Cell Counting by Regression Using Convolutional Neural Network

Xue, Yao; Ray, Nilanjan; Hugh, Judith; Bigras, Gilbert

doi:10.1007/978-3-319-46604-0_20

Cited by 68 publications

(62 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hand-crafted cell nuclei boundary masks are also used as shape prior to filter the detection of CNNs [20]. Others applied CNNs for cell detection with pixel-level classification for each patch in the images [21]- [23]. Hofener et.…”

Section: B Deep Cell Detection Methodsmentioning

confidence: 99%

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

Memariani

Nikou

Endres

et al. 2018

Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Clostridioides difficile infection (C. diff) is the most common cause of death due to secondary infection in hospital patients in the United States. Detection of C. diff cells in scanning electron microscopy (SEM) images is an important task to quantify the efficacy of the under-development treatments. However, detecting C. diff cells in SEM images is a challenging problem due to the presence of inhomogeneous illumination and occlusion. An Illumination normalization pre-processing step destroys the texture and adds noise to the image. Furthermore, cells are often clustered together resulting in touching cells and occlusion. In this paper, DETCID, a deep cell detection method using adversarial training, specifically robust to inhomogeneous illumination and occlusion, is proposed. An adversarial network is developed to provide region proposals and pass the proposals to a feature extraction network. Furthermore, a modified IoU metric is developed to allow the detection of touching cells in various orientations. The results indicate that DETCID outperforms the state-of-the-art in detection of touching cells in SEM images by at least 20 percent improvement of mean average precision.

show abstract

Section: B Deep Cell Detection Methodsmentioning

confidence: 99%

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

Memariani

Nikou

Endres

et al. 2018

Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

show abstract

“…Alternatively, Xue et al [29] divided the input into multiple subimages and tested multiple neural networks to map sub-images to a single scalar, namely the cell count. Similarly, [19] used a pre-train network to learn the same mapping for cross-domain counting.…”

Section: Related Workmentioning

confidence: 99%

“…This simple dot-annotation method is advantageous for this task since there could be hundreds of cells in a single images and a complete annotation would be timeconsuming. Therefore, recent work approaches this task from a regression perspective, i.e., learning a mapping from an input image to either a scalar (cell count) [19,29] or a density map [13,18,21,28], from which the cell count can be inferred by integration. Inspired by the recent success of U-Net based methods for image segmentation [7,20,24] and the similarity between a density map and a segmentation map, we follow the latter direction and choose U-Net as the regression model.…”

Section: Introductionmentioning

confidence: 99%

SAU-Net

Guo

Stein

et al. 2019

Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

View full text Add to dashboard Cite

Image-based cell counting is a fundamental yet challenging task with wide applications in biological research. In this paper, we propose a novel Deep Network designed to universally solve this problem for various cell types. Specifically, we first extend the segmentation network, U-Net with a Self-Attention module, named SAU-Net, for cell counting. Second, we design an online version of Batch Normalization to mitigate the generalization gap caused by data augmentation in small datasets. We evaluate the proposed method on four public cell counting benchmarks-synthetic fluorescence microscopy (VGG) dataset, Modified Bone Marrow (MBM) dataset, human subcutaneous adipose tissue (ADI) dataset, and Dublin Cell Counting (DCC) dataset. Our method surpasses the current state-ofthe-art performance in the three real datasets (MBM, ADI and DCC) and achieves competitive results in the synthetic dataset (VGG).

show abstract

“…In [2], a supervised machine learning counting method that can estimate the object count with manual annotation input was introduced. Another method that uses machine learning to count objects and estimates the density of the objects in images was described in [3]. The ImageJ toolset [4] has a 3D object counter, known as JACoP [5], that is a subcellular colocalization analysis tool that uses a statistical approach with a manually selected threshold to analyze intensity information to obtain the object count and location.…”

Section: Introductionmentioning

confidence: 99%

“…A way of counting that uses convolutional neural networks (CNN) to estimate the number of pedestrians in a video was presented in [13]. Similarly, a tumor cell counting CNN is trained to provide both cell count and the cell locations in [3]. In another example, cell counting using fully convolutional regression networks (FCRNs) was introduced [14].…”

Section: Introductionmentioning

confidence: 99%

Nuclei counting in microscopy images with three dimensional generative adversarial networks

Han

Lee

et al. 2019

Medical Imaging 2019: Image Processing

View full text Add to dashboard Cite

Microscopy image analysis can provide substantial information for clinical study and understanding of biological structures. Two-photon microscopy is a type of fluorescence microscopy that can image deep into tissue with nearinfrared excitation light. We are interested in methods that can detect and characterize nuclei in 3D fluorescence microscopy image volumes. In general, several challenges exist for counting nuclei in 3D image volumes. These include crowding and touching of nuclei, overlapping of nuclei, and shape and size variances of the nuclei. In this paper, a 3D nuclei counter using two different generative adversarial networks (GAN) is proposed and evaluated. Synthetic data that resembles real microscopy image is generated with a GAN and used to train another 3D GAN that counts the number of nuclei. Our approach is evaluated with respect to the number of groundtruth nuclei and compared with common ways of counting used in the biological research. Fluorescence microscopy 3D image volumes of rat kidneys are used to test our 3D nuclei counter. The accuracy results of proposed nuclei counter are compared with the ImageJ's 3D object counter (JACoP) and the 3D watershed. Both the counting accuracy and the object-based evaluation show that the proposed technique is successful for counting nuclei in 3D.

show abstract

Cell Counting by Regression Using Convolutional Neural Network

Cited by 68 publications

References 20 publications

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

SAU-Net

Nuclei counting in microscopy images with three dimensional generative adversarial networks

Contact Info

Product

Resources

About