adult zebrafish. , 2012, Methods in molecular biology.

[28]  Neeraj Sharma,et al.  Automated medical image segmentation techniques , 2010, Journal of medical physics.

[29]  Jeroen Bakkers,et al.  Zebrafish as a model to study cardiac development and human cardiac disease , 2011, Cardiovascular research.