Evaluation of Deep Learning Topcoders Method for Neuron Individualization in Histological Macaque Brain Section*

  title={Evaluation of Deep Learning Topcoders Method for Neuron Individualization in Histological Macaque Brain Section*},
  author={Huaqian Wu and Nicolas Souedet and Zhenzhen You and Caroline Jan and C{\'e}dric Clouchoux and Thierry Delzescaux},
  journal={2021 43rd Annual International Conference of the IEEE Engineering in Medicine \& Biology Society (EMBC)},
  • Huaqian Wu, N. Souedet, T. Delzescaux
  • Published 1 November 2021
  • Computer Science
  • 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Cell individualization has a vital role in digital pathology image analysis. Deep Learning is considered as an efficient tool for instance segmentation tasks, including cell individualization. However, the precision of the Deep Learning model relies on massive unbiased dataset and manual pixel-level annotations, which is labor intensive. Moreover, most applications of Deep Learning have been developed for processing oncological data. To overcome these challenges, i) we established a pipeline to… 

Figures and Tables from this paper

A General Deep Learning framework for Neuron Instance Segmentation based on Efficient UNet and Morphological Post-processing

This work aims to develop a robust and efficient framework for analyzing neurons using optical microscopic data, which can be used in preclinical biological studies and, more specifically, in the context of neurodegenerative diseases.

End-to-end Neuron Instance Segmentation based on Weakly Supervised Efficient UNet and Morphological Post-processing

This paper presents an end-to-end weakly-supervised framework to automatically detect and segment NeuN stained neuronal cells on histological images using only point annotations and integrates the state-of-the-art network, EfficientNet, into the U-Net-like architecture.

Quantitative Evaluation of Inflammatory Markers in Peri-Implantitis and Periodontitis Tissues: Digital vs. Manual Analysis—A Proof of Concept Study

DC could be used as a reliable and time-saving procedure for the immunohistochemical analysis of PD and PI soft tissues and showed a satisfying concordance.



Nucleus segmentation across imaging experiments: the 2018 Data Science Bowl

The 2018 Data Science Bowl attracted 3,891 teams worldwide to make the first attempt to build a segmentation method that could be applied to any two-dimensional light microscopy image of stained nuclei across experiments, with no human interaction.

Automated Individualization of Size-Varying and Touching Neurons in Macaque Cerebral Microscopic Images

Qualitative and quantitative analyses demonstrate that the proposed adaptive multiscale procedure aiming at individualizing touching neurons in optical microscopy two-dimensional images provides satisfactory results in most regions and outperforms a baseline Watershed algorithm.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.

Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map

A new method to automatically segment nuclei from Haematoxylin and Eosin stained histopathology data with fully convolutional networks is described and superior performance is demonstrated as compared to other approaches using Convolutional Neural Networks.

U-Net: deep learning for cell counting, detection, and morphometry

An ImageJ plugin is presented that enables non-machine-learning experts to analyze their data with U-Net on either a local computer or a remote server/cloud service.

Unbiased stereological estimation of the total number of neurons in the subdivisions of the rat hippocampus using the optical fractionator

A stereological method for obtaining estimates of the total number of neurons in five major subdivisions of the rat hippocampus is described, and a number of new stereological methods that have particular relevance to the quantitative study of the structure of the nervous system are briefly described in an appendix.

A deep learning algorithm for one-step contour aware nuclei segmentation of histopathology images

An automatic end-to-end deep neural network algorithm for segmentation of individual nuclei using a nucleus-boundary model to predict nuclei and their boundaries simultaneously simultaneously using a fully convolutional neural network is proposed.

Dual Path Networks

This work reveals the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, and finds that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations.

A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology

A large publicly accessible data set of hematoxylin and eosin (H&E)-stained tissue images with more than 21000 painstakingly annotated nuclear boundaries is introduced, whose quality was validated by a medical doctor.

Densely Connected Convolutional Networks

The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.