Structure-preserved color normalization for histological images

Vahadane, Abhishek; Peng, Tingying; Albarqouni, Shadi; Baust, Maximilian; Steiger, Katja; Schlitter, Anna Melissa; Sethi, Amit; Espósito, Irene; Navab, Nassir

doi:10.1109/isbi.2015.7164042

Cited by 81 publications

(61 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But in practice, the color of H&E stained images could vary a lot due to variation in the H&E reagents, staining process, scanner and the specialist who performs the staining, as shown in Fig.1. A few H&E stain normalization methods [23,24,25] have been proposed to eliminate the negative interference caused by color variation. We tried two of them [23,25] to normalize the raw H&E stained images.…”

Section: B Data Preprocessingmentioning

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

132

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 Data Preprocessingmentioning

confidence: 99%

“…A few H&E stain normalization methods [23,24,25] have been proposed to eliminate the negative interference caused by color variation. We tried two of them [23,25] to normalize the raw H&E stained images. For our segmentation algorithm, we did not find any considerable difference between these two normalization methods.…”

Section: B Data Preprocessingmentioning

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

132

View full text Add to dashboard Cite

show abstract

“…Consequently, stain normalization is essential as a pre-processing step, prior to conducting any analyses using histology images. Various strategies [9], [10] have been proposed for stain normalization in histological images. In this paper, we used the approach proposed by Reinhard et al [11] which matches the statistics of color histograms of a source and target image, following transformation of the RGB images to the de-correlated LAB color space.…”

Section: Stain Normalizationmentioning

confidence: 99%

Classification of Breast Cancer Histology Images Using Transfer Learning

Vesal

Ravikumar

Davari

et al. 2018

Lecture Notes in Computer Science

108

View full text Add to dashboard Cite

Breast cancer is one of the leading causes of mortality in women. Early detection and treatment are imperative for improving survival rates, which have steadily increased in recent years as a result of more sophisticated computer-aided-diagnosis (CAD) systems. A critical component of breast cancer diagnosis relies on histopathology, a laborious and highly subjective process. Consequently, CAD systems are essential to reduce inter-rater variability and supplement the analyses conducted by specialists. In this paper, a transfer-learning based approach is proposed, for the task of breast histology image classification into four tissue sub-types, namely, normal, benign, in situ carcinoma and invasive carcinoma. The histology images, provided as part of the BACH 2018 grand challenge, were first normalized to correct for color variations resulting from inconsistencies during slide preparation. Subsequently, image patches were extracted and used to fine-tune Google's Inception-V3 and ResNet50 convolutional neural networks (CNNs), both pre-trained on the ImageNet database, enabling them to learn domain-specific features, necessary to classify the histology images. The ResNet50 network (based on residual learning) achieved a test classification accuracy of 97.50% for four classes, outperforming the Inception-V3 network which achieved an accuracy of 91.25%.

show abstract

“…These variations makes it difficult for software trained on a particular stain appearance [23] therefore necessitates careful preprocessing to reduce such variances. Many methods have been proposed for stain normalization including [23], [7], [8] that are based on color devolution where RGB pixel values are decomposed into their stain-specific basis vectors. In addition to color information, Bejnordi et el.…”

Section: Image-wise Classification Of Microscopy Imagesmentioning

confidence: 99%

“…In our framework, we utilized both Macenko [7], which used singular value decomposition (SVD), and Vahadane normalizations [8], which used sparse nonnegative matrix factorization (SNMF), as part of our ensemble framework. This was due to the fact that initial empirical results showed Macenko-normalized images obtained high sensitivity for invasive and in situ classes whereas Vahadanenormalized images showed high sensitivity for benign and normal classes.…”

Section: Image-wise Classification Of Microscopy Imagesmentioning

confidence: 99%

Deep Learning Framework for Multi-class Breast Cancer Histology Image Classification

Vang

Chen

Xie

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this work, we present a deep learning framework for multiclass breast cancer image classification as our submission to the International Conference on Image Analysis and Recognition (ICIAR) 2018 Grand Challenge on BreAst Cancer Histology images (BACH). As these histology images are too large to fit into GPU memory, we first propose using Inception V3 to perform patch level classification. The patch level predictions are then passed through an ensemble fusion framework involving majority voting, gradient boosting machine (GBM), and logistic regression to obtain the image level prediction. We improve the sensitivity of the Normal and Benign predicted classes by designing a Dual Path Network (DPN) to be used as a feature extractor where these extracted features are further sent to a second layer of ensemble prediction fusion using GBM, logistic regression, and support vector machine (SVM) to refine predictions. Experimental results demonstrate our framework shows a 12.5% improvement over the state-of-the-art model.

show abstract

Structure-preserved color normalization for histological images

Cited by 81 publications

References 7 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

Classification of Breast Cancer Histology Images Using Transfer Learning

Deep Learning Framework for Multi-class Breast Cancer Histology Image Classification

Contact Info

Product

Resources

About