Nucleus segmentation of cervical cytology images based on multi-scale fuzzy clustering algorithm

Huang, Jinjie; Wang, Tao; Zheng, Dequan; He, Yongjun

doi:10.1080/21655979.2020.1747834

Cited by 33 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[52] J Huang et al utilize a segmentation method based on a "multi-scale fuzzy clustering algorithm" which segments cervical cell clump images at different scales. [53] Firstly, the algorithm is used to divide the cell clusters at different scales. Then a hierarchical tree is constructed based on the inclusion relationship between the segments.…”

Section: Image Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Automated Detection and Classification of Cervical Cancer Using Pap Smear Microscopic Images: A Comprehensive Review and Future Perspectives

Shanthi¹,

Hareesha²,

Kudva³

2022

Eng. Sci.

View full text Add to dashboard Cite

Computer aided categorization of smear images has been considered challenging in the past few decades. Cervical cancer is a main cause of mortality among women worldwide and more prevalent in underdeveloped countries. This disease can be successfully treated, even fully cured, if detected at its early phase. Computerized image analysis methods are primarily of great interest as they provide significant benefits for clinicians with reliable and timely diagnosis of the samples. Dedicated image analysis algorithms provide mathematical description of the region of interest which provide a great support to pathologists for decision making. In this review, we have outlined state of the art techniques expressed in prominent publications on computer assisted diagnostic system for cancer detection. By utilizing the domain aspects of cervical cancer, suitable methods and techniques are explored and presented. This review also presents a knowledge to assess the methodology used in the literature and emphasized some of the inadequacies and weaknesses in the reviewed methods. The study accentuates the future directions pertinent to the development of cost-effective, automated disease classification system that should be a significant advantage for countries with limited resources and treatment services.

show abstract

Section: Image Segmentationmentioning

confidence: 99%

“…Then a hierarchical tree is constructed based on the inclusion relationship between the segments. [53,54] In the final phase, interesting nodes in the hierarchical tree are identified according to the proposed interesting degree based on area prior. T Wang et al propose an algorithm based on depth information.…”

Section: Image Segmentationmentioning

confidence: 99%

Automated Detection and Classification of Cervical Cancer Using Pap Smear Microscopic Images: A Comprehensive Review and Future Perspectives

Shanthi¹,

Hareesha²,

Kudva³

2022

Eng. Sci.

View full text Add to dashboard Cite

show abstract

“…Marinakis et al [23] in a way similar to [39,42] of using the Herlev dataset as both a 2-class and a 7-class problem, used genetic algorithm combined with nearest neighbour classifier and got the best result with 1 nearest neighbour classifier giving an accuracy of 98.14% on the 2-class problem and 96.95% on the 7-class problem both in 10-fold cross-validation. Zhang et al [43] used a deep convolutional neural network architecture thus removing the need for cell segmentation like [9,19] on the Herlev dataset and achieved an accuracy of 98.3%.…”

Section: Related Workmentioning

confidence: 99%

Cervical Cytology Classification Using PCA and GWO Enhanced Deep Features Selection

Basak

Kundu

Chakraborty³

et al. 2021

SN COMPUT. SCI.

View full text Add to dashboard Cite

Cervical cancer is one of the most deadly and common diseases among women worldwide. It is completely curable if diagnosed in an early stage, but the tedious and costly detection procedure makes it unviable to conduct population-wise screening. Thus, to augment the effort of the clinicians, in this paper, we propose a fully automated framework that utilizes deep learning and feature selection using evolutionary optimization for cytology image classification. The proposed framework extracts deep feature from several convolution neural network (CNN) models and uses a two-step feature reduction approach to ensure reduction in computation cost and faster convergence. The features extracted from the CNN models form a large feature space whose dimensionality is reduced using principal component analysis while preserving 99% of the variance. A non-redundant, optimal feature subset is selected from this feature space using an evolutionary optimization algorithm, the grey wolf optimizer, thus improving the classification performance. Finally, the selected feature subset is used to train an support vector machine classifier for generating the final predictions. The proposed framework is evaluated on three publicly available benchmark datasets: Mendeley Liquid Based Cytology (4-class) dataset, Herlev Pap Smear (7-class) dataset, and the SIPaKMeD Pap Smear (5-class) dataset achieving classification accuracies of 99.47, 98.32 and 97.87%, respectively, thus justifying the reliability of the approach. The relevant codes for the proposed approach can be found in: https:// github. com/ DVLP-CMATE RJU/ Two-Step-Featu re-Enhan cement.

show abstract

“…Marinakis et al [26] in a way similar to [45,42] of using the Herlev Dataset as both a 2-class and a 7-class problem, used genetic algorithm combined with nearest neighbour classifier and got the best result with 1 nearest neighbour classifier giving an accuracy of 98.14% on the 2-class problem and 96.95% on the 7-class problem both in 10-fold cross-validation. Zhang et al [46] used a deep convolutional neural network architecture thus removing the need for cell segmentation like [22,12] on the Herlev Dataset and achieved an accuracy of 98.3%.…”

Section: Related Workmentioning

confidence: 99%

Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection

Basak,

Kundu,

Chakraborty

et al. 2021

Preprint

View full text Add to dashboard Cite

Cervical cancer is one of the most deadly and common diseases among women worldwide. It is completely curable if diagnosed in an early stage, but the tedious and costly detection procedure makes it unviable to conduct population-wise screening. Thus, to augment the effort of the clinicians, in this paper, we propose a fully automated framework that utilizes Deep Learning and feature selection using evolutionary optimization for cytology image classification. The proposed framework extracts Deep feature from several Convolution Neural Network models and uses a two-step feature reduction approach to to ensure reduction in computation cost and faster convergence. The features extracted from the CNN models form a large feature space whose dimensionality is reduced using Principal Component Analysis while preserving 99% of the variance. A non-redundant, optimal feature subset is selected from this feature space using an evolutionary optimization algorithm, the Grey Wolf Optimizer, thus improving the classification performance. Finally, the selected feature subset is used to train an SVM classifier for generating the final predictions. The proposed framework is evaluated on three publicly available benchmark datasets: Mendeley Liquid Based Cytology (4-class) dataset, Herlev Pap Smear (7-class) dataset, and the SIPaKMeD Pap Smear (5class) dataset achieving classification accuracies of 99.47%, 98.32% and 97.87% respectively, thus justifying the reliability of the approach. The relevant codes for the proposed approach can be found in: GitHub

show abstract

Nucleus segmentation of cervical cytology images based on multi-scale fuzzy clustering algorithm

Cited by 33 publications

References 38 publications

Automated Detection and Classification of Cervical Cancer Using Pap Smear Microscopic Images: A Comprehensive Review and Future Perspectives

Automated Detection and Classification of Cervical Cancer Using Pap Smear Microscopic Images: A Comprehensive Review and Future Perspectives

Cervical Cytology Classification Using PCA and GWO Enhanced Deep Features Selection

Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features Selection

Contact Info

Product

Resources

About