Segmentation, Detection, and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou

被引：0

作者：

Matias A.V. ^{[1
]}

Cerentini A. ^{[1
]}

Macarini L.A.B. ^{[2
]}

Amorim J.G.A. ^{[1
]}

Daltoé F.P. ^{[3
]}

von Wangenheim A. ^{[4
]}

机构：

[1] Department of Informatics and Statistics, Federal University of Santa Catarina, Florianópolis

[2] Automation and Systems Department, Federal University of Santa Catarina, Florianópolis

[3] Department of Pathology, Federal University of Santa Catarina, Florianópolis

[4] Brazilian Institute for Digital Convergence, Federal University of Santa Catarina, Florianópolis

来源：

SN Computer Science | 2021年 / 2卷 / 4期

关键词：

Classification; Cytology; Deep learning; Segmentation;

D O I：

10.1007/s42979-021-00676-8

中图分类号：

学科分类号：

摘要：

Although oral cancer is considered a global health issue with 350,000 people diagnosed over a year, it can successfully be treated if diagnosed at early stages. Papanicolaou is an inexpensive and non-invasive method, generally applied to detect cervical cancer, but it can also be useful to detect cancer on oral cavities. The manual process of analyzing cells to detect abnormalities is a time-consuming cell analysis and is subject to variations in perceptions from different professionals. This paper compares three different deep learning (DL) approaches: segmentation, object detection, and image classification. Our results show that the binary object detection with Faster R-CNN is the best approach for nuclei detection and localization (0.76 IoU). Since ResNet 34 had a good performance on abnormal nuclei classification (0.86 F1 score), we concluded that these two models can be used in combination to perform a reliable localization and classification pipeline. This work reinforces that the automated analysis of oral cytology to build a pipeline for nuclei classification and localization using DL can contribute to minimize the subjectivity of the human analysis and also support the detection of cancer at early stages. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

引用

共 41 条

[1]

Amorim J.G., Cerentini A., Macarini L.A.B., Matias A.V., Wangenheim A.V., Systematic literature review of computer vision-aided cytology - a review of classic computer vision and deep learning-based approaches published between january/2016 - march/2020, Tech. Rep., Instituto Nacional Para Convergência Digital - Incod, (2020)

[2]

Andreoli Petrolini V., Beckhauser E., Savaris A., Ines Meurer M., von Wangenheim A., Krechel D., Collaborative telepathology in a statewide telemedicine environment—first tests in the context of the Brazilian public healthcare system, 2019 IEEE 32Nd International Symposium on Computer-Based Medical Systems (CBMS), pp. 684-689, (2019)

[3]

Araujo F.H., Silva R.R., Ushizima D.M., Rezende M.T., Carneiro C.M., Campos Bianchi A.G., Medeiros F.N., Deep learning for cell image segmentation and ranking, Comput Med Imaging Graphics, 72, pp. 13-21, (2019)

[4]

Bell A.A., Kaftan J.N., Aach T., Meyer-Ebrecht D., Bocking A., High dynamic range images as a basis for detection of argyrophilic nucleolar organizer regions under varying stain intensities, 2006 International Conference on Image Processing, IEEE, (2006)

[5]

Bray F., Ferlay J., Soerjomataram I., Siegel R.L., Torre L.A., Jemal A., Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, Cancer J Clin, 68, 6, pp. 394-424, (2018)

[6]

Carvalho L., Fauth G., Baecker Fauth S., Krahl G., Moreira A., Fernandes C., von Wangenheim A., Automated microfossil identification and segmentation using a deep learning approach, Mar Micropaleontol, 158, (2020)

[7]

Deng J., Dong W., Socher R., Li L.J., Li K., Fei-Fei L.

[8]

Deng J., Lu Y., Ke J., An accurate neural network for cytologic whole-slide image analysis, Proceedings of the Australasian Computer Science Week Multiconference, Association for Computing Machinery

[9]

Dey S., Sarkar R., Chatterjee K., Datta P., Barui A., Maity S.P., Pre-cancer risk assessment in habitual smokers from DIC images of oral exfoliative cells using active contour and SVM analysis, Tissue Cell, 49, 2, pp. 296-306, (2017)

[10]

Du L.X., Li Q., Detection and classification of cervical exfoliated cells based on faster r-cnn*, In: 2019 IEEE 11Th International Conference on Advanced Infocomm Technology (ICAIT), 2019, pp. 52-57

← 1 2 3 4 5 →