Cervical Cancer Detection Using Segmentation on Pap smear Images

Arya, Mithlesh; Mittal, Namita; Singh, Girdhari

doi:10.1145/2980258.2980311

Cited by 15 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mostly used classifiers in the multi-cell cervical image analysis are support vector machine (SVM) [27], LDA (Linear Discriminant Analysis) [28], k-nearest neighbor (KNN) [29], and ANN (Artificial Neural Networks) [30]. There have been many research studies about cervical cancer detection, but most studies have only targeted the segmentation of nuclei regions [31]. The segmentation of cytoplasm regions is also essential.…”

Section: Methodsmentioning

confidence: 99%

Computer-Assisted Screening for Cervical Cancer Using Digital Image Processing of Pap Smear Images

et al. 2020

View full text Add to dashboard Cite

Cervical cancer can be prevented by having regular screenings to find any precancers and treat them. The Pap test looks for any abnormal or precancerous changes in the cells on the cervix. However, the manual screening of Pap smear in the microscope is subjective with poorly reproducible criteria. Therefore, the aim of this study was to develop a computer-assisted screening system for cervical cancer using digital image processing of Pap smear images. The analysis of Pap smear image is important in the cervical cancer screening system. There were four basic steps in our cervical cancer screening system. In cell segmentation, nuclei were detected using a shape-based iterative method, and the overlapping cytoplasm was separated using a marker-control watershed approach. In the features extraction step, three important features were extracted from the regions of segmented nuclei and cytoplasm. RF (random forest) algorithm was used as a feature selection method. In the classification stage, bagging ensemble classifier, which combined the results of five classifiers—LD (linear discriminant), SVM (support vector machine), KNN (k-nearest neighbor), boosted trees, and bagged trees—was applied. SIPaKMeD and Herlev datasets were used to prove the effectiveness of our proposed system. According to the experimental results, 98.27% accuracy in two-class classification and 94.09% accuracy in five-class classification was achieved using the SIPaKMeD dataset. When the results were compared with five classifiers, our proposed method was significantly better in two-class and five-class problems.

show abstract

Section: Methodsmentioning

confidence: 99%

Computer-Assisted Screening for Cervical Cancer Using Digital Image Processing of Pap Smear Images

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The proposed multiclass convolution neural network was used for the segmentation of nuclei and cytoplasm whereas the graph-based method was used for enhancing the results of segmentation. In 2016, Author Mithlesh et al published a paper [8] in which they demonstrated an approach that uses multiple and overlapped cells from the Pap smear images. The pap smear images were in JPEG format and collected from Jaipur pathology labs.…”

Section: Related Workmentioning

confidence: 99%

Cervix Image Classification for Prognosis of Cervical Cancer using Deep Neural Network with Transfer Learning

Dhawan¹,

Singh²,

Arora³

2018

EAI Endorsed Transactions on Pervasive Health and Technology

View full text Add to dashboard Cite

INTRODUCTION: Cervical cancer is the leading cancer among the other female cancers. It develops in the cervix of women. It takes decades in development thus can be preventable if diagnosed at an early stage. The cervix is classified into three types Type I/II/III. The efficacy of the treatment depends on the diagnosis of the right type of cervix. There is a thin line difference between the three types. Thus, identification of the right type of cervix becomes a difficult task for the health care providers too. To aid this problem, we proposed an algorithm based on the standard transfer learning approach used for building a model that classifies cervix images. OBJECTIVES: The objective of this study is to develop a cervical cancer predictive model based on deep learning and transfer learning techniques that will recognize and classify the cervix images into one of the classes (Type 1/Type2/Type3). METHODS: Techniques used for carrying out the experimental work includes deep learning and Transfer Learning. The three pertained models namely InceptionV3, ResNet50, and VGG19 are used for creating ConvNet that will classify the cervix images. RESULTS: The result of the experiment reveals that the Inception v3 model is performing better than Vgg19 and ResNet50 with an accuracy of 96.1% on the cervical cancer dataset. CONCLUSION: In the future, augmentation techniques can be employed to achieve better accuracy.

show abstract

“…Support vector machine (SVM), LDA (Linear Discriminant Analysis), k-nearest neighbour (KNN), and ANN (Artificial Neural Networks) are the most frequently utilised classifiers in multi-cell cervical image analysis [21][22][23][24][25][26]. Numerous research studies have been conducted on the detection of cervical cancer, however the majority of these studies only focused on the segmentation of nuclei regions [27]. Cytoplasmic area segmentation is also crucial.…”

Section: Introductionmentioning

confidence: 99%

Edge Enhancement and Detection Approach on Cervical Cytology Images

Alias

Mustafa

Jamlos

et al. 2022

ARASET

View full text Add to dashboard Cite

Cervical cancer is a prevalent and fatal disease that affects women all over the world. This affects roughly 0.5 million women annually and kills over 0.3 million people. Recently, a significant amount of literature has emerged around the advancement of technologies for identifying cervical cancer cells in women. Previously, diagnosing cervical cancer was done manually, which could lead to false positives or negatives. The best way of interpreting Pap smear images and automatically diagnose cervical cancer are still up for debate among the researchers. Method used in this study is the contrast enhancement technique for pre-processing and edge detection-based for segmentation of the nucleus. In this study, the average performance results of the method showed an accuracy of 96.99% in the seven-class problem using Herlev dataset. The present finding also support this study which concluded the results of accuracy achieved for the algorithm used for nucleus detection is improved by 6.15% when comparing to previous work. The accuracy value is in the lines of earlier literature that achieved accuracy of the approach used above 90% for seven class of cells. The major feature of the suggested approach is an improvement in the ability to anticipate which cells are aberrant and which are normal. Adding more classifiers could improve the suggested system even further. Therefore, a cervical cancer screening system might utilize this framework to identify women who have precancerous lesions.

show abstract

Cervical Cancer Detection Using Segmentation on Pap smear Images

Cited by 15 publications

References 9 publications

Computer-Assisted Screening for Cervical Cancer Using Digital Image Processing of Pap Smear Images

Computer-Assisted Screening for Cervical Cancer Using Digital Image Processing of Pap Smear Images

Cervix Image Classification for Prognosis of Cervical Cancer using Deep Neural Network with Transfer Learning

Edge Enhancement and Detection Approach on Cervical Cytology Images

Contact Info

Product

Resources

About