Adaptation of CytoProcessor for cervical cancer screening of challenging slides

Digital cytology part 2: artificial intelligence in cytology: a concept paper with review and recommendations from the American Society of Cytopathology Digital Cytology Task Force

Digital cytology and artificial intelligence (AI) are gaining greater adoption in the cytology laboratory. However, peer-reviewed real-world data and literature are lacking in regard to the current clinical landscape. The American Society of Cytopathology in conjunction with the International Academy of Cytology and the Digital Pathology Association established a special task force comprising 20 members with expertise and/or interest in digital cytology. The aim of the group was to investigate the feasibility of incorporating digital cytology, specifically cytology whole slide scanning and AI applications, into the workflow of the laboratory. In turn, the impact on cytopathologists, cytologists (cytotechnologists), and cytology departments were also assessed. The task force reviewed existing literature on digital cytology, conducted a worldwide survey, and held a virtual roundtable discussion on digital cytology and AI with multiple industry corporate representatives. This white paper, presented in 2 parts, summarizes the current state of digital cytology and AI practice in global cytology practice. Part 1 of the white paper is presented as a separate paper which details a review and best practice recommendations for incorporating digital cytology into practice. Part 2 of the white paper presented here provides a comprehensive review of AI in cytology practice along with best practice recommendations and legal considerations. Additionally, the cytology global survey results highlighting current AI practices by various laboratories, as well as current attitudes, are reported.

Diagnostic utility of ThinPrep Imaging System® for detecting atypical glandular cells in cervical smear samples

INTRODUCTION

The ThinPrep Imaging System® (TIS) is an automated system that has now been used for over 20 years in the primary screening of ThinPrep liquid-based cervical samples. Although there are a lot of publications about the diagnostic utility of this method in squamous cell lesions, which has advantages such as time-saving and standardization, there are only a few publications on this issue in glandular cell lesions in the literature. We aimed in this study to investigate the diagnostic utility of the system in the detection of premalignant and malignant glandular lesions in cervical smears.

MATERIAL AND METHOD

Our study was conducted retrospectively, and a total of 126 cervical smear samples between 2010 and 2022 that have histological confirmation of endometrial adenocarcinoma (EAC), endocervical adenocarcinoma (ECAC), or adenocarcinoma in situ (AİS), were included. These samples were re-evaluated by manual and TIS by two experienced pathologists, and the results were compared in terms of sensitivity.

RESULTS

We found out that 70 of the 126 smear samples have atypical glandular cells. We detect 48 cases (48/70) (sensitivity 68.5%) in manual examination, however TIS successfully determined 66 cases (66/70) (sensitivity 94.3%). In 4 cases (5.7%) TIS could not detect the atypical cells within the 22 areas.

CONCLUSION

TIS is quite an effective method with a high sensitivity for detecting atypical glandular cells in cervical smears, like detecting squamous cell anomalies. Imposing this system in our laboratory and using them appropriately, save us time and help to ensure standardization. Additionally, it may be a good way to adopt artificial intelligence and digital pathology in today's world.

Scrutinizing high-risk patients from ASC-US cytology via a deep learning model

BACKGROUND

Atypical squamous cells of undetermined significance (ASC-US) is the most frequent but ambiguous abnormal Papanicolaou (Pap) interpretation and is generally triaged by high-risk human papillomavirus (hrHPV) testing before colposcopy. This study aimed to evaluate the performance of an artificial intelligence (AI)-based triage system to predict ASC-US cytology for cervical intraepithelial neoplasia 2+ lesions (CIN2+).

METHODS

More than 60,000 images were used to train this proposed deep learning-based ASC-US triage system, where both cell-level and slide-level information were extracted. In total, 1967 consecutive ASC-US Paps from 2017 to 2019 were included in this study. Histological follow-ups were retrieved to compare the triage performance between the AI system and hrHPV in 622 patients with simultaneous hrHPV testing.

