Ki67 as a Biomarker of Prognosis and Prediction: Is it Ready for Use in Routine Pathology Practice?

Albarracin, Constance T.; Dhamne, Sagar

doi:10.1007/s12609-014-0163-y

“…There have been international standardization efforts to reduce observer variability in PI measurement, but many challenges remain (Khademi, 2013). Points of discussion include variability in manually counted cells (Khademi, 2013), the selection of appropriate cut-off thresholds for protein detection (Albarracin and Dhamne, 2014), the number of high power fields to evaluate (Harris et al, 2016), and the PI ranges that correlate to prognosis, i.e., low (<10%), intermediate (11-30%), and high (>30%) levels of proliferation activity (Khademi, 2013). The European Society for Medical Oncology (ESMO) and the American Society of Clinical Oncology have concluded that Ki67 would be a useful clinical tool if it was standardized (Dowsett et al, 2011;Senkus et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

Geread¹,

Morreale²,

Dony³

et al. 2022

Preprint

0

View full text Add to dashboard Cite

Automated image analysis tools for Ki67 breast cancer digital pathology images would have signiﬁcant value if integrated into diagnostic pathology workﬂows. Such tools would reduce the workload of pathologists, while improving efﬁciency, and accuracy. Developing tools that are robust and reliable to multicentre data is challenging, however, differences in staining protocols, digitization equipment, staining compounds, and slide preparation can create variabilities in image quality and color across digital pathology datasets. In this work, a novel unsupervised color separation framework based on the IHC color histogram (IHCCH) is proposed for the robust analysis of Ki67 and hematoxylin stained images in multicentre datasets. An “overstaining” threshold is implemented to adjustforbackgroundoverstaining,andanautomatednucleiradiusestimatorisdesigned to improve nuclei detection. Proliferation index and F1 scores were compared between the proposed method and manually labeled ground truth data for 30 TMA cores that have ground truths for Ki67+ and Ki67− nuclei. The method accurately quantiﬁed the PI over the dataset, with an average proliferation index difference of 3.25%. To ensure the method generalizes to new, diverse datasets, 50 Ki67 TMAs from the Protein Atlas were used to test the validated approach. As the ground truth for this dataset is PI ranges, the automated result was compared to the PI range. The proposed method correctly classiﬁed 74 out of 80 TMA images, resulting in a 92.5% accuracy. In addition to these validations experiments, performance was compared to two color-deconvolution based methods, and to six machine learning classiﬁers. In all cases, the proposed work maintained more consistent (reproducible) results, and higher PI quantiﬁcation accuracy.

show abstract

“…There have been international standardization efforts to reduce observer variability in PI measurement, but many challenges remain (Khademi, 2013). Points of discussion include variability in manually counted cells (Khademi, 2013), the selection of appropriate cut-off thresholds for protein detection (Albarracin and Dhamne, 2014), the number of high power fields to evaluate (Harris et al, 2016), and the PI ranges that correlate to prognosis, i.e., low (<10%), intermediate (11-30%), and high (>30%) levels of proliferation activity (Khademi, 2013). The European Society for Medical Oncology (ESMO) and the American Society of Clinical Oncology have concluded that Ki67 would be a useful clinical tool if it was standardized (Dowsett et al, 2011;Senkus et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

Geread¹,

Morreale²,

Dony³

et al. 2022

Preprint

0

View full text Add to dashboard Cite

Automated image analysis tools for Ki67 breast cancer digital pathology images would have signiﬁcant value if integrated into diagnostic pathology workﬂows. Such tools would reduce the workload of pathologists, while improving efﬁciency, and accuracy. Developing tools that are robust and reliable to multicentre data is challenging, however, differences in staining protocols, digitization equipment, staining compounds, and slide preparation can create variabilities in image quality and color across digital pathology datasets. In this work, a novel unsupervised color separation framework based on the IHC color histogram (IHCCH) is proposed for the robust analysis of Ki67 and hematoxylin stained images in multicentre datasets. An “overstaining” threshold is implemented to adjustforbackgroundoverstaining,andanautomatednucleiradiusestimatorisdesigned to improve nuclei detection. Proliferation index and F1 scores were compared between the proposed method and manually labeled ground truth data for 30 TMA cores that have ground truths for Ki67+ and Ki67− nuclei. The method accurately quantiﬁed the PI over the dataset, with an average proliferation index difference of 3.25%. To ensure the method generalizes to new, diverse datasets, 50 Ki67 TMAs from the Protein Atlas were used to test the validated approach. As the ground truth for this dataset is PI ranges, the automated result was compared to the PI range. The proposed method correctly classiﬁed 74 out of 80 TMA images, resulting in a 92.5% accuracy. In addition to these validations experiments, performance was compared to two color-deconvolution based methods, and to six machine learning classiﬁers. In all cases, the proposed work maintained more consistent (reproducible) results, and higher PI quantiﬁcation accuracy.

show abstract

“…There have been international standardization efforts to reduce observer variability in PI measurement, but many challenges remain (Khademi, 2013). Points of discussion include variability in manually counted cells (Khademi, 2013), the selection of appropriate cut-off thresholds for protein detection (Albarracin and Dhamne, 2014), the number of high power fields to evaluate (Harris et al, 2016), and the PI ranges that correlate to prognosis, i.e., low (<10%), intermediate (11–30%), and high (>30%) levels of proliferation activity (Khademi, 2013). The European Society for Medical Oncology (ESMO) and the American Society of Clinical Oncology have concluded that Ki67 would be a useful clinical tool if it was standardized (Dowsett et al, 2011; Senkus et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

Geread

¹

,

Morreale

²

,

Dony

³

et al. 2019

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Automated image analysis tools for Ki67 breast cancer digital pathology images would have significant value if integrated into diagnostic pathology workflows. Such tools would reduce the workload of pathologists, while improving efficiency, and accuracy. Developing tools that are robust and reliable to multicentre data is challenging, however, differences in staining protocols, digitization equipment, staining compounds, and slide preparation can create variabilities in image quality and color across digital pathology datasets. In this work, a novel unsupervised color separation framework based on the IHC color histogram (IHCCH) is proposed for the robust analysis of Ki67 and hematoxylin stained images in multicentre datasets. An “overstaining” threshold is implemented to adjust for background overstaining, and an automated nuclei radius estimator is designed to improve nuclei detection. Proliferation index and F1 scores were compared between the proposed method and manually labeled ground truth data for 30 TMA cores that have ground truths for Ki67+ and Ki67− nuclei. The method accurately quantified the PI over the dataset, with an average proliferation index difference of 3.25%. To ensure the method generalizes to new, diverse datasets, 50 Ki67 TMAs from the Protein Atlas were used to test the validated approach. As the ground truth for this dataset is PI ranges, the automated result was compared to the PI range. The proposed method correctly classified 74 out of 80 TMA images, resulting in a 92.5% accuracy. In addition to these validations experiments, performance was compared to two color-deconvolution based methods, and to six machine learning classifiers. In all cases, the proposed work maintained more consistent (reproducible) results, and higher PI quantification accuracy.

show abstract

Ki67 as a Biomarker of Prognosis and Prediction: Is it Ready for Use in Routine Pathology Practice?

Cited by 5 publications

References 35 publications

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

IHC Color Histograms for Unsupervised Ki67 Proliferation Index Calculation

Contact Info

Product

Resources

About