DeepProjection: Rapid and structure-specific projections of tissue sheets embedded in 3D microscopy stacks using deep learning

The efficient extraction of local high-resolution content from massive amounts of imaging data remains a serious and unsolved problem in studies of complex biological tissues. Here we present DeepProjection, a trainable projection algorithm based on deep learning. This algorithm rapidly and robustly extracts image content contained in curved manifolds from time-lapse recorded 3D image stacks by binary masking of background content, stack by stack. The masks calculated for a given movie, when predicted, e.g., on fluorescent cell boundaries on one channel, can subsequently be applied to project other fluorescent channels from the same manifold. We apply DeepProjection to follow the dynamic movements of 2D-tissue sheets in embryonic development. We show that we can selectively project the amnioserosa cell sheet during dorsal closure in Drosophila melanogaster embryos and the periderm layer in the elongating zebrafish embryo while masking highly fluorescent out-of-plane artifacts.

Reformulating the Binary Masking Approach of Adress as Soft Masking

Binary masking forms the basis for a number of source separation approaches that have been successfully applied to the problem of de-mixing music sources from a stereo recording. A well-known problem with binary masking is that, when music sources overlap in the time-frequency domain, only one of the overlapping sources can be assigned the energy in a particular time-frequency bin. To overcome this problem, we reformulate the classical pan-pot source separation problem for music sources as a non-negative quadratic program. This reformulation gives rise to an algorithm, called Redress, which extends the popular Adress algorithm. It works by defining an azimuth trajectory for each source based on its spatial position within the stereo field. Redress allows for the allocation of energy in one time-frequency bin to multiple sources. We present results that show that for music recordings Redress improves the SNR, SAR, and SDR in comparison to the Adress algorithm.

Automatic analysis of image quality by ETR-1 for the On-Board Imager

The test-plate image of an image quality test tool is processed. The processing is based on quality assurance with the well-established test device ETR-1. A program is developed to analyze the parameters such as contrast, low contrast and resolution automatically. This results in more accurate patient positioning for the On-Board Imager (OBI) system. The contrast and resolution are measured by means of Bresenham’s line algorithm. The low contrast is calculated with the help of binary masking. The modulation transfer function (MTF) is also observed for the system. The developed program imports the Digital Imaging and Communications in Medicine (DICOM) image and returns the image parameters. The program can process the ideal image or the less noisy image. The no-rotation-mode or the slight-rotation-mode of the test-plate can be analyzed.