Cell detection in pathology and microscopy images with multi-scale fully convolutional neural networks

Pan, Xipeng; Yang, Dengxian; Li, Lingqiao; Liu, Zhenbing; Yang, Huihua; Cao, Zhiwei; He, Yubei; Ma, Zhen; Chen, Yiyi

doi:10.1007/s11280-017-0520-7

Cited by 34 publications

(20 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cohen et al proposed to count cells by redundant counting [6] and improved the performance further. On the predicted density map, cells can be located by finding the local maxima or applying the non-maxima suppression algorithm [7][8][9]. Zhu et al took the fully convolutional network (FCN) as the backbone and found the local maxima beyond the threshold on predicted density maps, the detection result was regarded as the counting results [10].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Cell Counting Framework Based on Random Forest and Density Map

2020

Applied Sciences

View full text Add to dashboard Cite

Cell counting is a fundamental part of biomedical and pathological research. Predicting a density map is the mainstream method to count cells. As an easy-trained and well-generalized model, the random forest is often used to learn the cell images and predict the density maps. However, it cannot predict the data that are beyond the training data, which may result in underestimation. To overcome this problem, we propose a cell counting framework to predict the density map by detecting cells. The cell counting framework contains two parts: the training data preparation and the detection framework. The former makes sure that the cells can be detected even when overlapping, and the latter makes sure the count result accurate and robust. The proposed method uses multiple random forests to predict various probability maps where the cells can be detected by Hessian matrix. Take all the detection results into consideration to get the density map and achieve better performance. We conducted experiments on three public cell datasets. Experimental results showed that the proposed model performs better than the traditional random forest (RF) in terms of accuracy and robustness, and even superior to some state-of-the-art deep learning models. Especially when the training data are small, which is the usual case in cell counting, the count errors on VGG cells, and MBM cells were decreased from 3.4 to 2.9, from 11.3 to 9.3, respectively. The proposed model can obtain the lowest count error and achieves state-of-the-art.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We defined a probability map to describe the cell locations. Compared to the maps generated by the Gaussian function [4,8] or distance function [7], training data are more balanced and the proposed probability map can better distinguish the cell centroids.…”

mentioning

confidence: 99%

A Cell Counting Framework Based on Random Forest and Density Map

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In recent years, systematic comparison of the performance of cell trackers has shown that convolutional neural networks outperform rule-based approaches in accuracy of cell detection [11]. Convolutional neural networks have already been used successfully for microscopy cell images in 2D [12][13][14][15][16] as well as in 3D [17][18][19]. Therefore, we decided to use convolutional neural networks as a basis for developing an approach to track most, if not all individual cells in time-lapse movies of growing organoids.…”

Section: Introductionmentioning

confidence: 99%

OrganoidTracker: efficient cell tracking using machine learning and manual error correction

Kok

Hebert

Huelsz-Prince

et al. 2020

Preprint

View full text Add to dashboard Cite

Time-lapse microscopy is routinely used to follow cells within organoids, allowing direct study of division and differentiation patterns. There is an increasing interest in cell tracking in organoids, which makes it possible to study their growth and homeostasis at the single-cell level. As tracking these cells by hand is prohibitively time consuming, automation using a computer program is required. Unfortunately, organoids have a high cell density and fast cell movement, which makes automated cell tracking difficult. In this work, a semi-automated cell tracker has been developed. To detect the nuclei, we use a machine learning approach based on a convolutional neural network. To form cell trajectories, we link detections at different time points together using a min-cost flow solver. The tracker raises warnings for situations with likely errors. Rapid changes in nucleus volume and position are reported for manual review, as well as cases where nuclei divide, appear and disappear. When the warning system is adjusted such that virtually error-free lineage trees can be obtained, still less than 2% of all detected nuclei positions are marked for manual analysis. This provides an enormous speed boost over manual cell tracking, while still providing tracking data of the same quality as manual tracking.

show abstract

“…The defogged images are widely applied for many scenes, such as traffic monitoring [6], remote sensing image correction [7], underwater detection [8], and medical image detection [9].…”

Section: Introductionmentioning

confidence: 99%

Retinex-Based Laplacian Pyramid Method for Image Defogging

et al. 2019

View full text Add to dashboard Cite

To address the problem that the retinex algorithm cannot effectively enhance color and detail simultaneously, we propose a retinex-based laplacian pyramid method for image defogging. The method is implemented via MSRCR and laplacian pyramid, and it doesn't require additional hardware devices. The overall defogging process is composed of three vital parts: illumination color enhancement, detail of reflection component enhancement, and linear weighted fusion. Firstly, we add the gamma correction illumination back to reflection to achieve color enhancement. And then, the detail enhancement is achieved by the laplacian pyramid to process the reflection component. Finally, the detail enhanced image and color corrected image are used to reconstruct the clear image. Comparing with the state-of-the-art image defogging methods, the experimental results have shown that the contrast of defogged images can be effectively improved by the proposed method, and with better effects on both subjective and objective results. The contrast of images can be enhanced by the proposed method. Meanwhile, sufficient details can be preserved. Therefore, the proposed method is an effective image defogging method.

show abstract

Cell detection in pathology and microscopy images with multi-scale fully convolutional neural networks

Cited by 34 publications

References 42 publications

A Cell Counting Framework Based on Random Forest and Density Map

A Cell Counting Framework Based on Random Forest and Density Map

OrganoidTracker: efficient cell tracking using machine learning and manual error correction

Retinex-Based Laplacian Pyramid Method for Image Defogging

Contact Info

Product

Resources

About