Evaluation of Three Algorithms for the Segmentation of Overlapping Cervical Cells
Zhi Lu,Gustavo Carneiro,Andrew P. Bradley,Daniela Ushizima,Masoud Nosrati,Andrea Gomes Campos Bianchi,Cláudia Martins Carneiro,Ghassan Hamarneh +7 more
Reads0
Chats0
TLDR
The first Overlapping Cervical Cytology Image Segmentation Challenge as discussed by the authors was organized to encourage the development and benchmarking of techniques capable of segmenting individual cells from overlapping cellular clumps in cervical cytology images.Abstract:
In this paper, we introduce and evaluate the systems submitted to the first Overlapping Cervical Cytology Image Segmentation Challenge, held in conjunction with the IEEE International Symposium on Biomedical Imaging 2014. This challenge was organized to encourage the development and benchmarking of techniques capable of segmenting individual cells from overlapping cellular clumps in cervical cytology images, which is a prerequisite for the development of the next generation of computer-aided diagnosis systems for cervical cancer. In particular, these automated systems must detect and accurately segment both the nucleus and cytoplasm of each cell, even when they are clumped together and, hence, partially occluded. However, this is an unsolved problem due to the poor contrast of cytoplasm boundaries, the large variation in size and shape of cells, and the presence of debris and the large degree of cellular overlap. The challenge initially utilized a database of $16$ high-resolution ( $\times$ 40 magnification) images of complex cellular fields of view, in which the isolated real cells were used to construct a database of $945$ cervical cytology images synthesized with a varying number of cells and degree of overlap, in order to provide full access of the segmentation ground truth. These synthetic images were used to provide a reliable and comprehensive framework for quantitative evaluation on this segmentation problem. Results from the submitted methods demonstrate that all the methods are effective in the segmentation of clumps containing at most three cells, with overlap coefficients up to 0.3. This highlights the intrinsic difficulty of this challenge and provides motivation for significant future improvement.read more
Citations
More filters
Journal ArticleDOI
DeepPap: Deep Convolutional Networks for Cervical Cell Classification.
TL;DR: This paper proposes a method to directly classify cervical cells—without prior segmentation—based on deep features, using convolutional neural networks (ConvNets), which outperforms previous algorithms in classification accuracy, area under the curve values, and especially specificity.
Proceedings ArticleDOI
Mask-RCNN and U-Net Ensembled for Nuclei Segmentation
TL;DR: An ensemble model is developed to combine their predictions that can outperform both models by a significant margin and should be considered when aiming for best nuclei segmentation performance.
Journal ArticleDOI
A Survey for Cervical Cytopathology Image Analysis Using Deep Learning
Mamunur Rahaman,Chen Li,Xiangchen Wu,Yu-Dong Yao,Zhijie Hu,Tao Jiang,Xiaoyan Li,Shouliang Qi +7 more
TL;DR: This survey provides a comprehensive study of the state of the art approaches based on deep learning for the analysis of cervical cytology images and introduces deep learning and its simplified architectures that have been used in this field.
Journal ArticleDOI
Deep learning for cell image segmentation and ranking.
Flávio H. D. Araújo,Flávio H. D. Araújo,Romuere R. V. Silva,Romuere R. V. Silva,Daniela Ushizima,Daniela Ushizima,Mariana T. Rezende,Cláudia Martins Carneiro,Andrea Gomes Campos Bianchi,Fátima N. S. de Medeiros +9 more
TL;DR: Computational tools for cytological analysis that incorporate cell segmentation deep learning techniques are introduced that are capable of processing both free-lying and clumps of abnormal cells with a high overlapping rate from digitized images of conventional Pap smears.
Journal ArticleDOI
DeepPap: Deep Convolutional Networks for Cervical Cell Classification
TL;DR: In this paper, the authors proposed a method to directly classify cervical cells without prior segmentation based on deep features, using convolutional neural networks (ConvNets) first, the ConvNet is pre-trained on a natural image dataset It is subsequently fine-tuned on a cervical cell dataset consisting of adaptively re-sampled image patches coarsely centered on the nuclei In the testing phase, aggregation is used to average the prediction scores of a similar set of image patches, and the proposed method is evaluated on both Pap smear and liquid-based cytology (
References
More filters
Proceedings ArticleDOI
Bilateral filtering for gray and color images
Carlo Tomasi,Roberto Manduchi +1 more
TL;DR: In contrast with filters that operate on the three bands of a color image separately, a bilateral filter can enforce the perceptual metric underlying the CIE-Lab color space, and smooth colors and preserve edges in a way that is tuned to human perception.
Journal ArticleDOI
Robust wide-baseline stereo from maximally stable extremal regions
TL;DR: The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes.
Proceedings ArticleDOI
Robust wide baseline stereo from maximally stable extremal regions
TL;DR: The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints, is studied and an efficient and practically fast detection algorithm is presented for an affinely-invariant stable subset of extremal regions, the maximally stable extremal region (MSER).
Book ChapterDOI
Quick Shift and Kernel Methods for Mode Seeking
Andrea Vedaldi,Stefano Soatto +1 more
TL;DR: It is shown that the complexity of the recently introduced medoid-shift algorithm in clustering N points is O(N 2), with a small constant, if the underlying distance is Euclidean, which makes medoid shift considerably faster than mean shift, contrarily to what previously believed.