Glomerulus Classification and Detection Based on Convolutional Neural Networks

Gallego, Jaime; Pedraza, Aníbal; López, Samuel González; Steiner, Georg; González, Lucía Castañeda; Laurinavičius, Arvydas; Bueno, Gloria

doi:10.3390/jimaging4010020

Cited by 80 publications

(68 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The task we consider in this paper is glomerulus classification, which aims to classify whether an image patch contains a glomerulus or not. This task has also been studied in a recent work [10]. We ask the doctors to manually label the image patches.…”

Section: Experimental Settingsmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Experimental Settingsmentioning

confidence: 99%

“…Bound of objective function's norm: C o . 8 Initialize θ 0 randomly 9 for t ∈ [T ] do 10 Take a subset B t of patients with sampling ration p…”

mentioning

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

show abstract

“…For most glomeruli, it is difficult to find their perfect occurrences in all four stains, thus we cannot expect a simple algorithm to learn from correspondence across different stains. This partly limits previous work (Gallego et al 2018) from training classification models on multiple stains.…”

Section: Introductionmentioning

confidence: 88%

G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification

Zhang²,

Zhao³

et al. 2019

AAAI

View full text Add to dashboard Cite

Pathological glomerulus classification plays a key role in the diagnosis of nephropathy. As the difference between different subcategories is subtle, doctors often refer to slides from different staining methods to make decisions. However, creating correspondence across various stains is labor-intensive, bringing major difficulties in collecting data and training a vision-based algorithm to assist nephropathy diagnosis. This paper provides an alternative solution for integrating multi-stained visual cues for glomerulus classification. Our approach, named generator-to-classifier (G2C), is a twostage framework. Given an input image from a specified stain, several generators are first applied to estimate its appearances in other staining methods, and a classifier follows to combine visual cues from different stains for prediction (whether it is pathological, or which type of pathology it has). We optimize these two stages in a joint manner. To provide a reasonable initialization, we pre-train the generators in an unlabeled reference set under an unpaired image-to-image translation task, and then fine-tune them together with the classifier. We conduct experiments on a glomerulus type classification dataset collected by ourselves (there are no publicly available datasets for this purpose). Although joint optimization slightly harms the authenticity of the generated patches, it boosts classification performance, suggesting more effective visual cues are extracted in an automatic way. We also transfer our model to a public dataset for breast cancer classification, and outperform the state-of-the-arts significantly.

show abstract

“…It is hypothesised that since histopathological slides of the same staining exhibit very low colour variance when com-pared to natural images, a deep learning approach will rapidly learn to rely upon structures being present in specific channels (or combinations thereof), which may limit the network's ability to generalise to unseen stainings. The effects of this are already known when dealing with inter-laboratory variance of the same staining [13,14].…”

Section: Training Strategiesmentioning

confidence: 98%

Strategies for Training Stain Invariant CNNS

Lampert

Merveille

Schmitz

et al. 2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

View full text Add to dashboard Cite

An important part of Digital Pathology is the analysis of multiple digitised whole slide images from differently stained tissue sections. It is common practice to mount consecutive sections containing corresponding microscopic structures on glass slides, and to stain them differently to highlight specific tissue components. These multiple staining modalities result in very different images but include a significant amount of consistent image information. Deep learning approaches have recently been proposed to analyse these images in order to automatically identify objects of interest for pathologists. These supervised approaches require a vast amount of annotations, which are difficult and expensive to acquire-a problem that is multiplied with multiple stainings. This article presents several training strategies that make progress towards stain invariant networks. By training the network on one commonly used staining modality and applying it to images that include corresponding but differently stained tissue structures, the presented unsupervised strategies demonstrate significant improvements over standard training strategies.

show abstract

Glomerulus Classification and Detection Based on Convolutional Neural Networks

Cited by 80 publications

References 29 publications

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

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

G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification

Strategies for Training Stain Invariant CNNS

Contact Info

Product

Resources

About