Cell Tracking with Deep Learning for Cell Detection and Motion Estimation in Low-Frame-Rate

Hayashida, Junya; Bise, Ryoma

doi:10.1007/978-3-030-32239-7_44

Cited by 26 publications

(31 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These estimated coordinates are subsequently used to find the parent of the nucleus at the previous timepoint by the nearest neighbor algorithm (a similar concept was introduced for 2D phase contrast microscopy data; (Hayashida & Bise, 2019;Hayashida, Nishimura, & Bise, 2020)). The pairs with a distance smaller than are considered as link candidates, where the closer the Euclidean distance between the two points, the higher their priority of being the correct link.…”

Section: Algorithm For Detectionmentioning

confidence: 99%

Tracking cell lineages in 3D by incremental deep learning

Sugawara

Çevrim

Averof

2021

Preprint

View full text Add to dashboard Cite

Deep learning is emerging as a powerful approach for bioimage analysis, but its wider use is limited by the scarcity of annotated data for training. We present ELEPHANT, an interactive platform for cell tracking in 4D that seamlessly integrates annotation, deep learning, and proofreading. ELEPHANT's user interface supports cycles of incremental learning starting from sparse annotations, yielding accurate, user-validated cell lineages with a modest investment in time and effort.

show abstract

Section: Algorithm For Detectionmentioning

confidence: 99%

Tracking cell lineages in 3D by incremental deep learning

Sugawara

Çevrim

Averof

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning-based methods, i.e. Convolutional Neural Networks (CNNs) have shown a great potential in medical imaging and archived state-of-the-art performance to solve challenging tasks such as detection, 6 classification, 7 tracking, 8 and segmentation. [9][10][11][12][13] Although deep neural networks have become a dominant method and archived high accuracy close to human performance for many computer vision tasks on 2D images, it is still challenging and limited when applying to medical tasks on volumetric data, such as volumetric segmentation, due to the limited amount of labelled data as well as the limited computational resources for training the model.…”

Section: Introductionmentioning

confidence: 99%

Invertible Residual Network with Regularization for Effective Medical Image Segmentation

Yamazaki,

Rathour,

2021

Preprint

View full text Add to dashboard Cite

Deep Convolutional Neural Networks (CNNs) i.e. Residual Networks (ResNets) have been used successfully for many computer vision tasks, but are difficult to scale to 3D volumetric medical data. Memory is increasingly often the bottleneck when training 3D Convolutional Neural Networks (CNNs). Recently, invertible neural networks have been applied to significantly reduce activation memory footprint when training neural networks with backpropagation thanks to the invertible functions that allow retrieving input from its output without storing intermediate activations in memory to perform the backpropagation. Among many successful network architectures, 3D Unet 1 has been established as a standard architecture for volumetric medical segmentation. Thus, we choose 3D Unet as a baseline for a non-invertible network and we then extend it with the invertible residual network. In this paper, we proposed two versions of invertible Residual Network, namely Partially Invertible Residual Network (Partially-InvRes) and Fully Invertible Residual Network (Fully-InvRes). In Partially-InvRes, the invertible residual layer is defined by a technique called additive coupling 2 whereas in Fully-InvRes, both invertible upsampling and downsampling operations are learned based on squeezing (known as pixel shuffle). 3 Furthermore, to avoid the overfitting problem because of less training data, a variational auto-encoder (VAE) branch is added to reconstruct the input volumetric data itself. Our results indicate that by using partially/fully invertible networks as the central workhorse in volumetric segmentation, we not only reduce memory overhead but also achieve compatible segmentation performance compared against the non-invertible 3D Unet. We have demonstrated the proposed networks on various volumetric datasets such as iSeg 2019 4 and BraTS 2020. 5 .

show abstract

“…These methods tend to have poor generalization ability and necessitate tuning numerous parameters. Several methods have been proposed to adopt deep learning approaches in cell tracking task [7][8][9][10][11][12][13]. In [7], a motion model and a classification neural network were combined for cell tracking.…”

Section: Introductionmentioning

confidence: 99%

“…In [7], a motion model and a classification neural network were combined for cell tracking. [8] and [9] attempted to achieve joint cell detection and tracking by predicting cell position likelihood and motion map with a neural network, but they were unable to generate segmentation masks. [10], [11] and [12] used deep learning techniques for both cell segmentation and tracking but these processes were executed in sequence with two neural networks trained separately.…”

Section: Introductionmentioning

confidence: 99%

CellTrack R-CNN: A Novel End-To-End Deep Neural Network for Cell Segmentation and Tracking in Microscopy Images

Chen

Song

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Cell segmentation and tracking in microscopy images are of great significance to new discoveries in biology and medicine. In this study, we propose a novel approach to combine cell segmentation and cell tracking into a unified end-to-end deep learning based framework, where cell detection and segmentation are performed with a current instance segmentation pipeline and cell tracking is implemented by integrating Siamese Network with the pipeline. Besides, tracking performance is improved by incorporating spatial information into the network and fusing spatial and visual prediction. Our approach was evaluated on the DeepCell benchmark dataset. Despite being simple and efficient, our method outperforms state-of-the-art algorithms in terms of both cell segmentation and cell tracking accuracies.

show abstract

Cell Tracking with Deep Learning for Cell Detection and Motion Estimation in Low-Frame-Rate

Cited by 26 publications

References 10 publications

Tracking cell lineages in 3D by incremental deep learning

Tracking cell lineages in 3D by incremental deep learning

Invertible Residual Network with Regularization for Effective Medical Image Segmentation

CellTrack R-CNN: A Novel End-To-End Deep Neural Network for Cell Segmentation and Tracking in Microscopy Images

Contact Info

Product

Resources

About