Robust Individual-Cell/Object Tracking via PCANet Deep Network in Biomedicine and Computer Vision

Abstract

Tracking individual-cell/object over time is important in understanding drug treatment effects on cancer cells and video surveillance. A fundamental problem of individual-cell/object tracking is to simultaneously address the cell/object appearance variations caused by intrinsic and extrinsic factors. In this paper, inspired by the architecture of deep learning, we propose a robust feature learning method for constructing discriminative appearance models without large-scale pretraining. Specifically, in the initial frames, an unsupervised method is firstly used to learn the abstract feature of a target by exploiting both classic principal component analysis (PCA) algorithms with recent deep learning representation architectures. We use learned PCA eigenvectors as filters and develop a novel algorithm to represent a target by composing of a PCA-based filter bank layer, a nonlinear layer, and a patch-based pooling layer, respectively. Then, based on the feature representation, a neural network with one hidden layer is trained in a supervised mode to construct a discriminative appearance model. Finally, to alleviate the tracker drifting problem, a sample update scheme is carefully designed to keep track of the most representative and diverse samples during tracking. We test the proposed tracking method on two standard individual cell/object tracking benchmarks to show our tracker's state-of-the-art performance.

Deep Learning‐Based Single‐Cell Optical Image Studies

“…Single cell tracing is a basic problem in the fields of computational biology, immunology, pharmacology, and high content screening . Cell tracking is fundamentally a complex target tracking problem.…”

“…With the great breakthroughs made by deep learning in the field of target detection and recognition, researchers have begun to apply deep learning models to target tracking . Many deep learning‐based cell tracking methods have effectively overcome the difficulties of cell tracking caused by cell overlap and deformation . Deep learning techniques can learn the robust properties of cells and track cells in complex movements of multiple modes.…”

Automated in vivo Tracking of Cortical Oligodendrocytes

“…Currently, most available cell tracking algorithms are designed for in vitro analysis and are not readily adaptable to in vivo conditions ( van Valen et al, 2016 ; Zhong et al, 2016 ; Nketia et al, 2017 ; Lugagne et al, 2020 ; Wang et al, 2020 ). The few in vivo tracking algorithms that exist are modality specific and cannot be readily adapted to our fluorescent longitudinal datasets ( Acton et al, 2002 ; Nguyen et al, 2011 ; Wang et al, 2015 ).…”

Automated in vivo tracking of cortical oligodendrocytes

“…Currently, most available cell tracking algorithms are designed for in vitro analysis and are not readily adaptable to in vivo conditions (Van Valen et al, 2016; Zhong et al, 2016; Nketia et al, 2017; Lugagne et al, 2020; Wang et al, 2020). The few in vivo tracking algorithms that exist are modality specific and cannot be readily adapted to our fluorescent longitudinal datasets (Acton et al, 2002; Nguyen et al, 2011).…”