A New Cervical Cytology Dataset for Nucleus Detection and Image Classification (Cervix93) and Methods for Cervical Nucleus Detection

Analyzing Pap cytology slides is an important tasks in detecting and grading precancerous and cancerous cervical cancer stages. Processing cytology images usually involve segmenting nuclei and overlapping cells. We introduce a cervical cytology dataset that can be used to evaluate nucleus detection, as well as image classification methods in the cytology image processing area. This dataset contains 93 real image stacks with their grade labels and manually annotated nuclei within images. We also present two methods: a baseline method based on a previously proposed approach, and a deep learning method, and compare their results with other state-of-the-art methods. Both the baseline method and the deep learning method outperform other state-of-the-art methods by significant margins. Along with the dataset, we publicly make the evaluation code and the baseline method available to download for further benchmarking.

[1]  Mariusz Bajger,et al.  Circular shape constrained fuzzy clustering (CiscFC) for nucleus segmentation in Pap smear images , 2017, Comput. Biol. Medicine.

[2]  Jianping Yin,et al.  A novel unsupervised segmentation method for overlapping cervical cell images , 2017, International Conference on Digital Image Processing.

[3]  Lawrence O. Hall,et al.  A new approach to detect and segment overlapping cells in multi-layer cervical cell volume images , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[4]  Srishti Gautam,et al.  Unsupervised Segmentation of Cervical Cell Nuclei via Adaptive Clustering , 2017, MIUA.

[5]  Gustavo Carneiro,et al.  An Improved Joint Optimization of Multiple Level Set Functions for the Segmentation of Overlapping Cervical Cells , 2015, IEEE Transactions on Image Processing.

[6]  Ghassan Hamarneh,et al.  Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells , 2017, IEEE Journal of Biomedical and Health Informatics.

[7]  A. Bradley,et al.  A One-Pass Extended Depth of Field Algorithm Based on the Over-Complete Discrete Wavelet Transform , 2004 .

[8]  Mark Sherman,et al.  The 2001 Bethesda System: terminology for reporting results of cervical cytology. , 2002, JAMA.

[9]  Lawrence O. Hall,et al.  A framework for nucleus and overlapping cytoplasm segmentation in cervical cytology extended depth of field and volume images , 2017, Comput. Medical Imaging Graph..

[10]  Karolin Baecker,et al.  Two Dimensional Signal And Image Processing , 2016 .

[11]  Aurobinda Routray,et al.  An unsupervised approach for overlapping cervical cell cytoplasm segmentation , 2016, 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES).

[12]  Yue Wang,et al.  Optimizing the cervix cytological examination based on deep learning and dynamic shape modeling , 2017, Neurocomputing.

[13]  Zahidul Islam,et al.  Multi-step level set method for segmentation of overlapping cervical cells , 2015, 2015 IEEE International Conference on Telecommunications and Photonics (ICTP).