RESULTS

In the triage of women with ASC-US cytology for CIN2+, our system attained equivalent sensitivity (92.9%; 95% confidence interval [CI], 75.0%-98.8%) and higher specificity (49.7%; 95% CI, 45.6%-53.8%) than hrHPV testing (sensitivity: 89.3%; 95% CI, 70.6%-97.2%; specificity: 34.3%; 95% CI, 30.6%-38.3%) without requiring additional patient examination or testing. Additionally, the independence of this system from hrHPV testing (κ = 0.138) indicated that these 2 different methods could be used to triage ASC-US as an alternative way.

CONCLUSION

This de novo deep learning-based system can triage ASC-US cytology for CIN2+ with a performance superior to hrHPV testing and without incurring additional expenses.

High variability in anatomic patterns of cutaneous photodamage: a population-based study

BACKGROUND

Skin cancer is strongly associated with photodamaged skin, but body sites are often referred to as 'exposed' or 'unexposed' to sun without recognizing extent of site-specific variation.

OBJECTIVES

To assess whole-body patterns of photodamage in an Australian population.

METHODS

A random sample of adult residents of Queensland underwent imaging across 10 body sites. Photodamage was graded from images using an ordinal photonumeric scale. We used cluster analysis to identify whole-body photodamage patterns and prevalence proportion ratios (PPRs) to assess associated factors.

RESULTS

Of 190 adults (median age 52; 58% males), 58% showed severe or moderate-to-severe photodamage on most body sites. A higher proportion of woman had severe photodamage on the arms (upper: P = 0.002, lower: P = 0.034). A higher proportion of men had moderate or severe photodamage on the lower back (P = 0.004). We identified four photodamage patterns: 'severe general' (n = 24, 13%), 'moderate-severe general' (n = 86, 45%), 'moderate-severe v-neck' (n = 40, 21%) and 'mild-moderate upper body' (n = 12, 6%). All participants with 'severe-general' photodamage were >50 years and more likely to have past skin cancer (PPR: 2.54, 95% CI: 1.44-4.49) than those with 'moderate-severe v-neck' photodamage. Those with 'moderate-severe general' photodamage showed similar associations and were more likely female (PPR: 1.33, 95% CI: 1.04-1.69). Past or current smoking was associated with having higher levels of photodamage, with no smokers in those with 'mild-moderate upper body' photodamage.

CONCLUSIONS

Moderate-to-severe photodamage across much of the body is common in Queensland adults and associated with age, sex, past skin cancer and smoking. Assuming a universal pattern of site-specific sun exposure could lead to spurious correlations, while accurate and objective assessment of site-specific photodamage can add to understanding of the development of sun-associated skin cancers, in particular site-specific skin carcinogenesis. Additionally, degree of site-specific photodamage has the potential to assist skin cancer screening.

Cervical cancer: Automation of Pap test screening

BACKGROUND

Cervical cancer progresses slowly, increasing the chance of early detection of pre-neoplastic lesions via Pap exam test and subsequently preventing deaths. However, the exam presents both false-negatives and false-positives results. Therefore, automatic methods (AMs) of reading the Pap test have been used to improve the quality control of the exam. We performed a literature review to evaluate the feasibility of implementing AMs in laboratories.

METHODS

This work reviewed scientific publications regarding automated cytology from the last 15 years. The terms used were "Papanicolaou test" and "Automated cytology screening" in Portuguese, English, and Spanish, in the three scientific databases (SCIELO, PUBMED, MEDLINE).

RESULTS

Of the resulting 787 articles, 34 were selected for a complete review, including three AMs: ThinPrep Imaging System, FocalPoint GS Imaging System and CytoProcessor. In total, 1 317 148 cytopathological slides were evaluated automatically, with 1 308 028 (99.3%) liquid-based cytology slides and 9120 (0.7%) conventional cytology smears. The AM diagnostic performances were statistically equal to or better than those of the manual method. AM use increased the detection of cellular abnormalities and reduced false-negatives. The average sample rejection rate was ≤3.5%.

CONCLUSION

AMs are relevant in quality control during the analytical phase of cervical cancer screening. This technology eliminates slide-handling steps and reduces the sample space, allowing professionals to focus on diagnostic interpretation while maintaining high-level care, which can reduce false-negatives. Further studies with conventional cytology are needed. The use of AM is still not so widespread in cytopathology laboratories.