Detection of Cervical Cancer Cells in Whole Slide Images Using Deformable and Global Context Aware Faster RCNN-FPN

Overview

Journal Curr Oncol

Publisher MDPI

Specialty Oncology

Date 2021 Sep 30

PMID 34590614

Citations 17

Authors

Xia Li

Zhenhao Xu

Xi Shen

Yongxia Zhou

Binggang Xiao

Tie-Qiang Li

Affiliations

Soon will be listed here.

Abstract

Cervical cancer is a worldwide public health problem with a high rate of illness and mortality among women. In this study, we proposed a novel framework based on Faster RCNN-FPN architecture for the detection of abnormal cervical cells in cytology images from a cancer screening test. We extended the Faster RCNN-FPN model by infusing deformable convolution layers into the feature pyramid network (FPN) to improve scalability. Furthermore, we introduced a global contextual aware module alongside the Region Proposal Network (RPN) to enhance the spatial correlation between the background and the foreground. Extensive experimentations with the proposed deformable and global context aware (DGCA) RCNN were carried out using the cervical image dataset of "Digital Human Body" Vision Challenge from the Alibaba Cloud TianChi Company. Performance evaluation based on the mean average precision (mAP) and receiver operating characteristic (ROC) curve has demonstrated considerable advantages of the proposed framework. Particularly, when combined with tagging of the negative image samples using traditional computer-vision techniques, 6-9% increase in mAP has been achieved. The proposed DGCA-RCNN model has potential to become a clinically useful AI tool for automated detection of cervical cancer cells in whole slide images of Pap smear.

Citing Articles

Performance of artificial intelligence for diagnosing cervical intraepithelial neoplasia and cervical cancer: a systematic review and meta-analysis.

Liu L, Liu J, Su Q, Chu Y, Xia H, Xu R EClinicalMedicine. 2025; 80():102992.

PMID: 39834510 PMC: 11743870. DOI: 10.1016/j.eclinm.2024.102992.

Automated analysis of digital medical images in cervical cancer screening: A systematic review.

Ledwaba L, Saidu R, Malila B, Kuhn L, Mutsvangwa T medRxiv. 2024; .

PMID: 39399017 PMC: 11469345. DOI: 10.1101/2024.09.27.24314466.

Swin-GA-RF: genetic algorithm-based Swin Transformer and random forest for enhancing cervical cancer classification.

Alohali M, El-Rashidy N, Alaklabi S, Elmannai H, Alharbi S, Saleh H Front Oncol. 2024; 14:1392301.

PMID: 39099689 PMC: 11294103. DOI: 10.3389/fonc.2024.1392301.

Pixel-wise segmentation of cells in digitized Pap smear images.

Harangi B, Bogacsovics G, Toth J, Kovacs I, Dani E, Hajdu A Sci Data. 2024; 11(1):733.

PMID: 38971865 PMC: 11227563. DOI: 10.1038/s41597-024-03566-9.

CerviCell-detector: An object detection approach for identifying the cancerous cells in pap smear images of cervical cancer.

Kalbhor M, Shinde S, Wajire P, Jude H Heliyon. 2023; 9(11):e22324.

PMID: 38058644 PMC: 10696000. DOI: 10.1016/j.heliyon.2023.e22324.

References

Song Y, Tan E, Jiang X, Cheng J, Ni D, Chen S . Accurate Cervical Cell Segmentation from Overlapping Clumps in Pap Smear Images. IEEE Trans Med Imaging. 2016; 36(1):288-300. DOI: 10.1109/TMI.2016.2606380. View

Yang-Mao S, Chan Y, Chu Y . Edge enhancement nucleus and cytoplast contour detector of cervical smear images. IEEE Trans Syst Man Cybern B Cybern. 2008; 38(2):353-66. DOI: 10.1109/TSMCB.2007.912940. View

Cai Z, Vasconcelos N . Cascade R-CNN: High Quality Object Detection and Instance Segmentation. IEEE Trans Pattern Anal Mach Intell. 2019; 43(5):1483-1498. DOI: 10.1109/TPAMI.2019.2956516. View

Savage N . How AI is improving cancer diagnostics. Nature. 2020; 579(7800):S14-S16. DOI: 10.1038/d41586-020-00847-2. View

