Title | ||
---|---|---|
Training Convolutional Neural Networks and Compressed Sensing End-to-End for Microscopy Cell Detection. |
Abstract | ||
---|---|---|
Automated cell detection and localization from microscopy images are significant tasks in biomedical research and clinical practice. In this paper, we design a new cell detection and localization algorithm that combines deep convolutional neural network (CNN) and compressed sensing (CS) or sparse coding (SC) for end-to-end training. We also derive, for the first time, a backpropagation rule, which is applicable to train any algorithm that implements a sparse code recovery layer. The key innovation behind our algorithm is that the cell detection task is structured as a point object detection task in computer vision, where the cell centers (i.e., point objects) occupy only a tiny fraction of the total number of pixels in an image. Thus, we can apply compressed sensing (or, equivalently sparse coding) to compactly represent a variable number of cells in a projected space. Subsequently, CNN regresses this compressed vector from the input microscopy image. The SC/CS recovery algorithm (L1 optimization) can then recover sparse cell locations from the output of CNN. We train this entire processing pipeline end-to-end and demonstrate that end-to-end training improves accuracy over a training paradigm that treats CNN and CS-recovery layers separately. We have validated our algorithm on five benchmark datasets with excellent results. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TMI.2019.2907093 | IEEE Transactions on Medical Imaging |
Keywords | Field | DocType |
Computer architecture,Microprocessors,Encoding,Microscopy,Training,Compressed sensing,Backpropagation | Computer vision,Object detection,Convolutional neural network,End-to-end principle,Neural coding,Pixel,Artificial intelligence,Backpropagation,Compressed sensing,Mathematics,Encoding (memory) | Journal |
Volume | Issue | ISSN |
abs/1810.03075 | 11 | 0278-0062 |
Citations | PageRank | References |
2 | 0.39 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yao Xue | 1 | 79 | 6.56 |
Gilbert Bigras | 2 | 11 | 1.96 |
Judith Hugh | 3 | 11 | 1.62 |
Ray Nilanjan | 4 | 541 | 55.39 |