Discriminant analysis of exfoliated cells in bladder urothelium cancer

Yonghong Lan, Hong Shen, Yaodan Lu, Min Deng

Article ID: 2056
Vol 3, Issue 1, 2022
DOI: https://doi.org/10.54517/urr.v3i1.2056
VIEWS - 2372 (Abstract)

Download PDF

Abstract

Objective To explore the method of computer discriminant on exfoliated cells in bladder urothelium cancer by Pap stain. Methods The exfoliated cells in 107 urine smears included 386 uroepi-thelium normal exfoliated cells (UNC) , 439 urothelium dysplastic exfoliated cells (UDC) and 500 blad-der urothelial cancer exfoliated cells (UCC). The cells were randomly divided into training group (n = 1077) and identifying group (n = 248) , and the chromatic and geometric shape parameters of cytoplasm and nuclear were tested. The stepwise discriminant analysis was used in cells of the training group to establish a discriminant function and analyze the rate of back substitution discriminant. The function was evaluated by cells of identifying group, and the coincidence rate was analyzed in 107 specimens. Results The back discriminant coincidence rate of cells in training group was 80.8%. The coincidence rate of identifying group and 107 specimens were 80.2% and 92.5% respectively. The discriminant effect was significantly better than function based on chromatics and geometric shape parameters individually (P < 0.05). Conclusions The function combined with chromatics and geometric shape parameters has good discriminant performance in bladder urothelium cancer.


Keywords

Chromatics; Geometric shape; Urothelium cancer of bladder; Exfoliated cell; Computer dis-criminant


References

1. Lan Yonghong, Shen Hong, Lu Yaodan, et al. Quantitative chromatic study on transitional cell cancer cells in urine by papanicolaou staining [J]. Chinese Journal of Stereology and Image Analysis, 2009, 14 (4) : 402-405. (in Chinese)

2. Lan Yonghong, Shen Hong, Lu Yaodan, et al. Quantitative analysis on morphological structure of exfoliated cells in bladder urothelium cancer by Papanicolaou staining [J]. Chinese Journal of Clinical and Experimental Pathology, 2012, 28(1) : 54-56, 60. (in Chinese)

3. Lan Yonghong, Shen Hong, Lu Yaodan, et al. Discrimi-nant analysis of exfoliated cells in bladder urothelial cancer based on chromatic parameters of Pap stain [J]. Chinese Journal of Stereology and Image Analysis, 2016, 21 (2) : 229-234. (in Chinese)

4. Lan Yonghong, Shen Hong, Lu Yaodan, et al. The com-puter discriminant on exfoliated cells in bladder urothelial carcinoma based on characteristics of morphological struc-ture [J]. Journal of Hainan medical Unviersity, 2012, 18 (5) : 604-606, 609. (in Chinese)

5. Ma Zhengzhong. Diagnosis Cytopathology [M]. Henan: Henan Science and Technology Press, 2000, 218-225. (in Chinese)

6. Pumingqiu, Ge Xiufeng. Observation on the effect of mod-ified Papanicolaou staining [J]. Chinese Journal of Clinical and Experimental Pathology, 1995, 11(2) : 162-163. (in Chinese)

7. Shen Hong, Shen Zhongying. Practical technology of bio-logical stereology [M]. Guangzhou: Sun Yat-sen Univer-sity Press, 1991: 223-229. (in Chinese)

8. Torre L A, Bray F, Siegel R L, et al. Global cancer statis-tics, 2012. [J]. CA Cancer J Clin, 2015, 65 (2) : 87-108.

9. Wang fang, Tian Hongwei, Ding Hui, et al. The Significance of multiprobe fluorescence in situ hybridization in diagnosis of urary bladder cancer[J]. Chinese Journal of Laboratory Diagnosis, 2014, 18(12) : 1957-1961. (in Chinese)

10. Yangminggen, Zhao Xiaokun, Hou Yi, et al. Meta-analysis of fluorescence in situ hybridization and cytology for diagnosis of bladder cancer [J]. Chinese Journal of Cancer, 2009, 28(6) : 655-662. (in Chinese)

11. Yangminggen, Zhao Xiaokun, Wu Zhiping, et al. Blad-der cancer antigen BTA stat and urine cytology in bladder cancer diagnosis: A meta-analysis [J]. Chinese Journal of Evidence-Based Medicine, 2009, 9 (4) : 458-464. (in Chinese)

Refbacks

  • There are currently no refbacks.


Copyright (c) 2022 Yonghong Lan, Hong Shen, Yaodan Lu, min Deng

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.


This site is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).