Segmentation of acetowhite region in uterine cervical image based on deep learning.
Cervical cancer
deep learning
medical image segmentation
visual inspection with acetic acid
Journal
Technology and health care : official journal of the European Society for Engineering and Medicine
ISSN: 1878-7401
Titre abrégé: Technol Health Care
Pays: Netherlands
ID NLM: 9314590
Informations de publication
Date de publication:
2022
2022
Historique:
pubmed:
29
6
2021
medline:
1
4
2022
entrez:
28
6
2021
Statut:
ppublish
Résumé
Acetowhite (AW) region is a critical physiological phenomenon of precancerous lesions of cervical cancer. An accurate segmentation of the AW region can provide a useful diagnostic tool for gynecologic oncologists in screening cervical cancers. Traditional approaches for the segmentation of AW regions relied heavily on manual or semi-automatic methods. To automatically segment the AW regions from colposcope images. First, the cervical region was extracted from the original colposcope images by k-means clustering algorithm. Second, a deep learning-based image semantic segmentation model named DeepLab V3+ was used to segment the AW region from the cervical image. The results showed that, compared to the fuzzy clustering segmentation algorithm and the level set segmentation algorithm, the new method proposed in this study achieved a mean Jaccard Index (JI) accuracy of 63.6% (improved by 27.9% and 27.5% respectively), a mean specificity of 94.9% (improved by 55.8% and 32.3% respectively) and a mean accuracy of 91.2% (improved by 38.6% and 26.4% respectively). A mean sensitivity of 78.2% was achieved by the proposed method, which was 17.4% and 10.1% lower respectively. Compared to the image semantic segmentation models U-Net and PSPNet, the proposed method yielded a higher mean JI accuracy, mean sensitivity and mean accuracy. The improved segmentation performance suggested that the proposed method may serve as a useful complimentary tool in screening cervical cancer.
Sections du résumé
BACKGROUND
BACKGROUND
Acetowhite (AW) region is a critical physiological phenomenon of precancerous lesions of cervical cancer. An accurate segmentation of the AW region can provide a useful diagnostic tool for gynecologic oncologists in screening cervical cancers. Traditional approaches for the segmentation of AW regions relied heavily on manual or semi-automatic methods.
OBJECTIVE
OBJECTIVE
To automatically segment the AW regions from colposcope images.
METHODS
METHODS
First, the cervical region was extracted from the original colposcope images by k-means clustering algorithm. Second, a deep learning-based image semantic segmentation model named DeepLab V3+ was used to segment the AW region from the cervical image.
RESULTS
RESULTS
The results showed that, compared to the fuzzy clustering segmentation algorithm and the level set segmentation algorithm, the new method proposed in this study achieved a mean Jaccard Index (JI) accuracy of 63.6% (improved by 27.9% and 27.5% respectively), a mean specificity of 94.9% (improved by 55.8% and 32.3% respectively) and a mean accuracy of 91.2% (improved by 38.6% and 26.4% respectively). A mean sensitivity of 78.2% was achieved by the proposed method, which was 17.4% and 10.1% lower respectively. Compared to the image semantic segmentation models U-Net and PSPNet, the proposed method yielded a higher mean JI accuracy, mean sensitivity and mean accuracy.
CONCLUSION
CONCLUSIONS
The improved segmentation performance suggested that the proposed method may serve as a useful complimentary tool in screening cervical cancer.
Identifiants
pubmed: 34180439
pii: THC212890
doi: 10.3233/THC-212890
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM