HSIL Colposcopy Image Segmentation Using Improved U-Net

Liu, Juanqin; Chen, Qili; Fan, Junfang

doi:10.1109/yac53711.2021.9486581

Cited by 4 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The metrics are not like another models [ 30 , 31 , 32 ] where the IoU index overcomes our results ( Figure 5 a–d). For example, in [ 7 ] a Unet network was used for colposcopy image classification based on a Resnet model, with an IoU value of more than 0.5.…”

Section: Discussioncontrasting

confidence: 94%

Section: Discussionsupporting

confidence: 60%

“…The U-Net was shown to be the most appropriate for this task because it is normally the most useful model in biological image segmentation. Recent literature agrees with this last proposition, e.g., Liu et al [30] compared U-Net, FCN and SegNet models as an image segmentation method for cervical squamous intraepithelial lesions, the results indicated that Unet outperformance the other two models with the following scores: average pixel accuracy (MPA) of 0.8736, the average intersection (MIoU) of 0.7786, and the frequency weight intersection (FWIoU) of 0.7895. In the same way, Liu et al [31] reported Unet as colposcopy image segmentation where the experimental results showed that the proposed model has a better effect on colposcopy cervical image segmentation.…”

Section: Discussionsupporting

confidence: 57%

See 2 more Smart Citations

Radiomics Diagnostic Tool Based on Deep Learning for Colposcopy Image Classification

et al. 2022

View full text Add to dashboard Cite

Background: Colposcopy imaging is widely used to diagnose, treat and follow-up on premalignant and malignant lesions in the vulva, vagina, and cervix. Thus, deep learning algorithms are being used widely in cervical cancer diagnosis tools. In this study, we developed and preliminarily validated a model based on the Unet network plus SVM to classify cervical lesions on colposcopy images. Methodology: Two sets of images were used: the Intel & Mobile ODT Cervical Cancer Screening public dataset, and a private dataset from a public hospital in Ecuador during a routine colposcopy, after the application of acetic acid and lugol. For the latter, the corresponding clinical information was collected, specifically cytology on the PAP smear and the screening of human papillomavirus testing, prior to colposcopy. The lesions of the cervix or regions of interest were segmented and classified by the Unet and the SVM model, respectively. Results: The CAD system was evaluated for the ability to predict the risk of cervical cancer. The lesion segmentation metric results indicate a DICE of 50%, a precision of 65%, and an accuracy of 80%. The classification results’ sensitivity, specificity, and accuracy were 70%, 48.8%, and 58%, respectively. Randomly, 20 images were selected and sent to 13 expert colposcopists for a statistical comparison between visual evaluation experts and the CAD tool (p-value of 0.597). Conclusion: The CAD system needs to improve but could be acceptable in an environment where women have limited access to clinicians for the diagnosis, follow-up, and treatment of cervical cancer; better performance is possible through the exploration of other deep learning methods with larger datasets.

show abstract

Section: Discussioncontrasting

confidence: 94%

Section: Discussionsupporting

confidence: 60%

Section: Discussionsupporting

confidence: 57%

See 1 more Smart Citation

Radiomics Diagnostic Tool Based on Deep Learning for Colposcopy Image Classification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The performance of cervix segmentation significantly affects the accuracy of diagnosis when analyzing colposcopy and is an essential step in training deep learning-based models. Previous studies utilized segmentation and object detection models to extract the ROI in a supervised manner [ 19 , 20 ]. Supervised learning can achieve high performance, but annotating the cervix region for every colposcopy image is not only a subjective judgment but is also burdensome for doctors.…”

Section: Introductionmentioning

confidence: 99%

Encoder-Weighted W-Net for Unsupervised Segmentation of Cervix Region in Colposcopy Images

Park

Yang

Roh

et al. 2022

Cancers

View full text Add to dashboard Cite

Cervical cancer can be prevented and treated better if it is diagnosed early. Colposcopy, a way of clinically looking at the cervix region, is an efficient method for cervical cancer screening and its early detection. The cervix region segmentation significantly affects the performance of computer-aided diagnostics using a colposcopy, particularly cervical intraepithelial neoplasia (CIN) classification. However, there are few studies of cervix segmentation in colposcopy, and no studies of fully unsupervised cervix region detection without image pre- and post-processing. In this study, we propose a deep learning-based unsupervised method to identify cervix regions without pre- and post-processing. A new loss function and a novel scheduling scheme for the baseline W-Net are proposed for fully unsupervised cervix region segmentation in colposcopy. The experimental results showed that the proposed method achieved the best performance in the cervix segmentation with a Dice coefficient of 0.71 with less computational cost. The proposed method produced cervix segmentation masks with more reduction in outliers and can be applied before CIN detection or other diagnoses to improve diagnostic performance. Our results demonstrate that the proposed method not only assists medical specialists in diagnosis in practical situations but also shows the potential of an unsupervised segmentation approach in colposcopy.

show abstract

“…Yuan [8] replace the encoder of vanilla UNet with ResNet-50 to enhance the feature extraction capability. Liu [16] modify the basic convolutional block in UNet via sub-coding modules and attempt to segment HSIL area based on a small dataset through intensive data augmentation. Shinohara [17] improve the discrimination on lesion characteristics by fusing the pre-and post-acetic-acid images.…”

mentioning

confidence: 99%

Cervical lesion segmentation via transformer-based network with attention and boundary-aware modules

Shen,

Lu,

et al. 2024

Preprint

View full text Add to dashboard Cite

Colposcopic diagnosis and directed biopsy is the foundation of cervical cancer screening. In the procedure of colposcopy, automatic segmentation of cervical lesion in colposcopic images can provide great assistance and convenience especially in underdeveloped region. However, the existing methods based on Convolutional Neural Networks only differentiate the abnormality from healthy tissue, which is hard to further subdivide the lesion. In this paper, a Transformer-based network TABNet is proposed which can precisely extract the cervical lesion and recognize the corresponding category of each lesion. Unlike the other CNN-based methods, a more powerful vision transformer is adopted as the encoder. Three effective modules in decoder are constructed to integrate the advance in attention mechanism and boundary-aware prior knowledge. Extensive experiments on a large clinical colposcopic image dataset show that TABNet outperforms the existing state-of-art methods and achieves great improvement. Compared with nnUNet, our proposed model improves the mean DSC by 7.74% and mean IoU by 8.51%, respectively.

show abstract

HSIL Colposcopy Image Segmentation Using Improved U-Net

Cited by 4 publications

References 19 publications

Radiomics Diagnostic Tool Based on Deep Learning for Colposcopy Image Classification

Radiomics Diagnostic Tool Based on Deep Learning for Colposcopy Image Classification

Encoder-Weighted W-Net for Unsupervised Segmentation of Cervix Region in Colposcopy Images

Cervical lesion segmentation via transformer-based network with attention and boundary-aware modules

Contact Info

Product

Resources

About