Prediction using hierarchical data: Applications for automated detection of cervical cancer

Triage Value of Cervical Exfoliated Cell DNA Ploidy Analysis in Cervical High-Risk Human Papillomavirus-Positive Women

OBJECTIVE

This study aimed to investigate the triage value obtained in DNA ploidy analysis of cervical exfoliated cells in women with high-risk human papillomavirus (HR-HPV)-positive status in the primary screening of cervical cancer.

METHODS

The authors selected 3,000 HR-HPV-positive women for cervical exfoliated cell sampling and conducted DNA ploidy analysis, liquid-based cytology (LBC), colposcopy, and cervical biopsy. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of high-grade squamous intraepithelial lesion (HSIL)-positive detection between DNA ploidy analysis and LBC were compared according to histopathology diagnosis as the golden criteria, and the efficacy of predicting HSIL-positive immediate risk was evaluated.

RESULTS

A total of 2,892 HR-HPV-positive women were enrolled in the investigation. For HSIL+ women, the DNA ploidy group showed a significantly higher sensitivity (CIN2+: 79.21% vs 65.35%, p = .022; CIN3+: 81.48% vs 70.37%, p = .013), lower specificity (CIN2+: 85.00% vs 96.59%, p < .001; CIN3+: 84.14% vs 93.41%, p < .001), and lower PPV (CIN2+: 16.23% vs 29.33%, p = .001; CIN3+: 8.92% vs 16.89%, p = .002) compared with the LBC group, whereas the NPV showed no significant difference. Compared with LBC alone in diagnosing HSIL, DNA ploidy combined with LBC showed higher specificity (CIN2+: 99.21% vs 96.59%, p = .003; CIN3+: 96.48% vs 93.41%, p < .001) and higher PPV (CIN2+: 41.35% vs 29.33%, p = .022; CIN3+: 24.81% vs 16.89%, p = .028), whereas no significant difference was observed in the sensitivity (CIN2+: 54.46% vs 65.35%, p = .063; CIN3+: 61.11% vs 70.37%, p = .221) and NPV ( p > .05). Among the HR-HPV-positive women positive for DNA ploidy, the imminent risk of CIN2+ and CIN3+ were 15.62% and 8.92%, respectively, above the threshold for the colposcopy positive rate. Among the positive cases both for DNA ploidy and the LBC result of negative for intraepithelial lesion or malignancy, the immediate risk of CIN3+ was 3.31%, below the threshold for colposcopy positive rate. Besides, for women with LBC result of ASC-US and above, the immediate risk of CIN3+ was greater than 4%.

CONCLUSIONS

The DNA ploidy analysis can be used as an effective triage method for HR-HPV-positive women during the primary screening of cervical cancer, although it can provide higher specificity when combined with LBC and reduce the referral rate for colposcopy.

Cervical Cancer Detection Techniques: A Chronological Review

Cervical cancer is known as a major health problem globally, with high mortality as well as incidence rates. Over the years, there have been significant advancements in cervical cancer detection techniques, leading to improved accuracy, sensitivity, and specificity. This article provides a chronological review of cervical cancer detection techniques, from the traditional Pap smear test to the latest computer-aided detection (CAD) systems. The traditional method for cervical cancer screening is the Pap smear test. It consists of examining cervical cells under a microscope for abnormalities. However, this method is subjective and may miss precancerous lesions, leading to false negatives and a delayed diagnosis. Therefore, a growing interest has been in shown developing CAD methods to enhance cervical cancer screening. However, the effectiveness and reliability of CAD systems are still being evaluated. A systematic review of the literature was performed using the Scopus database to identify relevant studies on cervical cancer detection techniques published between 1996 and 2022. The search terms used included "(cervix OR cervical) AND (cancer OR tumor) AND (detect* OR diagnosis)". Studies were included if they reported on the development or evaluation of cervical cancer detection techniques, including traditional methods and CAD systems. The results of the review showed that CAD technology for cervical cancer detection has come a long way since it was introduced in the 1990s. Early CAD systems utilized image processing and pattern recognition techniques to analyze digital images of cervical cells, with limited success due to low sensitivity and specificity. In the early 2000s, machine learning (ML) algorithms were introduced to the CAD field for cervical cancer detection, allowing for more accurate and automated analysis of digital images of cervical cells. ML-based CAD systems have shown promise in several studies, with improved sensitivity and specificity reported compared to traditional screening methods. In summary, this chronological review of cervical cancer detection techniques highlights the significant advancements made in this field over the past few decades. ML-based CAD systems have shown promise for improving the accuracy and sensitivity of cervical cancer detection. The Hybrid Intelligent System for Cervical Cancer Diagnosis (HISCCD) and the Automated Cervical Screening System (ACSS) are two of the most promising CAD systems. Still, deeper validation and research are required before being broadly accepted. Continued innovation and collaboration in this field may help enhance cervical cancer detection as well as ultimately reduce the disease's burden on women worldwide.

Diagnostic Utility of Selective Upper Tract Urinary Cytology: A Systematic Review and Meta-analysis of the Literature

The diagnosis of upper tract urothelial carcinoma (UTUC) can be a challenging diagnostic pursuit. To date, there is no large-scale study assessing the statistical utility (eg, sensitivity and specificity) of selective cytology. Herein, we systematically reviewed and meta-analyzed the published literature to evaluate the efficacy of selective cytology for the detection of UTUC in patients with a suspicious clinical profile Selective cytology confers a high specificity but marginal sensitivity for the detection of UTUC. The sensitivity is greater for high-grade UTUC lesions. The statistical assessment of its utility is limited by the heterogeneity and bias of previous studies.