Analysis of Image Feature Characteristics for Automated Scoring of HER2 in Histology Slides

Mukundan, Ramakrishnan

doi:10.3390/jimaging5030035

Cited by 25 publications

(22 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among primary colors, blue hue is the most discriminative for brown color 61 . Therefore, the blue hue was discriminative for NeuN and anti-Phox2B (two brown stainings), which was coherent with previous works 62 .…”

Section: Part Iii: Discussionsupporting

confidence: 91%

Reduced and stable feature sets selection with random forest for neurons segmentation in histological images of macaque brain

Bouvier

Souedet

Lévy

et al. 2021

Sci Rep

View full text Add to dashboard Cite

In preclinical research, histology images are produced using powerful optical microscopes to digitize entire sections at cell scale. Quantification of stained tissue relies on machine learning driven segmentation. However, such methods require multiple additional information, or features, which are increasing the quantity of data to process. As a result, the quantity of features to deal with represents a drawback to process large series or massive histological images rapidly in a robust manner. Existing feature selection methods can reduce the amount of required information but the selected subsets lack reproducibility. We propose a novel methodology operating on high performance computing (HPC) infrastructures and aiming at finding small and stable sets of features for fast and robust segmentation of high-resolution histological images. This selection has two steps: (1) selection at features families scale (an intermediate pool of features, between spaces and individual features) and (2) feature selection performed on pre-selected features families. We show that the selected sets of features are stables for two different neuron staining. In order to test different configurations, one of these dataset is a mono-subject dataset and the other is a multi-subjects dataset to test different configurations. Furthermore, the feature selection results in a significant reduction of computation time and memory cost. This methodology will allow exhaustive histological studies at a high-resolution scale on HPC infrastructures for both preclinical and clinical research.

show abstract

Section: Part Iii: Discussionsupporting

confidence: 91%

Reduced and stable feature sets selection with random forest for neurons segmentation in histological images of macaque brain

Bouvier

Souedet

Lévy

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In the past, some of the works mainly employ approximations of area proportion of staining area as a measurement of scoring [5,6,7]. Recently, the characteristic curve defined for the stained area is used for some of the work to distinguish the different levels of staining, and therefore predict the HER2 scores(some machine learning classification algorithms may use for extracting features from characteristics curves) [8,9]. However, these methods use disparate scoring rules in comparison with the HER2 scoring guidelines, such that it is unreasonable for clinical application.…”

Section: Introductionmentioning

confidence: 99%

Automated Scoring System of HER2 in Pathological Images under the Microscope

Zhang¹,

Wang²,

Wang³

2021

Preprint

View full text Add to dashboard Cite

Breast cancer is the most common cancer among women worldwide. The human epidermal growth factor receptor 2(HER2) with immunohistochemical(IHC) is widely used for pathological evaluation to provide the appropriate therapy for patients with breast cancer. However, the deficiency of pathologists is extremely significant in the current society, and visual diagnosis of the HER2 overexpression is subjective and susceptible to inter-observer variation. Recently, with the rapid development of artificial intelligence(AI) in disease diagnosis, several automated HER2 scoring methods using traditional computer vision or machine learning methods indicate the improvement of the HER2 diagnostic accuracy, but the unreasonable interpretation in pathology, as well as the expensive and ethical issues for annotation, make these methods still have a long way to deploy in hospitals to ease pathologists' burden in real. In this paper, we propose a HER2 automated scoring system that strictly follows the HER2 scoring guidelines simulating the real workflow of HER2 scores diagnosis by pathologists. Unlike the previous work, our method takes the positive control of HER2 into account to make sure the assay performance for each slide, eliminating work for repeated comparison and checking for the current field of view(FOV) and positive control FOV, especially for the borderline cases. Besides, for each selected FOV under the microscope, our system provides real-time HER2 scores analysis and visualizations of the membrane staining intensity and completeness corresponding with the cell classification. Our rigorous workflow along with the flexible interactive adjustion in demand substantially assists pathologists to finish the HER2 diagnosis faster and improves the robustness and accuracy. The proposed system will be embedded in our Thorough Eye ® platform for deployment in hospitals.

show abstract

“…Other researchers tried to detect HER2 from HER2 stained digital slides, using ML or not ML methods [ 29 , 30 , 31 , 32 , 33 , 34 ]; we do not detail their methodology, since they are out of scope for this work.…”

Section: Introductionmentioning

confidence: 99%

Detection of HER2 from Haematoxylin-Eosin Slides Through a Cascade of Deep Learning Classifiers via Multi-Instance Learning

et al. 2020

View full text Add to dashboard Cite

Breast cancer is the most frequently diagnosed cancer in woman. The correct identification of the HER2 receptor is a matter of major importance when dealing with breast cancer: an over-expression of HER2 is associated with aggressive clinical behaviour; moreover, HER2 targeted therapy results in a significant improvement in the overall survival rate. In this work, we employ a pipeline based on a cascade of deep neural network classifiers and multi-instance learning to detect the presence of HER2 from Haematoxylin–Eosin slides, which partly mimics the pathologist’s behaviour by first recognizing cancer and then evaluating HER2. Our results show that the proposed system presents a good overall effectiveness. Furthermore, the system design is prone to further improvements that can be easily deployed in order to increase the effectiveness score.

show abstract

Analysis of Image Feature Characteristics for Automated Scoring of HER2 in Histology Slides

Cited by 25 publications

References 30 publications

Reduced and stable feature sets selection with random forest for neurons segmentation in histological images of macaque brain

Reduced and stable feature sets selection with random forest for neurons segmentation in histological images of macaque brain

Automated Scoring System of HER2 in Pathological Images under the Microscope

Detection of HER2 from Haematoxylin-Eosin Slides Through a Cascade of Deep Learning Classifiers via Multi-Instance Learning

Contact Info

Product

Resources

About