Zhang L, Kong H, Chin C, Liu S, Chen Z, Wang T . Segmentation of cytoplasm and nuclei of abnormal cells in cervical cytology using global and local graph cuts. Comput Med Imaging Graph. 2014; 38(5):369-80. DOI: 10.1016/j.compmedimag.2014.02.001. View

Thrall M . Automated screening of Papanicolaou tests: A review of the literature. Diagn Cytopathol. 2018; 47(1):20-27. DOI: 10.1002/dc.23931. View

Li X, Shen X, Zhou Y, Wang X, Li T . Classification of breast cancer histopathological images using interleaved DenseNet with SENet (IDSNet). PLoS One. 2020; 15(5):e0232127. PMC: 7198071. DOI: 10.1371/journal.pone.0232127. View

Arbyn M, Weiderpass E, Bruni L, de Sanjose S, Saraiya M, Ferlay J . Estimates of incidence and mortality of cervical cancer in 2018: a worldwide analysis. Lancet Glob Health. 2019; 8(2):e191-e203. PMC: 7025157. DOI: 10.1016/S2214-109X(19)30482-6. View

Lu Z, Carneiro G, Bradley A, Ushizima D, Nosrati M, G C Bianchi A . Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells. IEEE J Biomed Health Inform. 2016; 21(2):441-450. DOI: 10.1109/JBHI.2016.2519686. View

10.

Xiao Y, Wang X, Zhang P, Meng F, Shao F . Object Detection Based on Faster R-CNN Algorithm with Skip Pooling and Fusion of Contextual Information. Sensors (Basel). 2020; 20(19). PMC: 7582940. DOI: 10.3390/s20195490. View

11.

Bhatt A, Ganatra A, Kotecha K . Cervical cancer detection in pap smear whole slide images using convNet with transfer learning and progressive resizing. PeerJ Comput Sci. 2021; 7:e348. PMC: 7959623. DOI: 10.7717/peerj-cs.348. View

12.

Lu Z, Carneiro G, Bradley A . Automated nucleus and cytoplasm segmentation of overlapping cervical cells. Med Image Comput Comput Assist Interv. 2014; 16(Pt 1):452-60. DOI: 10.1007/978-3-642-40811-3_57. View

13.

T Rezende M, Silva R, Bernardo F, Tobias A, Oliveira P, Machado T . Cric searchable image database as a public platform for conventional pap smear cytology data. Sci Data. 2021; 8(1):151. PMC: 8192784. DOI: 10.1038/s41597-021-00933-8. View

14.

Ren S, He K, Girshick R, Sun J . Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Anal Mach Intell. 2016; 39(6):1137-1149. DOI: 10.1109/TPAMI.2016.2577031. View

15.

Peng J, Bao C, Hu C, Wang X, Jian W, Liu W . Automated mammographic mass detection using deformable convolution and multiscale features. Med Biol Eng Comput. 2020; 58(7):1405-1417. DOI: 10.1007/s11517-020-02170-4. View

16.

Tan X, Li K, Zhang J, Wang W, Wu B, Wu J . Automatic model for cervical cancer screening based on convolutional neural network: a retrospective, multicohort, multicenter study. Cancer Cell Int. 2021; 21(1):35. PMC: 7791865. DOI: 10.1186/s12935-020-01742-6. View

17.

Plissiti M, Nikou C . Overlapping cell nuclei segmentation using a spatially adaptive active physical model. IEEE Trans Image Process. 2012; 21(11):4568-80. DOI: 10.1109/TIP.2012.2206041. View

18.

Esteva A, Kuprel B, Novoa R, Ko J, Swetter S, Blau H . Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542(7639):115-118. PMC: 8382232. DOI: 10.1038/nature21056. View

19.

Lin T, Goyal P, Girshick R, He K, Dollar P . Focal Loss for Dense Object Detection. IEEE Trans Pattern Anal Mach Intell. 2018; 42(2):318-327. DOI: 10.1109/TPAMI.2018.2858826. View

20.

Chen Y, Huang P, Lin K, Lin H, Wang L, Cheng C . Semi-automatic segmentation and classification of Pap smear cells. IEEE J Biomed Health Inform. 2014; 18(1):94-108. DOI: 10.1109/JBHI.2013.2250984. View