Automatic cytoplasm and nuclei segmentation for color cervical smear image using an efficient gap-search MRF

Zhao, Lili; Li, Kuan; Wang, Mao; Yin, Jianping; Zhu, En; Wu, Chengkun; Wang, Siqi; Zhu, Chengzhang

doi:10.1016/j.compbiomed.2016.01.025

Cited by 57 publications

(25 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Along with other robust refinement methods, supervised and unsupervised methods were used to distinguish image patches or superpixels from extracted elements, such as Adaboost detectors [27], support vector machine (SVM) [28] or Gauussian mixture models [29]. In a study by Zhao et al [30] a novel superpixel-based Markov random field (MRF) segmentation was also implemented for non-overlapping cells.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Cervical Cancer Prediction Model with Outlier Detection and Over-Sampling Methods

Ijaz

Attique

Son

2020

Sensors

180

114

View full text Add to dashboard Cite

Globally, cervical cancer remains as the foremost prevailing cancer in females. Hence, it is necessary to distinguish the importance of risk factors of cervical cancer to classify potential patients. The present work proposes a cervical cancer prediction model (CCPM) that offers early prediction of cervical cancer using risk factors as inputs. The CCPM first removes outliers by using outlier detection methods such as density-based spatial clustering of applications with noise (DBSCAN) and isolation forest (iForest) and by increasing the number of cases in the dataset in a balanced way, for example, through synthetic minority over-sampling technique (SMOTE) and SMOTE with Tomek link (SMOTETomek). Finally, it employs random forest (RF) as a classifier. Thus, CCPM lies on four scenarios: (1) DBSCAN + SMOTETomek + RF, (2) DBSCAN + SMOTE+ RF, (3) iForest + SMOTETomek + RF, and (4) iForest + SMOTE + RF. A dataset of 858 potential patients was used to validate the performance of the proposed method. We found that combinations of iForest with SMOTE and iForest with SMOTETomek provided better performances than those of DBSCAN with SMOTE and DBSCAN with SMOTETomek. We also observed that RF performed the best among several popular machine learning classifiers. Furthermore, the proposed CCPM showed better accuracy than previously proposed methods for forecasting cervical cancer. In addition, a mobile application that can collect cervical cancer risk factors data and provides results from CCPM is developed for instant and proper action at the initial stage of cervical cancer.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Cytoplasm DSC: 0.914. In one other study, Zhao et al 2016 [30] used an MRF classifier with a Gap-search algorithm + Automatic labeling map. The findings revealed that Nuclei DSC: 0.93.…”

Section: Related Workmentioning

confidence: 99%

Data-Driven Cervical Cancer Prediction Model with Outlier Detection and Over-Sampling Methods

Ijaz

Attique

Son

2020

Sensors

180

114

View full text Add to dashboard Cite

show abstract

“…As described in [11], there exists substantial difference between abnormal and normal nuclei in shape and size. We thus separate the nuclei class into abnormal (small) and normal (large) classes, resulting in four classes for D-MEM training Method ZSI Precision Recall Unsupervised [15] 0.89±0.15 0.88±0.15 0.93±0.15 FCM [16] 0.80±0.24 0.85±0.21 0.83±0.25 P-MRF [17] 0.93±0.03 − − SP-CNN [18] 0.90 0.89 0.91 Our Method 0.933±0.14 0.946±0.06 0.984±0.00 Table 1. Comparison of the state-of-the-art methods and proposed method and predicting.…”

Section: Model Training and Predictingmentioning

confidence: 99%

Automated Segmentation Of Cervical Nuclei In Pap Smear Images Using Deformable Multi-Path Ensemble Model

Zhao

Li³

et al. 2019

2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019)

View full text Add to dashboard Cite

Pap smear testing has been widely used for detecting cervical cancers based on the morphological properties of cell nuclei in microscopic image. An accurate nuclei segmentation could thus improve the success rate of cervical cancer screening. In this work, a method of automated cervical nuclei segmentation using Deformable Multipath Ensemble Model (D-MEM) is proposed. The approach adopts a U-shaped convolutional network as a backbone network, in which dense blocks are used to transfer feature information more effectively. To increase the flexibility of the model, we then use deformable convolution to deal with different nuclei irregular shapes and sizes. To reduce the predictive bias, we further construct multiple networks with different settings, which form an ensemble model. The proposed segmentation framework has achieved state-of-the-art accuracy on Herlev dataset with Zijdenbos similarity index (ZSI) of 0.933±0.14, and has the potential to be extended for solving other medical image segmentation tasks.

show abstract

“…Nosrati and Hamarneh [6] used MSER combined with Random Decision Forest. Further, a framework for detecting the nuclei of cells based on Markov Random Field (MRF) was proposed by Zhao et al [11].…”

Section: Introductionmentioning

confidence: 99%

Nuclei Detection Using Deep Learning

Braz¹,

Lotufo²

2017

Anais De XXXV Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

An important objective in the analysis of Pap smear images is automatic detection of a cell's nucleus. Various methods that automatically detect the nuclei of cervical cells have been proposed to improve the analysis of screening test images. In this paper, we propose a Convolutional Neural Networksbased method that automatically detects the nuclei of cervical cells. Following training using a public dataset provided by the Overlapping Cervical Cytology Image Segmentation Challenge-ISBI 2014, the network's fully connected layers are converted to convolutional layers to enable processing of images of any size. Our results were then compared with those achieved by other participants who successfully submitted their work to ISBI 2014 and other studies that used the same dataset. Our experimental results indicate that the methodology provides fast nuclei detection with precision and recall that are comparable with the state-of-the-art methods used to detect the nuclei of cervical cells.

show abstract

Automatic cytoplasm and nuclei segmentation for color cervical smear image using an efficient gap-search MRF

Cited by 57 publications

References 36 publications

Data-Driven Cervical Cancer Prediction Model with Outlier Detection and Over-Sampling Methods

Data-Driven Cervical Cancer Prediction Model with Outlier Detection and Over-Sampling Methods

Automated Segmentation Of Cervical Nuclei In Pap Smear Images Using Deformable Multi-Path Ensemble Model

Nuclei Detection Using Deep Learning

Contact Info

Product

Resources

About