Abstract
Computer assisted image acquisition techniques, including confocal microscopy, require efficient tools for an automatic sorting of vast amount of generated image data. The complexity of the classification process, absence of adequate tools, and insufficient amount of reference data has made the automated processing of images challenging. Mastering of this issue would allow implementation of statistical analysis in research areas such as in research on formation of t-tubules in cardiac myocytes. We developed a system aimed at automatic assessment of cardiomyocyte development stages (SAACS). The system classifies confocal images of cardiomyocytes with fluorescent dye stained sarcolemma. We based SAACS on a densely connected convolutional network (DenseNet) topology. We created a set of labelled source images, proposed an appropriate data augmentation technique and designed a class probability graph. We showed that the DenseNet topology, in combination with the augmentation technique is suitable for the given task, and that high-resolution images are instrumental for image categorization. SAACS, in combination with the automatic high-throughput confocal imaging, will allow application of statistical analysis in the research of the tubular system development or remodelling and loss.
Highlights
We show that SAACS trained on the augmented dataset, consisting of fifteen source images of each class only, was able to identify the whole and healthy myocytes, and differentiate among five cardiomyocyte development stages
The used building components are listed with respect to their placement in the network; where DBa and DBb are the basic and the bottleneck versions of the dense blocks; MPL is the max pooling layer; transition layers (TLs) is the transition layer, GAP denotes the global average pooling, and C is used for a classifier that consists of one fully connected layer followed by the softmax function
The ability of SAACS to assess cardiomyocyte development stages from confocal microscopy images varied with respect to the composition of training sets and with respect to the resolution of object images (Table 4)
Summary
15 and 9 source images of class 0 were allocated to the training and the evaluation set, respectively. The used building components are listed with respect to their placement in the network (the first block is the leftmost one); where DBa and DBb are the basic and the bottleneck versions of the dense blocks; MPL is the max pooling layer; TL is the transition layer, GAP denotes the global average pooling, and C is used for a classifier that consists of one fully connected layer followed by the softmax function. The class probability graph displays scores of each sample (object image) in an evaluation set as a bar of fixed height. We organized samples in the evaluation set with respect to source images, their rotation and flipping. Python implementations of the networks, of training and evaluation routines, likewise of a code which delineates class probability graphs are provided in a supplementary file S1 File
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
