Cervical cancer detection and classification using Independent Level sets and multi SVMs

Kashyap, Debashree; Somani, Abhishek; Shekhar, Jatin; Bhan, Anupama; Dutta, Malay Kishore; Bürget, Radim; Říha, Kamil

doi:10.1109/tsp.2016.7760935

Cited by 37 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most literature, the classification of Pap smear images consists of a binary separation between normal and abnormal cell (two classes), using different methodologies such as Support Vector Machines (SVM) ( Chen et al, 2014 ; Chankong, Theera-Umpon & Auephanwiriyakul, 2014 ; Kashyap et al, 2016 ; Bora et al, 2017 ), k -Nearest Neighbours (kNN) ( Chankong, Theera-Umpon & Auephanwiriyakul, 2014 ; Bora et al, 2017 ; Marinakis, Dounias & Jantzen, 2009 ; Fekri Ershad, 2019 ), Fuzzy c -Means Algorithm (FCM) ( Chankong, Theera-Umpon & Auephanwiriyakul, 2014 ; William et al, 2019 ), k -Means clustering ( Paul, Bhowmik & Bhattacharjee, 2015 ), Artificial Neural Networks (ANN) ( Chankong, Theera-Umpon & Auephanwiriyakul, 2014 ), and, more recently, Convolutional Neural Networks (CNN) ( Zhang et al, 2017 ; Lin et al, 2019 ; Kurnianingsih et al, 2019 ).…”

Section: Related Workmentioning

confidence: 99%

Ordinal losses for classification of cervical cancer risk

Albuquerque

Cruz

Cardoso

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Cervical cancer is the fourth leading cause of cancer-related deaths in women, especially in low to middle-income countries. Despite the outburst of recent scientific advances, there is no totally effective treatment, especially when diagnosed in an advanced stage. Screening tests, such as cytology or colposcopy, have been responsible for a substantial decrease in cervical cancer deaths. Cervical cancer automatic screening via Pap smear is a highly valuable cell imaging-based detection tool, where cells must be classified as being within one of a multitude of ordinal classes, ranging from abnormal to normal. Current approaches to ordinal inference for neural networks are found to not sufficiently take advantage of the ordinal problem or to be too uncompromising. A non-parametric ordinal loss for neuronal networks is proposed that promotes the output probabilities to follow a unimodal distribution. This is done by imposing a set of different constraints over all pairs of consecutive labels which allows for a more flexible decision boundary relative to approaches from the literature. Our proposed loss is contrasted against other methods from the literature by using a plethora of deep architectures. A first conclusion is the benefit of using non-parametric ordinal losses against parametric losses in cervical cancer risk prediction. Additionally, the proposed loss is found to be the top-performer in several cases. The best performing model scores an accuracy of 75.6% for seven classes and 81.3% for four classes.

show abstract

Section: Related Workmentioning

confidence: 99%

Ordinal losses for classification of cervical cancer risk

Albuquerque

Cruz

Cardoso

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Later, to detect the model does overfit or not, K-fold validation method is applied. Results are analyzed by accuracy, kappa, precision and recall [7].…”

Section: Classificationmentioning

confidence: 99%

Cervical Cancer Risk Factors: Classification and Mining Associations

Islam¹,

Ripon²,

Bhuiyan³

2020

csit

View full text Add to dashboard Cite

Women of all over the world suffer from a common cancer, named Cervical cancer. Cervical cancer cellsgrow slowly at the cervix. This cancer can be avoided if it is recognized and handled in its first stage. Now it is a keychallenge for Medical experts to identify such cancer before it develops extremely. Nowadays, data mining modelsare popularly used to extract hidden patterns from huge medical dataset. This paper introduces data miningtechinques for classification and finding associations in order to detect Cervical cancer at early stage. Afterpreprocessing, the dataset was tested on Decision Tree, Random Forest, Logistic Model Tree and Artificial NeuralNetwork. These methods achieve considerable success in case of both K-fold cross validations and randomly splitdataset. Association rules has been established for detecting comparatively riskier factors which are moreresponsible for cancer development. The proposed methodology can help Medical experts to conduct their researchon Cervical cancer.

show abstract

“…Three SVM-based approaches (standard SVM, SVM combined with RFE algorithm, and SVM combined with the PCA algorithm) are used to classify the cervical cancer dataset from the repository of University of California at Irvine [11]. Nucleus and cytoplasm segmentation and classification using multi-class SVM classifiers such as polynomial SVMs, quadratic SVMs, Gaussian RBF SVMs, and linear SVMs resulted in 95% accuracy [12]. SVMs were also used to separate the nucleus from the cervical smear model with 95.134% precision for adaptive segmentation based on the GVF Snake model [13].…”

Section: Related Workmentioning

confidence: 99%

Segmentation and Classification of Cervical Cells Using Deep Learning

et al. 2019

View full text Add to dashboard Cite

Cervical cancer is the fourth most prevalent disease in women. Accurate and timely cancer detection can save lives. Automatic and reliable cervical cancer detection methods can be devised through the accurate segmentation and classification of Pap smear cell images. This paper presents an approach to whole cervical cell segmentation using a mask regional convolutional neural network (Mask R-CNN) and classifies this using a smaller Visual Geometry Group-like Network (VGG-like Net). ResNet10 is used to make full use of spatial information and prior knowledge as the backbone of the Mask R-CNN. We evaluate our proposed method on the Herlev Pap Smear dataset. In the segmentation phase, when Mask R-CNN is applied on the whole cell, it outperforms the previous segmentation method in precision (0.92±0.06), recall (0.91±0.05) and ZSI (0.91±0.04). In the classification phase, VGG-like Net is applied on the whole segmented cell and yields a sensitivity score of more than 96% with low standard deviation (±2.8%) for the binary classification problem and yields a higher result of more than 95% with low standard deviation (maximum 4.2% in accuracy measurement) for the 7-class problem in terms of sensitivity, specificity, accuracy, h-mean, and F1 score.

show abstract

Cervical cancer detection and classification using Independent Level sets and multi SVMs

Cited by 37 publications

References 4 publications

Ordinal losses for classification of cervical cancer risk

Ordinal losses for classification of cervical cancer risk

Cervical Cancer Risk Factors: Classification and Mining Associations

Segmentation and Classification of Cervical Cells Using Deep Learning

Contact Info

Product

Resources

About