Nuclei segmentation in histopathology images using deep neural networks

Naylor, Peter; Laé, Marick; Reyal, Fabien; Walter, Thomas

doi:10.1109/isbi.2017.7950669

Cited by 157 publications

(93 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this experiment, only Figure 9 shows the visual comparison between our algorithm and algorithm in [9] in terms of segmentation results. At last, we follow the same strategy in [21] to validate our method. The strategy is called leave-one-patient-out cross-validation.…”

Section: B Experiments Resultsmentioning

confidence: 99%

See 1 more Smart Citation

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

Cui

Zhang

Liu

et al. 2019

Med Biol Eng Comput

131

View full text Add to dashboard Cite

This paper addresses the task of nuclei segmentation in high-resolution histopathological images. We propose an automatic end-to-end deep neural network algorithm for segmentation of individual nuclei. A nucleus-boundary model is introduced to predict nuclei and their boundaries simultaneously using a fully convolutional neural network. Given a color normalized image, the model directly outputs an estimated nuclei map and a boundary map. A simple, fast and parameter-free post-processing procedure is performed on the estimated nuclei map to produce the final segmented nuclei. An overlapped patch extraction and assembling method is also designed for seamless prediction of nuclei in large whole-slide images. We also show the effectiveness of data augmentation methods for nuclei segmentation task. Our experiments showed our method outperforms prior state-of-theart methods. Moreover, it is efficient that one 1000X1000 image can be segmented in less than 5 seconds. This makes it possible to precisely segment the whole-slide image in acceptable time.

show abstract

Section: B Experiments Resultsmentioning

confidence: 99%

“…Current deep learning methods for nuclei segmentation usually need complex post-processing procedure to obtain the final nuclei boundries. Naylor [21] employs FCN to discriminate the nuclei from background and then applies the watershed method to split the nuclei. However the resulting boundaries are not accurate.…”

Section: Introductionmentioning

confidence: 99%

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

Cui

Zhang

Liu

et al. 2019

Med Biol Eng Comput

131

View full text Add to dashboard Cite

show abstract

“…In recent years, deep CNNs have emerged as powerful tools for various pathological image analysis tasks, such as * Work performed while interning at IBM Research -China. tissue classification [30,10], lesion detection [17,22], nuclei segmentation [38,50,26], etc. The superior performance of deep CNNs usually relies on large amounts of labeled training data [40].…”

Section: Introductionmentioning

confidence: 99%

P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification

Zhao²,

Sun

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Recently, deep convolutional neural networks (CNNs) have achieved great success in pathological image classification. However, due to the limited number of labeled pathological images, there are still two challenges to be addressed: (1) overfitting: the performance of a CNN model is undermined by the overfitting due to its huge amounts of parameters and the insufficiency of labeled training data.(2) privacy leakage: the model trained using a conventional method may involuntarily reveal the private information of the patients in the training dataset. The smaller the dataset, the worse the privacy leakage.To tackle the above two challenges, we introduce a novel stochastic gradient descent (SGD) scheme, named patient privacy preserving SGD (P3SGD), which performs the model update of the SGD in the patient level via a large-step update built upon each patient's data. Specifically, to protect privacy and regularize the CNN model, we propose to inject the well-designed noise into the updates. Moreover, we equip our P3SGD with an elaborated strategy to adaptively control the scale of the injected noise. To validate the effectiveness of P3SGD, we perform extensive experiments on a real-world clinical dataset and quantitatively demonstrate the superior ability of P3SGD in reducing the risk of overfitting. We also provide a rigorous analysis of the privacy cost under differential privacy. Additionally, we find that the models trained with P3SGD are resistant to the model-inversion attack compared with those trained using non-private SGD.

show abstract

“…While in more industrial applications (see (Grigorescu et al, 2019)for an overview of autonomous driving) a large amount of training data can be collected relatively easily: see the cityscapes dataset (Cordts et al, 2016) (available at https://www.cityscapes-dataset.com/ ) of traffic video frames using a car and camera to record and potentially non-expert individuals to label the objects, clinical data is considerably more difficult, due to ethical constraints, and expensive to gather as expert annotation is required. Datasets available in the public domain such as BBBC (Ljosa et al, 2012) at https://data.broadinstitute.org/bbbc/ , TNBC (Naylor et al, 2017(Naylor et al, , 2019 or TCGA (Cancer Genome Atlas Research Network, 2008;Kumar et al, 2017) and detection challenges including ISBI (Coelho et al, 2009), Kaggle ( https://www.kaggle.com/ ), ImageNet (Russakovsky et al, 2015) etc. contribute to the development of genuinely useful DL methods; however, most of them lack heterogeneity of the covered domains and are limited in data size.…”

Section: Introductionmentioning

confidence: 99%

AnnotatorJ: an ImageJ plugin to ease hand-annotation of cellular compartments

Hollandi

Horváth

2020

Preprint

View full text Add to dashboard Cite

When single-cell identification and deep learning meet, AnnotatorJ arises. Cellular analysis quality depends on accurate and reliable detection and segmentation of cells so that the subsequent steps of analyses e.g. expression measurements may be carried out precisely and without bias. Deep learning has recently become a popular way of segmenting cells, performing unimaginably better than conventional methods. However, such deep learning applications may be trained on a large amount of annotated data to be able to match the highest expectations. High-quality annotations are unfortunately expensive as they require field experts to create them, and often cannot be shared outside the lab due to medical regulations.We propose AnnotatorJ, an ImageJ plugin for the semi-automatic annotation of cells (or generally, objects of interest) on (not only) microscopy images that helps find the true contour of individual objects by applying U-Net pre-segmentation. The manual labour of hand-annotating cells can be significantly accelerated by using our tool. Thus, it enables users to create such datasets that could potentially increase the accuracy of state-of-the-art solutions, deep learning or otherwise, when used as training data.

show abstract

Nuclei segmentation in histopathology images using deep neural networks

Cited by 157 publications

References 9 publications

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

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

P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification

AnnotatorJ: an ImageJ plugin to ease hand-annotation of cellular compartments

Contact Info

Product

Resources

About