Better resource utilization and quality of care for cervical cancer screening in low-resourced districts using an internet-based expert system

Accuracy of Smartphone Images of the Cervix After Acetic Acid Application for Diagnosing Cervical Intraepithelial Neoplasia Grade 2 or Greater in Women With Positive Cervical Screening: A Systematic Review and Meta-Analysis

PURPOSE

Smartphones are used in cervical screening for visual inspection after acetic acid or Lugol's iodine (VIA/VILI) application to capture and share images to improve the sensitivity and interobserver variability of VIA/VILI. We undertook a systematic review and meta-analysis assessing the diagnostic accuracy of smartphone images of the cervix at the time of VIA/VILI (termed S-VIA) in the detection of precancerous lesions in women undergoing cervical screening.

METHODS

This systematic review was conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Studies from January 1, 2010, to June 30, 2020, were assessed. MEDLINE/PubMed, Embase, CINAHL, Cochrane, and LILACS were searched. Cohort and cross-sectional studies were considered. S-VIA was compared with the reference standard of histopathology. We excluded studies where additional technology was added to the smartphone including artificial intelligence, enhanced visual assessment, and other algorithms to automatically diagnose precancerous lesions. The primary outcome was the accuracy of S-VIA for the diagnosis of cervical intraepithelial neoplasia grade 2 or greater (CIN 2+). Data were extracted, and we plotted the sensitivity, specificity, negative predictive value, and positive predictive value of S-VIA using forest plots. This study was prospectively registered with The International Prospective Register of Systematic Reviews:CRD42020204024.

RESULTS

Six thousand three studies were screened, 71 full texts assessed, and eight studies met criteria for inclusion, with six included in the final meta-analysis. The sensitivity of S-VIA for the diagnosis of CIN 2+ was 74.56% (95% CI, 70.16 to 78.95; I² 61.30%), specificity was 61.75% (95% CI, 56.35 to 67.15; I² 95.00%), negative predictive value was 93.71% (95% CI, 92.81 to 94.61; I² 0%), and positive predictive value was 26.97% (95% CI, 24.13 to 29.81; I² 61.3%).

CONCLUSION

Our results suggest that S-VIA has accuracy in the detection of CIN 2+ and may provide additional support to health care providers delivering care in low-resource settings.

Segmentation of acetowhite region in uterine cervical image based on deep learning

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

To automatically segment the AW regions from colposcope images.

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

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

The improved segmentation performance suggested that the proposed method may serve as a useful complimentary tool in screening cervical cancer.