Preliminary establishment of an unsupervised quantification model of Ki-67 proliferation index based on local variable threshold method

doi:10.19439/j.sjos.2022.03.005

Abstract

Abstract: PURPOSE: To develop an effective machine learning method for estimation of Ki-67 cell proliferation index. METHODS: Oral squamous cell carcinoma(OSCC) slices were selected for Ki-67 immunohistochemical staining. The digital pathology images were obtained through whole-slide imaging technology. Variable threshold method based on local statistics was applied to preprocess the images, aiming at reducing the noise in the images. Adaptive threshold method was used to remove the irrelevant light-colored background area in the image, retaining the nucleus part. A threshold method in space was applied to differentiate brown from blue content. Finally, the proliferation index was estimated and compared with manual and the color deconvolution method by paired sample t test and spearman correlation coefficients with SPSS 24.0 software package. RESULTS: A new nucleus detection and classification method was established, which can process pathologic images of different sizes, and effectively detect immunohistochemical brown positive cells and blue negative cells. There was no significant difference between this algorithm and manual counting（P>0.05）, but the speed was faster. The calculation efficiency advantage was more obvious when processing a large image, and the detection result of Ki-67 proliferation index was better than the commonly used color deconvolution method（P<0.05）. CONCLUSIONS: The automatic nucleus quantitative analysis method developed in this study can analyze Ki-67 staining of the nucleus in OSCC cells efficiently and calculate the proliferation index, which can be used for auxiliary diagnosis in pathology.

Key words: Oral squamous cell carcinoma, Ki-67, Proliferation index, Machine learning

CLC Number:

R739.8

QIN Zhi-ming, JIE Wei-ping, CHI Yan-ting, LI Hong-feng, LI Bin-bin. Preliminary establishment of an unsupervised quantification model of Ki-67 proliferation index based on local variable threshold method[J]. Shanghai Journal of Stomatology, 2022, 31(3): 248-254.

References

[1] Sasaki K, Murakami T, Kawasaki M, et al.The cell cycle associated change of the Ki-67 reactive nuclear antigen expression[J]. J Cell Physiol, 1987, 133(3): 579-584.
[2] Jing Y, Zhou Q, Zhu H, et al.Ki-67 is an independent prognostic marker for the recurrence and relapse of oral squamous cell carcinoma[J]. Oncol Lett, 2019, 17(1): 974-980.
[3] Takkem A, Barakat C, Zakaraia S, et al.Ki-67 prognostic value in different histological grades of oral epithelial dysplasia and oral squamous cell carcinoma[J]. Asian Pac J Cancer Prev, 2018, 19(11): 3279-3286.
[4] Dowsett M, Nielsen TO, A'Hern R, et al. Assessment of Ki67 in breast cancer: recommendations from the international Ki67 in breast cancer working group[J]. J Natl Cancer Inst, 2011, 103(22): 1656-1664.
[5] Nielsen LAG, Bangsθ JA, Lindahl KH, et al.Evaluation of the proliferation marker Ki-67 in gliomas: interobserver variability and digital quantification[J]. Diagn Pathol, 2018, 13(1): 38-45.
[6] Aeffner F, Zarella MD, Buchbinder N, et al.Introduction to digital image analysis in whole-slide imaging: a white paper from the digital pathology association[J]. J Pathol Inform, 2019, 10: 9-26.
[7] Stålhammar G, Fuentes Martinez N, Lippert M, et al.Digital image analysis outperforms manual biomarker assessment in breast cancer[J]. Mod Pathol, 2016, 29(4): 318-329.
[8] Lykkegaard Andersen N, Brügmann A, Lelkaitis G, et al.Virtual double staining: a digital approach to immunohistochemical quantification of estrogen receptor protein in breast carcinoma specimens[J]. Appl Immunohistochem Mol Morphol, 2018,26(9): 620-626.
[9] Stålhammar G, Robertson S, Wedlund L, et al.Digital image analysis of Ki67 in hot spots is superior to both manual Ki67 and mitotic counts in breast cancer[J]. Histopathology, 2018, 72(6): 974-989.
[10] Mungle T, Tewary S, Arun I, et al.Automated characterization and counting of Ki-67 protein for breast cancer prognosis: a quantitative immunohistochemistry approach[J]. Comput Methods Programs Biomed, 2017, 139: 149-161.
[11] Alheejawi S, Xu H, Berendt R, et al.Novel lymph node segmentation and proliferation index measurement for skin melanoma biopsy images[J]. Comput Med Imaging Graph, 2019,73: 19-29.
[12] Acs B, Pelekanou V, Bai Y, et al.Ki67 reproducibility using digital image analysis: an inter-platform and inter-operator study[J]. Lab Invest, 2019, 99(1): 107-117.
[13] Koopman T, Buikema HJ, Hollema H, et al.Digital image analysis of Ki67 proliferation index in breast cancer using virtual dual staining on whole tissue sections: clinical validation and inter-platform agreement[J]. Breast Cancer Res Treat, 2018,169(1): 33-42.
[14] Ruifrok AC, Johnston DA.Quantification of histochemical staining by color deconvolution[J]. Anal Quant Cytol Histol, 2001, 23(4): 291-299.
[15] Varghese F, Bukhari AB, Malhotra R, et al.IHC profiler: an open source plugin for the quantitative evaluation and automated scoring of immunohistochemistry images of human tissue samples[J]. PLoS One, 2014, 9(5): e96801.
[16] El-Naggar AK, Chan JKC, Grandis JR, et al.WHO classification of head and neck tumours[M]. Geneva: International Agency for Research on Cancer, 2017.
[17] Morreale P.A perceptual colour separation methodology for automated quantification of Ki67 and hematoxylin stained digital histopathology images[D]. Ontario: The University of Guelph, 2018.
[18] Qi X, Xing F, Foran DJ, et al.Robust segmentation of overlapping cells in histopathology specimens using parallel seed detection and repulsive level set[J]. IEEE Trans Biomed Eng, 2012, 59(3): 754-765.
[19] Gonzalez RC, Woods RE.Digital image processing[M]. New Jersey: Perarson Education, 2002.
[20] Di Cataldo S, Ficarra E, Acquaviva A, et al.Automated segmentation of tissue images for computerized IHC analysis[J]. Comput Methods Programs Biomed, 2010, 100(1): 1-15.
[21] Grala B, Markiewicz T, Kozlowski W, et al.New automated image analysis method for the assessment of Ki-67 labeling index in meningiomas[J]. Folia Histochem Cytobiol, 2009, 47(4): 587-592.
[22] Kårsnäs A, Dahl AL, Larsen R.Learning histopathological patterns[J]. J Pathol Inform, 2011, 2: S12.
[23] Komura D, Ishikawa S.Machine learning methods for histopathological image analysis[J]. Comput Struct Biotechnol J, 2018, 16(1): 34-42.