Deep Metric Learning for Cervical Image Classification
Cervical cancer is caused by the persistent infection of certain types of the Human Papillomavirus (HPV) and is a leading cause of female mortality particularly in low and middle-income countries (LMIC). Visual inspection of the cervix with acetic acid (VIA) is a commonly used technique in cervical...
Published in: | IEEE Access |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224396/ https://doi.org/10.1109/access.2021.3069346 |
id |
ftpubmed:oai:pubmedcentral.nih.gov:8224396 |
---|---|
record_format |
openpolar |
spelling |
ftpubmed:oai:pubmedcentral.nih.gov:8224396 2023-05-15T16:01:31+02:00 Deep Metric Learning for Cervical Image Classification PAL, ANABIK XUE, ZHIYUN BEFANO, BRIAN RODRIGUEZ, ANA CECILIA LONG, L. RODNEY SCHIFFMAN, MARK ANTANI, SAMEER 2021-03-29 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224396/ https://doi.org/10.1109/access.2021.3069346 en eng http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224396/ http://dx.doi.org/10.1109/access.2021.3069346 https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ CC-BY-NC-ND IEEE Access Article Text 2021 ftpubmed https://doi.org/10.1109/access.2021.3069346 2021-06-27T00:46:02Z Cervical cancer is caused by the persistent infection of certain types of the Human Papillomavirus (HPV) and is a leading cause of female mortality particularly in low and middle-income countries (LMIC). Visual inspection of the cervix with acetic acid (VIA) is a commonly used technique in cervical screening. While this technique is inexpensive, clinical assessment is highly subjective, and relatively poor reproducibility has been reported. A deep learning-based algorithm for automatic visual evaluation (AVE) of aceto-whitened cervical images was shown to be effective in detecting confirmed precancer (i.e. direct precursor to invasive cervical cancer). The images were selected from a large longitudinal study conducted by the National Cancer Institute in the Guanacaste province of Costa Rica. The training of AVE used annotation for cervix boundary, and the data scarcity challenge was dealt with manually optimized data augmentation. In contrast, we present a novel approach for cervical precancer detection using a deep metric learning-based (DML) framework which does not incorporate any effort for cervix boundary marking. The DML is an advanced learning strategy that can deal with data scarcity and bias training due to class imbalance data in a better way. Three different widely-used state-of-the-art DML techniques are evaluated- (a) Contrastive loss minimization, (b) N-pair embedding loss minimization, and, (c) Batch-hard loss minimization. Three popular Deep Convolutional Neural Networks (ResNet-50, MobileNet, NasNet) are configured for training with DML to produce class-separated (i.e. linearly separable) image feature descriptors. Finally, a K-Nearest Neighbor (KNN) classifier is trained with the extracted deep features. Both the feature quality and classification performance are quantitatively evaluated on the same data set as used in AVE. It shows that, unlike AVE, without using any data augmentation, the best model produced from our research improves specificity in disease detection without compromising ... Text DML PubMed Central (PMC) IEEE Access 9 53266 53275 |
institution |
Open Polar |
collection |
PubMed Central (PMC) |
op_collection_id |
ftpubmed |
language |
English |
topic |
Article |
spellingShingle |
Article PAL, ANABIK XUE, ZHIYUN BEFANO, BRIAN RODRIGUEZ, ANA CECILIA LONG, L. RODNEY SCHIFFMAN, MARK ANTANI, SAMEER Deep Metric Learning for Cervical Image Classification |
topic_facet |
Article |
description |
Cervical cancer is caused by the persistent infection of certain types of the Human Papillomavirus (HPV) and is a leading cause of female mortality particularly in low and middle-income countries (LMIC). Visual inspection of the cervix with acetic acid (VIA) is a commonly used technique in cervical screening. While this technique is inexpensive, clinical assessment is highly subjective, and relatively poor reproducibility has been reported. A deep learning-based algorithm for automatic visual evaluation (AVE) of aceto-whitened cervical images was shown to be effective in detecting confirmed precancer (i.e. direct precursor to invasive cervical cancer). The images were selected from a large longitudinal study conducted by the National Cancer Institute in the Guanacaste province of Costa Rica. The training of AVE used annotation for cervix boundary, and the data scarcity challenge was dealt with manually optimized data augmentation. In contrast, we present a novel approach for cervical precancer detection using a deep metric learning-based (DML) framework which does not incorporate any effort for cervix boundary marking. The DML is an advanced learning strategy that can deal with data scarcity and bias training due to class imbalance data in a better way. Three different widely-used state-of-the-art DML techniques are evaluated- (a) Contrastive loss minimization, (b) N-pair embedding loss minimization, and, (c) Batch-hard loss minimization. Three popular Deep Convolutional Neural Networks (ResNet-50, MobileNet, NasNet) are configured for training with DML to produce class-separated (i.e. linearly separable) image feature descriptors. Finally, a K-Nearest Neighbor (KNN) classifier is trained with the extracted deep features. Both the feature quality and classification performance are quantitatively evaluated on the same data set as used in AVE. It shows that, unlike AVE, without using any data augmentation, the best model produced from our research improves specificity in disease detection without compromising ... |
format |
Text |
author |
PAL, ANABIK XUE, ZHIYUN BEFANO, BRIAN RODRIGUEZ, ANA CECILIA LONG, L. RODNEY SCHIFFMAN, MARK ANTANI, SAMEER |
author_facet |
PAL, ANABIK XUE, ZHIYUN BEFANO, BRIAN RODRIGUEZ, ANA CECILIA LONG, L. RODNEY SCHIFFMAN, MARK ANTANI, SAMEER |
author_sort |
PAL, ANABIK |
title |
Deep Metric Learning for Cervical Image Classification |
title_short |
Deep Metric Learning for Cervical Image Classification |
title_full |
Deep Metric Learning for Cervical Image Classification |
title_fullStr |
Deep Metric Learning for Cervical Image Classification |
title_full_unstemmed |
Deep Metric Learning for Cervical Image Classification |
title_sort |
deep metric learning for cervical image classification |
publishDate |
2021 |
url |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224396/ https://doi.org/10.1109/access.2021.3069346 |
genre |
DML |
genre_facet |
DML |
op_source |
IEEE Access |
op_relation |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8224396/ http://dx.doi.org/10.1109/access.2021.3069346 |
op_rights |
https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ |
op_rightsnorm |
CC-BY-NC-ND |
op_doi |
https://doi.org/10.1109/access.2021.3069346 |
container_title |
IEEE Access |
container_volume |
9 |
container_start_page |
53266 |
op_container_end_page |
53275 |
_version_ |
1766397335229693952 |