Search NASA⌕ Search

Engineering topics

Shirinifard, Abbas

Publications and source records attributed to Shirinifard, Abbas.

YOLO2U-Net: Detection-guided 3D instance segmentation for microscopy

Microscopy imaging techniques are instrumental for characterization and analysis of biological structures. As these techniques typically render 3D visualization of cells by stacking 2D projections, issues such as out-of-plane excitation and low resolution in the z-axis may pose challenges (even for human experts) to detect individual cells in 3D volumes as these non-overlapping cells may appear as overlapping. In this paper a comprehensive method for accurate 3D instance segmentation of cells in the brain tissue is introduced. The proposed method combines the 2D YOLO detection method with a multi-view fusion algorithm to construct a 3D localization of the cells. Next, the 3D bounding boxes along with the data volume are input to a 3D U-Net network that is designed to segment the primary cell in each 3D bounding box, and in turn, to carry out instance segmentation of cells in the entire volume. The promising performance of the proposed method is shown in comparison with current deep learning-based 3D instance segmentation methods.

3D instance segmentation↗

A Two-Tier Convolutional Neural Network for Combined Detection and Segmentation in Biological Imagery

Deep learning techniques have been useful for modern microscopy imaging techniques to further study and analyze biological structures and organs. Convolutional neural networks (CNN) have improved 2D object detection, localization, and segmentation. For imagery containing biological structures with depth, it is especially desirable to perform these tasks in 3D. Traditionally, performing these tasks simultaneously in 3D has proven to be computationally expensive. Currently available methodologies thus largely work to segment 3D objects from 2D images (without context from captured 3D volumes). In this work, we present a novel approach to perform fast and accurate localization, detection, and segmentation of volumes containing cells. Specifically, in our method, we modify and tune two state-of-the-art CNNs, namely 2D YOLOv2 and 3D U-Net, and combine them with a new fusion and image processing algorithms. Annotated volumes in this space are limited, and we have created synthetic data that mimics actual structures for training and testing our proposed approach. Promising results on this test data demonstrate the value of the technique and offers a methodology for 3D cell analysis in real microscopy imagery.

Ziabari, Amir↗

A 2.5d Yolo-Based Fusion Algorithm for 3d Localization Of Cells

Advances in microscopy techniques such as lattice-light-sheet, confocal, two-photon, and electron microscopy have enabled the visualization of 3D image volumes of tightly packed cells, extracellular structures in tissues, organelles, and subcellular components inside cells. These images sampled by 2D projections are often not accurately interpreted even by human experts. As a use case we focus on 3D image volumes of tightly packed nuclei in brain tissue. Due to out-of-plane excitation and low resolution in the z-axis, non-overlapping cells appear as overlapping 3D volumes and make detecting individual cells challenging. On the other hand, running 3D detection algorithms is computationally expensive and infeasible for large datasets. In addition, most existing 3D algorithms are designed to extract 3D objects by identifying the depth in the 2D images. In this work, we propose a YOLO-based 2.5D fusion algorithm for 3D localization of individual cells in densely packed volumes of nuclei. The proposed method fuses 2D detection of nuclei in sagittal, coronal, and axial planes and predicts six coordinates of the 3D bounding cubes around the detected 3D cells. Promising results were obtained on multiple examples of synthetic dense volumes of nuclei imitating confocal microscopy experimental datasets.

Ziabari, Amir↗

Adhesion Failures Determine the Pattern of Choroidal Neovascularization in the Eye: A Computer Simulation Study

Choroidal neovascularization (CNV) of the macular area of the retina is the major cause of severe vision loss in adults. In CNV, after choriocapillaries initially penetrate Bruch’s membrane (BrM), invading vessels may regress or expand (CNV initiation). Next, during Early and Late CNV, the expanding vasculature usually spreads in one of three distinct patterns: in a layer between BrM and the retinal pigment epithelium (sub-RPE or Type 1 CNV), in a layer between the RPE and the photoreceptors (subretinal or Type 2 CNV) or in both loci simultaneously (combined pattern or Type 3 CNV). While most studies hypothesize that CNV primarily results from growth-factor effects or holes in BrM, our three-dimensional simulations of multi-cell model of the normal and pathological maculae recapitulate the three growth patterns, under the hypothesis that CNV results from combinations of impairment of: 1) RPE-RPE epithelial junctional adhesion, 2) Adhesion of the RPE basement membrane complex to BrM (RPE-BrM adhesion), and 3) Adhesion of the RPE to the photoreceptor outer segments (RPE-POS adhesion). Our key findings are that when an endothelial tip cell penetrates BrM: 1) RPE with normal epithelial junctions, basal attachment to BrM and apical attachment to POS resists CNV. 2) Small holes in BrM do not, by themselves, initiate CNV. 3) RPE with normal epithelial junctions and normal apical RPE-POS adhesion, but weak adhesion to BrM (e.g. due to lipid accumulation in BrM) results in Early sub-RPE CNV. 4) Normal adhesion of RBaM to BrM, but reduced apical RPE-POS or epithelial RPE-RPE adhesion (e.g. due to inflammation) results in Early sub-retinal CNV. 5) Simultaneous reduction in RPE-RPE epithelial binding and RPEBrM adhesion results in either sub-RPE or sub-retinal CNV which often progresses to combined pattern CNV. These findings suggest that defects in adhesion dominate CNV initiation and progression.

59 BASIC BIOLOGICAL SCIENCES↗