Deep learning-based instance segmentation for the precise automated quantification of digital breast cancer immunohistochemistry images

Torres, Blanca Maria Priego; Lobato-Delgado, Barbara; Atienza-Cuevas, Lidia; Morillo, Daniel

doi:10.1016/j.eswa.2021.116471

Cited by 12 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study proposed a deep learning-based method for quantifying DAB staining in immunohistochemistry images and showed that the proposed method achieved high accuracy and efficiency. Another study, ”Deep learning-based instance segmentation for the precise automated quantification of digital breast cancer immunohistochemistry images” by [16], published in 2022 in the Journal of Expert Systems with Applications, also proposed a deep learning-based method for quantifying immunohistochemistry staining. The study reported that the proposed method achieved high accuracy and efficiency compared to manual measurements.…”

Section: Discussionmentioning

confidence: 99%

Unlocking the Power of R: A High-Accuracy Method for Measuring DAB Staining on Immunohistochemical Slides

Fares

Khenenou

Rahmoun

2023

Preprint

View full text Add to dashboard Cite

The current research aimed to establish a method for measuring the percentage of diaminobenzidine (DAB) staining on immunohistochemical slides with high accuracy and efficiency. The R programming language was utilized in this endeavor. A total of 50 slides were collected from various types of tissue, and were stained using an anti-cytokeratin antibody and the DAB detection method. These slides were then scanned using a high-resolution scanner, and the resulting images were analyzed using R, a custom script was specifically developed to segment the tissue and DAB-positive areas, and calculate the percentage of DAB staining on the slide. The results were then compared to manual measurements of DAB staining performed by a trained technician. The R-based method was found to be highly accurate, with a mean absolute error of only 0.76 % compared to manual measurements, this study provides evidence that the use of R for DAB quantification is a fast and reliable alternative to manual methods, enabling the analysis of large numbers of slides in a short period of time. It offers a valuable tool for researchers and technicians in the field of histopathology, enabling them to quickly and accurately analyze DAB staining on immunohistochemical slides, which is essential for the diagnosis and treatment of various diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Unlocking the Power of R: A High-Accuracy Method for Measuring DAB Staining on Immunohistochemical Slides

Fares

Khenenou

Rahmoun

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, there has been a significant body of work concerning the quantitative analysis of IHC-stained slides. Some studies [ 20 , 22 , 23 , 27 ] have focused on the detection or segmentation of tumor-positive and tumor-negative cells, yet they have not taken into account the automatic segmentation of IC regions. Yao et al [ 26 ] have approached IHC quantification by calculating grayscale features for each tile and generating WSI-level feature maps based on these characteristics, subsequently using these maps for HER2 grading.…”

Section: Discussionmentioning

confidence: 99%

“…Several studies have focused on immunohistochemical quantification [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 ], demonstrating high consistency with reference scores and the feasibility of computer-assisted immunohistochemical scoring. However, existing algorithms have limitations that hinder their clinical application.…”

Section: Introductionmentioning

confidence: 99%

AI-Powered Segmentation of Invasive Carcinoma Regions in Breast Cancer Immunohistochemical Whole-Slide Images

Liu,

Zhen,

et al. 2023

Cancers

View full text Add to dashboard Cite

Aims: The automation of quantitative evaluation for breast immunohistochemistry (IHC) plays a crucial role in reducing the workload of pathologists and enhancing the objectivity of diagnoses. However, current methods face challenges in achieving fully automated immunohistochemistry quantification due to the complexity of segmenting the tumor area into distinct ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) regions. Moreover, the quantitative analysis of immunohistochemistry requires a specific focus on invasive carcinoma regions. Methods and Results: In this study, we propose an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images (WSIs). Our method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional H&E and P63 staining slides. In addition, we introduced an advanced semi-supervised learning algorithm, allowing efficient training of the model using unlabeled data. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 618 IHC-stained WSIs from 170 cases, including four types of staining (ER, PR, HER2, and Ki-67). Notably, the model demonstrated an impressive intersection over union (IoU) score exceeding 80% on the test set. Furthermore, to ascertain the practical utility of our model in IHC quantitative evaluation, we constructed a fully automated Ki-67 scoring system based on the model’s predictions. Comparative experiments convincingly demonstrated that our system exhibited high consistency with the scores given by experienced pathologists. Conclusions: Our developed model excels in accurately distinguishing between DCIS and invasive carcinoma regions in breast cancer immunohistochemistry WSIs. This method paves the way for a clinically available, fully automated immunohistochemistry quantitative scoring system.

show abstract

“…Feasibility in the quantification of Ki-67, ER, PR, and HER2 biomarkers was proven in [ 27 ]. However, the article did not provide algorithms and software tools for diagnosis based on the analyzed biomarkers.…”

Section: Literature Reviewmentioning

confidence: 99%

An Approach toward Automatic Specifics Diagnosis of Breast Cancer Based on an Immunohistochemical Image

Berezsky

Pitsun²,

Melnyk³

et al. 2023

J. Imaging

View full text Add to dashboard Cite

The paper explored the problem of automatic diagnosis based on immunohistochemical image analysis. The issue of automated diagnosis is a preliminary and advisory statement for a diagnostician. The authors studied breast cancer histological and immunohistochemical images using the following biomarkers progesterone, estrogen, oncoprotein, and a cell proliferation biomarker. The authors developed a breast cancer diagnosis method based on immunohistochemical image analysis. The proposed method consists of algorithms for image preprocessing, segmentation, and the determination of informative indicators (relative area and intensity of cells) and an algorithm for determining the molecular genetic breast cancer subtype. An adaptive algorithm for image preprocessing was developed to improve the quality of the images. It includes median filtering and image brightness equalization techniques. In addition, the authors developed a software module part of the HIAMS software package based on the Java programming language and the OpenCV computer vision library. Four molecular genetic breast cancer subtypes could be identified using this solution: subtype Luminal A, subtype Luminal B, subtype HER2/neu amplified, and basalt-like subtype. The developed algorithm for the quantitative characteristics of the immunohistochemical images showed sufficient accuracy in determining the cancer subtype “Luminal A”. It was experimentally established that the relative area of the nuclei of cells covered with biomarkers of progesterone, estrogen, and oncoprotein was more than 85%. The given approach allows for automating and accelerating the process of diagnosis. Developed algorithms for calculating the quantitative characteristics of cells on immunohistochemical images can increase the accuracy of diagnosis.

show abstract

Deep learning-based instance segmentation for the precise automated quantification of digital breast cancer immunohistochemistry images

Cited by 12 publications

References 30 publications

Unlocking the Power of R: A High-Accuracy Method for Measuring DAB Staining on Immunohistochemical Slides

Unlocking the Power of R: A High-Accuracy Method for Measuring DAB Staining on Immunohistochemical Slides

AI-Powered Segmentation of Invasive Carcinoma Regions in Breast Cancer Immunohistochemical Whole-Slide Images

An Approach toward Automatic Specifics Diagnosis of Breast Cancer Based on an Immunohistochemical Image

Contact Info

Product

Resources

About