Pap smear cell image classification using global MPEG-7 descriptors

Camargo, Luz Helena; Díaz, G. A.; Romero, E

doi:10.1186/1746-1596-8-s1-s38

Cited by 9 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most patients with cervical cancer, a high level of accuracy is not obtained when determining the stage of the disease. This problem has been approached from a computational perspective [2,3,4,7,10,13,17], however, based on the analysis of the state of the art, it has been identified that: the percentages of correct classification of stages of the disease can still be improved.…”

Section: Problematicmentioning

confidence: 99%

“…They use the Herlev University Hospital database, where, unlike the aforementioned methods that use the morphological characteristics of the cells, the proposed method uses the color space and texture information of the nucleus and cytoplasm. The classification algorithms used were KNN and SVM [3].…”

Section: Previous Workmentioning

confidence: 99%

“…Each sample examined may contain about 300,000 cells. In the literature related to pap smear [2,3,4,7,10,13,17] we can identify that the classification of the samples has been approached from a computational perspective.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Cervical Cancer Using Assembled Algorithms in Microscopic Images of Papanicolaou

Gómez¹,

Sánchez-DelaCruz²,

Mata³

2017

RCS

View full text Add to dashboard Cite

In Mexico cervical cancer is the second leading cause of death from malignant neoplasms in women, but this mortality rate has been reduced in recent years thanks to early detection programs as the pap smear test, which is aimed at finding pre-cancerous abnormalities in cells that cover the cervix. The pap smear test is an efficient medical test, but it presents problems at the moment of interpretation under the microscope, due to the large number of cells in the sample and others external factors. In order to solve this disadvantage, computational techniques are used to support the samples classification. In this research we propose to use assembled algorithms to construct a classifier. The database used is from Herlev University Hospital, the data were formulated as a binary classification problem. The results of the experiments (exhaustive search) show that using the combinations of algorithms Bagging+MultilayerPerceptron and AdaBoostM1+LMT is obtained a high percentage of correctly classified instances, 95.74%.

show abstract

Section: Problematicmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Cervical Cancer Using Assembled Algorithms in Microscopic Images of Papanicolaou

Gómez¹,

Sánchez-DelaCruz²,

Mata³

2017

RCS

View full text Add to dashboard Cite

show abstract

“…In order to solve the problem of overlap, [21–26] were proposed. After getting good segmentation results, we need to extract morphological and structural features of the nucleus and cytoplasm, and then use a classifier to classify these features to get pathological cells [27–30]. Due to the inefficiency of manual feature extraction, it is difficult to improve the performance of classification.…”

Section: Introductionmentioning

confidence: 99%

Cervical cancer detection in cervical smear images using deep pyramid inference with refinement and spatial‐aware booster

Liu

et al. 2020

IET image process

View full text Add to dashboard Cite

With the development of artificial intelligence and image processing technology, more and more intelligent diagnosis technologies are used in cervical cancer screening. Among them, the detection of cervical lesions by thin liquid‐based cytology is the most common method for cervical cancer screening. At present, most cervical cancer detection algorithms use the object detection technology of natural images, and often only minor modifications are made while ignoring the specificity of the complex application scenario of cervical lesions detection in cervical smear images. In this study, the authors combine the domain knowledge of cervical cancer detection and the characteristics of pathological cells to design a network and propose a booster for cervical cancer detection (CCDB). The booster mainly consists of two components: the refinement module and the spatial‐aware module. The characteristics of cancer cells are fully considered in the booster, and the booster is light and transplantable. As far as the authors know, they are the first to design a CCDB according to the characteristics of cervical cancer cells. Compared with baseline (Retinanet), the sensitivity at four false positives per image and average precision of the proposed method are improved by 2.79 and 7.2%, respectively.

show abstract