An Automated and Accurate Methodology to Assess Ki-67 Labeling Index of Immunohistochemical Staining Images of Breast Cancer Tissues

Razavi, Salar; Khameneh, Fariba D.; Serteli, Ercan Alp; Çayır, Sercan; Cetin, Sukru Burak; Hatipoglu, Gokhan; Ayaltı, Samet; Kamasak, Mustafa E.

doi:10.1109/iwssip.2018.8439184

Cited by 5 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the methods of inspection and evaluation were insufficient due to variability between institutions, which precluded this cutoff from being included in a verified clinical guideline [9]. Recently, as inspection methods and evaluations have become automated, the objectivity of Ki-67 values has been secured to some extent; however, it is challenging to ensure standardization across all institutions [29,30]. Our study proves that Ki-67 level is valuable as a prognostic factor despite such issues.…”

Section: Discussionmentioning

confidence: 84%

Ki-67 and breast cancer prognosis: does it matter if Ki-67 level is examined using preoperative biopsy or postoperative specimen?

Choi

Park

Ahn

et al. 2022

Breast Cancer Res Treat

View full text Add to dashboard Cite

Purpose This study aimed to identify the association between Ki-67 level and the prognosis of patients with breast cancer, regardless of the timing of Ki-67 testing (using preoperative biopsy vs. postoperative specimen). Methods A total of 4177 patients underwent surgery between January 2008 and December 2016. Immunohistochemical Ki-67 levels, using either preoperative (1673) or postoperative (2831) specimens, were divided into four groups using cutoff points of 10%, 15%, and 20%. Results Groups with higher-Ki-67 levels, in both the pre- and postoperative periods, showed significantly larger tumor size, higher grade, more frequent hormone receptor-negativity and human epidermal growth factor receptor 2 overexpression, and active adjuvant treatments than groups with lower-Ki-67 levels. High-Ki-67 levels were also significantly associated with poor survival, irrespective of the timing of specimen examination. Conclusion Despite the problems associated with Ki-67, Ki-67 level is an important independent prognostic factor, regardless of the timing of Ki-67 testing, i.e., preoperative or postoperative testing.

show abstract

Section: Discussionmentioning

confidence: 84%

Ki-67 and breast cancer prognosis: does it matter if Ki-67 level is examined using preoperative biopsy or postoperative specimen?

Choi

Park

Ahn

et al. 2022

Breast Cancer Res Treat

View full text Add to dashboard Cite

show abstract

“…Lopez et al [19] brain hot-spot detection 4 WSI Acc = 93.8% Niazi et al [18] digestive system hot-spot and cell detection 55 images Acc = 94.60% Lu et al [17] adrenal glands hot-spot detection 50 WSI rho > 0.8. Xing et al [20] gastro-intestinal tract, pancreas cell detection 46 cases F1 = 90% Swiderska et al [21] brain hot-spot detection and LI estimation 104 WSI rho >0.95 Laurinavicius et al [9] breast hot-spot detection 152 WSI good agreement Valous et al [22] pancreas heterogeneity of proliferation 43 WSI -Paulik et al [23] breast detecting and count nuclear signals 25 WSI PPV = 90.23% Pilutti et al [24] breast hot-spot detection 50 cases, 3 experts Acc = 82% Razavi et al [30] breast LI estimation 30 TMA, 1 expert Acc = 91% Gerard et al [31] breast LI estimation 80 TMA Acc = 93,5% Ko et al [25] breast LI estimation 15 WSI Acc = 89%…”

Section: Classical Machine Learningmentioning

confidence: 99%

Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images

et al. 2020

View full text Add to dashboard Cite

Ki67 hot-spot detection and its evaluation in invasive breast cancer regions play a significant role in routine medical practice. The quantification of cellular proliferation assessed by Ki67 immunohistochemistry is an established prognostic and predictive biomarker that determines the choice of therapeutic protocols. In this paper, we present three deep learning-based approaches to automatically detect and quantify Ki67 hot-spot areas by means of the Ki67 labeling index. To this end, a dataset composed of 100 whole slide images (WSIs) belonging to 50 breast cancer cases (Ki67 and H&E WSI pairs) was used. Three methods based on CNN classification were proposed and compared to create the tumor proliferation map. The best results were obtained by applying the CNN to the mutual information acquired from the color deconvolution of both the Ki67 marker and the H&E WSIs. The overall accuracy of this approach was 95%. The agreement between the automatic Ki67 scoring and the manual analysis is promising with a Spearman’s ρ correlation of 0.92. The results illustrate the suitability of this CNN-based approach for detecting hot-spots areas of invasive breast cancer in WSI.

show abstract

“…In H&E-based tumour classification, most studies leverage the pattern recognition capabilities of conventional convolutional neural networks (CNN). While these approaches have also been applied to the assessment IHC studies,8 precise quantification of events usually requires nuclei (instance) segmentation approaches 9–11. This can be achieved with variants such as Mask R-CNN that automatically apply and refine multiple ROIs to isolate individual nuclei while also benefiting from the superior generalisability of CNNs for object segmentation and classification 9 12.…”

Section: Introductionmentioning

confidence: 99%

Compound computer vision workflow for efficient and automated immunohistochemical analysis of whole slide images

et al. 2022

View full text Add to dashboard Cite

AimsImmunohistochemistry (IHC) assessment of tissue is a central component of the modern pathology workflow, but quantification is challenged by subjective estimates by pathologists or manual steps in semi-automated digital tools. This study integrates various computer vision tools to develop a fully automated workflow for quantifying Ki-67, a standard IHC test used to assess cell proliferation on digital whole slide images (WSIs).MethodsWe create an automated nuclear segmentation strategy by deploying a Mask R-CNN classifier to recognise and count 3,3′-diaminobenzidine positive and negative nuclei. To further improve automation, we replaced manual selection of regions of interest (ROIs) by aligning Ki-67 WSIs with corresponding H&E-stained sections, using scale-invariant feature transform (SIFT) and a conventional histomorphological convolutional neural networks to define tumour-rich areas for quantification.ResultsThe Mask R-CNN was tested on 147 images generated from 34 brain tumour Ki-67 WSIs and showed a high concordance with aggregate pathologists’ estimates (n=3 assessors; y=0.9712x−1.945, r=0.9750). Concordance of each assessor’s Ki-67 estimates was higher when compared with the Mask R-CNN than between individual assessors (ravg=0.9322 vs 0.8703; p=0.0213). Coupling the Mask R-CNN with SIFT-CNN workflow demonstrated ROIs can be automatically chosen and partially sampled to improve automation and dramatically decrease computational time (average: 88.55–19.28 min; p<0.0001).ConclusionsWe show how innovations in computer vision can be serially compounded to automate and improve implementation in clinical workflows. Generalisation of this approach to other ancillary studies has significant implications for computational pathology.

show abstract

An Automated and Accurate Methodology to Assess Ki-67 Labeling Index of Immunohistochemical Staining Images of Breast Cancer Tissues

Cited by 5 publications

References 10 publications

Ki-67 and breast cancer prognosis: does it matter if Ki-67 level is examined using preoperative biopsy or postoperative specimen?

Ki-67 and breast cancer prognosis: does it matter if Ki-67 level is examined using preoperative biopsy or postoperative specimen?

Detection of Ki67 Hot-Spots of Invasive Breast Cancer Based on Convolutional Neural Networks Applied to Mutual Information of H&E and Ki67 Whole Slide Images

Compound computer vision workflow for efficient and automated immunohistochemical analysis of whole slide images

Contact Info

Product

Resources

About