Textural Analysis of Pap Smears Images for k-NN and SVM Based Cervical Cancer Classification System

Amole, Abraham; Osalusi, Bamidele

doi:10.25046/aj030420

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, a reliable and automated segmentation or detection of abnormal nuclei and cytoplasm boundaries is determined to be the vital step of accurately estimating the abnormality of the cytoplasm and nucleus in a predominant manner [7]. Furthermore, a diversified number of previous works were contributed through the enforcement of models that include level set, morphological reconstruction and active contour model for effective and accurate nucleus and cytoplasmic boundaries [8]. The segmentation process over the normal cervical nuclei has proved to facilitate maximum accuracy.…”

Section: Eai Endorsed Transactions On Pervasive Health and Technologymentioning

confidence: 99%

Enhanced Boykov's graph cuts based segmentation for Cervical Cancer Detection

Balaji¹,

Suryanarayana²,

Sengathir³

2021

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

Introduction: Cervical cancer is considered as the major curse to women society of the world due to their low survival rate. However, the prognosis of cervical cancer at an early stage through periodic screening was identified to enhance the survival probability of the women patients around the world. Objective: In this paper, a Boykov-Kolmogorov Graph Cuts and Cloud Model-based Synergy Integrated Segmentation (BKGC-CMSIS) Technique for facilitating predominant cervical cancer detection from the pap smear images used for prognosis. Methods: This proposed BKGC-CMSIS scheme introduces an effective Boykov-Kolmogorov Graph Cuts-based image partitioning method that estimates the image data through a synergy cloud model for formulating objective functions. The objective function used in this proposed BKGC-CMSIS scheme includes a data item and a smooth term for boundary preservation in order to determine the deviation of each pixel corresponding to the different regions of the cervical pap smear cells. Results: Also, it identifies the data item through the utilization of X-condition cloud generator for determining and defining the accurate boundaries of cytoplasm and nuclei derived from the pap smear cells. This proposed BKGC-CMSIS scheme uses the merits of membership degree through the incorporation of the smooth term for estimating the degree of similarity existing among the neighboring regions of the cervical pap smear cells. Conclusion: The experimental results of this proposed BKGC-CMSIS scheme is also potent in enhancing the classification accuracy by 14% superior to the benchmarked cervical cancer detection schemes considered for investigation.

show abstract

Section: Eai Endorsed Transactions On Pervasive Health and Technologymentioning

confidence: 99%

Enhanced Boykov's graph cuts based segmentation for Cervical Cancer Detection

Balaji¹,

Suryanarayana²,

Sengathir³

2021

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

show abstract

“…In addition, the results of the proposed method provide an accuracy of 94.32%, which is the second-highest accuracy result compared to other studies in Table 7. The results of sensitivity and specificity of the proposed method provide better results compared to the results of Amole and Osalusi (2018) , which only reached 67.3% and 31.62% respectively. These results indicate that the majority voting ensemble method is an excel-lent and valid method for the classification of cervical cancer based on pap smear cells into two classes, namely normal and abnormal.…”

Section: Ensemble Methodsmentioning

confidence: 76%

Majority Voting as Ensemble Classifier for Cervical Cancer Classification

Desiani

Kresnawati

Arhami³

et al. 2023

Sci. Technol. Indones

View full text Add to dashboard Cite

Cervical cancer is one of the deadliest female cancers. Early identification of cervical cancer through pap smear cell image evaluation is one of the strategies to reduce cervical cancer cases. The classification methods that are often used are SVM, MLP, and K-NN. The weakness of the SVM method is that it is not efficient on large datasets. Meanwhile, in the MLP method, large amounts of data can increase the complexity of each layer, thereby affecting the duration of the weighting process. Moreover, the K-NN method is not efficient for data with a large number of attributes. The ensemble method is one of the techniques to overcome the limitations of a single classification method. The ensemble classification method combines the performance of several classification methods. This study proposes an ensemble method with the majority voting that can be used in cervical cancer classification based on pap smear images in the Herlev dataset. Majority Voting is used to integrate test results from the SVM, MLP, and KNN methods by looking at the majority results on the test data classification. The results of this study indicate that the accuracy results obtained in the ensemble method increased by 1.72% compared to the average accuracy value in SVM, MLP, and KNN. for sensitivity results, the results of the ensemble method were able to increase the sensitivity increase by 0.74% compared to the average of the three single classification methods. for specificity, the ensemble method can increase the specificity results by 3.4%. From the results of the study, it can be concluded that the ensemble method with the most votes is able to improve the classification performance of the single classification method in classifying cervical cancer abnormalities with pap smear images.

show abstract

“…So, the authors chose wavelet filtration technology with adaptive threshold scheme. Wavelets are widely used in various signal processing tasks [12,13], in particular in noise reduction tasks [14][15][16]. Denoising has three stages: direct wavelet transforms, application of a selected threshold scheme to every detailing component, inverse wavelet transforms.…”

Section: Classification Of Pulse Diversitymentioning

confidence: 99%