Classification of Cervical-Cancer Using Pap-Smear Images: A Convolutional Neural Network Approach

Taha, Bilal; Dias, Jorge; Werghi, Naoufel

doi:10.1007/978-3-319-60964-5_23

Cited by 49 publications

(24 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Devi et al [ 24 ] discussed the different types of methods used for the detection of CC based on neural networks. Taha et al [ 25 ] proposed a deep learning approach for detecting cervix cancer from pap-smear images, employing pre-trained CNN architecture as a feature extractor and using the output features as input to train a Support Vector Machine Classifier. However, the methods mentioned above did not meet our requirements as they needed strict prerequisites.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic classification of cervical cancer from cytological images by using convolutional neural network

Yan

Liu

et al. 2018

Bioscience Reports

View full text Add to dashboard Cite

Cervical cancer (CC) is one of the most common gynecologic malignancies in the world. The incidence and mortality keep high in some remote and poor medical condition regions in China. In order to improve the current situation and promote the pathologists’ diagnostic accuracy of CC in such regions, we tried to propose an intelligent and efficient classification model for CC based on convolutional neural network (CNN) with relatively simple architecture compared with others. The model was trained and tested by two groups of image datasets, respectively, which were original image group with a volume of 3012 datasets and augmented image group with a volume of 108432 datasets. Each group has a number of fixed-size RGB images (227*227) of keratinizing squamous, non-keratinizing squamous, and basaloid squamous. The method of three-folder cross-validation was applied to the model. And the classification accuracy of the models, overall, 93.33% for original image group and 89.48% for augmented image group. The improvement of 3.85% has been achieved by using augmented images as input data for the model. The results got from paired-samples ttest indicated that two models’ classification accuracy has a significant difference (P<0.05). The developed scheme we proposed was useful for classifying CCs from cytological images and the model can be served as a pathologist assistance to improve the doctor’s diagnostic level of CC, which has a great meaning and huge potential application in poor medical condition areas in China.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Devi et al [ 24 ] only discussed the methods in theory which were not implemented. Taha et al [ 25 ] methods also needed pre-required work like accurate cell image segmentation which remained a tough problem especially when the images contained adherent cells.…”

Section: Introductionmentioning

confidence: 99%

Automatic classification of cervical cancer from cytological images by using convolutional neural network

Yan

Liu

et al. 2018

Bioscience Reports

View full text Add to dashboard Cite

show abstract

“…The CNN needs a large amount of training data to achieve good performance. Image augmentation (Lee et al, 2017;Taha et al, 2017 ;Zhang et al, 2017) helps in creating more number of training images artificially through different ways of processing such as random rotation, translation, scaling and flipping. In cervical cell images, size and intensity of the nucleus are considered the key features to distinguish the normal and the abnormal cells.…”

Section: Deep Convolution Neural Network For Malignancy Detection Andmentioning

confidence: 99%

“…The success of the traditional classification method mainly depends on the accuracy of the cell segmentation to extract features. Taha et al, (2017) proposed an idea to classify the cells directly without prior segmentation based on the deep feature learning using convolution neural network. They achieved good classification result and acquired 98.3 % accuracy on Herlev data set.…”

Section: Related Workmentioning

confidence: 99%

“…In Herlev data set, as the abnormal cells are more than the normal cells, disease diagnosis will be a bias towards the abnormal cells in the classifier. This has to be balanced to improve the performance of the classifier and improve the accuracy and the convergence rate of CNN (Taha et al, 2017;Ker et al, 2018). To exclude any bias in the classification, equal amounts of instances of each class were maintained in the training process.…”

Section: Data Augmentationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Convolution Neural Network for Malignancy Detection and Classification in Microscopic Uterine Cervix Cell Images

Shanthi

Faruqi

Hareesha

et al. 2019

Asian Pac J Cancer Prev

View full text Add to dashboard Cite

Objective: Automated Pap smear cervical screening is one of the most effective imaging based cancer detection tools used for categorizing cervical cell images as normal and abnormal. Traditional classification methods depend on hand-engineered features and show limitations in large, diverse datasets. Effective feature extraction requires an efficient image preprocessing and segmentation, which remains prominent challenge in the field of Pathology. In this paper, a deep learning concept is used for cell image classification in large datasets. Methods: This relatively proposed novel method, combines abstract and complicated representations of data acquired in a hierarchical architecture. Convolution Neural Network (CNN) learns meaningful kernels that simulate the extraction of visual features such as edges, size, shape and colors in image classification. A deep prediction model is built using such a CNN network to classify the various grades of cancer: normal, mild, moderate, severe and carcinoma. It is an effective computational model which uses multiple processing layers to learn complex features. A large dataset is prepared for this study by systematically augmenting the images in Herlev dataset. Result: Among the three sets considered for the study, the first set of single cell enhanced original images achieved an accuracy of 94.1% for 5 class, 96.2% for 4 class, 94.8% for 3 class and 95.7% for 2 class problems. The second set includes contour extracted images showed an accuracy of 92.14%, 92.9%, 94.7% and 89.9% for 5, 4, 3 and 2 class problems. The third set of binary images showed 85.07% for 5 class, 84% for 4 class, 92.07% for 3 class and highest accuracy of 99.97% for 2 class problems. Conclusion: The experimental results of the proposed model showed an effective classification of different grades of cancer in cervical cell images, exhibiting the extensive potential of deep learning in Pap smear cell image classification.

show abstract

Hierarchical and Robust Pathology Image Reading for High-Throughput Cervical Abnormality Screening

Zhou

Zhang

et al. 2020

Machine Learning in Medical Imaging

View full text Add to dashboard Cite

Classification of Cervical-Cancer Using Pap-Smear Images: A Convolutional Neural Network Approach

Cited by 49 publications

References 15 publications

Automatic classification of cervical cancer from cytological images by using convolutional neural network

Automatic classification of cervical cancer from cytological images by using convolutional neural network

Deep Convolution Neural Network for Malignancy Detection and Classification in Microscopic Uterine Cervix Cell Images

Hierarchical and Robust Pathology Image Reading for High-Throughput Cervical Abnormality Screening

Contact Info

Product

Resources

About