A Fast and Scalable Pipeline for Stain Normalization of Whole-Slide Images in Histopathology

Stanisavljević, Miloš; Anghel, Andreea; Παπανδρεου, Νικολαοσ; Andani, Sonali; Pati, Pushpak; Rüschoff, Jan H.; Wild, Peter J.; Gabrani, Maria; Pozidis, Haralampos

doi:10.1007/978-3-030-11024-6_32

Cited by 9 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We begin with normalizing the H&E stained images using color deconvolution [18] to reduce the variability due to tissue preparation and imaging techniques. Since in H&E staining, nuclei possess higher blue channel intensity, we convert RGB images into blue-ratio images [19] and identify potential nuclei locations by detecting high brightness objects in them.…”

Section: Methodsmentioning

confidence: 99%

Mitosis Detection Under Limited Annotation: A Joint Learning Approach

Pati

Foncubierta–Rodríguez

Göksel

et al. 2020

2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)

Self Cite

View full text Add to dashboard Cite

Mitotic counting is a vital prognostic marker of tumor proliferation in breast cancer. Deep learning-based mitotic detection is on par with pathologists, but it requires large labeled data for training. We propose a deep classification framework for enhancing mitosis detection by leveraging class label information, via softmax loss, and spatial distribution information among samples, via distance metric learning. We also investigate strategies towards steadily providing informative samples to boost the learning. The efficacy of the proposed framework is established through evaluation on ICPR 2012 and AMIDA 2013 mitotic data. Our framework significantly improves the detection with small training data and achieves on par or superior performance compared to state-of-the-art methods for using the entire training data.

show abstract

Section: Methodsmentioning

confidence: 99%

Mitosis Detection Under Limited Annotation: A Joint Learning Approach

Pati

Foncubierta–Rodríguez

Göksel

et al. 2020

2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Before describing the run-time optimizations, we present an algorithm enhancement that we have introduced in our optimized stain normalization implementation (the processing block A in Figure 4) in addition to what we have previously presented in Stanisavljevic et al (14). This first processing step automatically calculates the threshold based on which the pixels with low optical density are removed in Step 2 of Algorithm 1.…”

Section: Optimized Stain Normalization Of Whole-slide Images (Fast_sn)mentioning

confidence: 99%

“…A good sampling rate that we use in this paper is 1%. This rate was found by computing the Euclidean distance of the OD matrix and the relative error of the robust maximum of the individual stain concentrations (max C h and max C e ) between the sampling (with different sampling rates) and no-sampling results (14).…”

Section: Optimized Stain Normalization Of Whole-slide Images (Fast_sn)mentioning

confidence: 99%

“…When using pixel sampling, it is important to define metrics that quantify the impact of using only a part of the available pixels on the quality of the normalization. In our work, we used the Euclidean distance of the H&E vectors and the relative error of the robust maximum of the individual stain concentrations (max C h and max C e ) between the sampling (with different sampling rates) and no-sampling results (14).…”

Section: High-performance Stain Normalization Systemmentioning

confidence: 99%

“…Our stain normalization system architecture is based on an optimized multi-core implementation that integrates multiple system-level optimizations (14) 1 . With this architecture we 1 The content of sections 3.1 and 3.2 of this journal article is partially based on results from our previously published workshop paper (14). This journal paper includes new material as follows: (a) the optimized stain normalization system presented in Stanisavljevic et al (14) is enhanced with automatic detection of the background pixels threshold; (b) we report the run-time of the optimized system and the speedup gains over the baseline implementation using a larger set of 175 images; (c) we identify a new challenge of the stain normalization algorithm, namely its sensitivity to the quality of the input images, and propose a method to deal with low-quality input images; (d) we evaluate the benefits of the new method address two challenges of the stain normalization algorithm: (1) long processing time, and (2) large system memory consumption, when normalizing high-resolution images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A High-Performance System for Robust Stain Normalization of Whole-Slide Images in Histopathology

et al. 2019

Self Cite

View full text Add to dashboard Cite

Stain normalization is an important processing task for computer-aided diagnosis (CAD) systems in modern digital pathology. This task reduces the color and intensity variations present in stained images from different laboratories. Consequently, stain normalization typically increases the prediction accuracy of CAD systems. However, there are computational challenges that this normalization step must overcome, especially for real-time applications: the memory and run-time bottlenecks associated with the processing of images in high resolution, e.g., 40X. Moreover, stain normalization can be sensitive to the quality of the input images, e.g., when they contain stain spots or dirt. In this case, the algorithm may fail to accurately estimate the stain vectors. We present a high-performance system for stain normalization using a state-of-the-art unsupervised method based on stain-vector estimation. Using a highly-optimized normalization engine, our architecture enables high-speed and large-scale processing of high-resolution whole-slide images. This optimized engine integrates an automated thresholding technique to determine the useful pixels and uses a novel pixel-sampling method that significantly reduces the processing time of the normalization algorithm. We demonstrate the performance of our architecture using measurements from images of different sizes and scanner formats that belong to four different datasets. The results show that our optimizations achieve up to 58x speedup compared to a baseline implementation. We also prove the scalability of our system by showing that the processing time scales almost linearly with the amount of tissue pixels present in the image. Furthermore, we show that the output of the normalization algorithm can be adversely affected when the input images include artifacts. To address this issue, we enhance the stain normalization pipeline by introducing a parameter cross-checking technique that automatically detects the distortion of the algorithm's critical parameters. To assess the robustness of the proposed method we employ a machine learning (ML) pipeline that classifies images for detection of prostate cancer. The results show that the enhanced normalization algorithm increases the classification accuracy of the ML pipeline in the presence of poor-quality input images. For an exemplary ML pipeline, our new method increases the accuracy on an unseen dataset from 0.79 to 0.87.

show abstract

Breast histopathological image analysis using image processing techniques for diagnostic purposes: A methodological review

2021

View full text Add to dashboard Cite

Breast cancer in women is the second most common cancer worldwide. Early detection of breast cancer can reduce the risk of human life. Non-invasive techniques such as mammograms and ultrasound imaging are popularly used to detect the tumour. However, histopathological analysis is necessary to determine the malignancy of the tumour as it analyses the image at the cellular level. Manual analysis of these slides is time consuming, tedious, subjective and are susceptible to human errors. Also, at times the interpretation of these images are inconsistent between laboratories. Hence, a Computer-Aided Diagnostic system that can act as a decision support system is need of the hour. Moreover, recent developments in computational power and memory capacity led to the application of computer tools and medical image processing techniques to process and analyze breast cancer histopathological images. This review paper summarizes various traditional and deep learning based methods developed to analyze breast cancer histopathological images. Initially, the characteristics of breast cancer histopathological images are discussed. A detailed discussion on the various potential regions of interest is presented which is crucial for the development of Computer-Aided Diagnostic systems. We summarize the recent trends and choices made during the selection of medical image processing techniques. Finally, a detailed discussion on the various challenges involved in the analysis of BCHI is presented along with the future scope.

show abstract

A Fast and Scalable Pipeline for Stain Normalization of Whole-Slide Images in Histopathology

Cited by 9 publications

References 15 publications

Mitosis Detection Under Limited Annotation: A Joint Learning Approach

Mitosis Detection Under Limited Annotation: A Joint Learning Approach

A High-Performance System for Robust Stain Normalization of Whole-Slide Images in Histopathology

Breast histopathological image analysis using image processing techniques for diagnostic purposes: A methodological review

Contact Info

Product

Resources

About