Cell Detection with Deep Convolutional Neural Network and Compressed Sensing
share
The ability to automatically detect certain types of cells or cellular subunits in microscopy images is of significant interest to a wide range of biomedical research and clinical practices. Cell detection methods have evolved from employing hand-crafted features to deep learning-based techniques to locate target cells. The essential idea of these methods is that their cell classifiers or detectors are trained in the pixel space, where the locations of target cells are labeled. In this paper, we seek a different route and propose a convolutional neural network (CNN)-based cell detection method that uses encoding of the output pixel space. For the cell detection problem, the output space is the sparsely labeled pixel locations indicating cell centers. Consequently, we employ random projections to encode the output space to a compressed vector of fixed dimension. Then, CNN regresses this compressed vector from the input pixels. Using L_1-norm optimization, we recover sparse cell locations on the output pixel space from the predicted compressed vector. In the past, output space encoding using compressed sensing (CS) has been used in conjunction with linear and non-linear predictors. To the best of our knowledge, this is the first successful use of CNN with CS-based output space encoding. We experimentally demonstrate that proposed CNN + CS framework (referred to as CNNCS) exceeds the accuracy of the state-of-the-art methods on many benchmark datasets for microscopy cell detection. Additionally, we show that CNNCS can exploit ensemble average by using more than one random encodings of the output space. In the AMIDA13 MICCAI grand competition, we achieve the 3rd highest F1-score in all the 17 participated teams. More ranking details are available at http://amida13.isi.uu.nl/?q=node/62. Implementation of CNNCS is available at https://github.com/yaoxuexa/CNNCS.
READ FULL TEXT