Development and validation of a deep learning algorithm for pattern-based classification system of cervical cancer from pathological sections

Background

Multi-center research has demonstrated that adopting Silva's pattern-based classification system (SPBC) enhances the clinical prognosis and facilitates hierarchical management of patients with endocervical adenocarcinomas (EAC). However, inconsistencies in SPBC can arise due to variations in pathologists' experience levels. Thus, the implementation of standardized decision-making tools becomes crucial to enhance the practicality of SPBC in clinical diagnosis and treatment.

Methods

We enrolled a total of 90 patients with EAC in this study, of which 63 were assigned to the training group, and the remaining 27 were allocated to the validation group. To create and validate the prediction models for SPBC, we utilized a deep learning system (DLS) and calculated the area under the receiver operating characteristic curve (AUC).

Results

In Silva pattern classification, ResNet50 achieved an average accuracy of 74.36% (63.64% for pattern A, 55.56% for pattern B, and 89.47% for pattern C respectively). Moreover, in test set, ResNet50 achieved an AUC of 0.69 for pattern A, 0.58 for pattern B, and 0.91 for pattern C.

Conclusions

We successfully established a DLS for SPBC, which holds the potential to aid pathologists in accurately classifying patients with EAC.

Endocervical adenocarcinomas and HPV genotyping in an HIV endemic milieu - a retrospective study

BACKGROUND

Cervical cancer is the most prevalent cancer in Mozambique, with endocervical adenocarcinoma accounting for approximately 5.5% of cases. Knowledge regarding the most prevalent HPV genotypes in endocervical adenocarcinoma is limited, within this setting. This study aimed to investigate human papillomavirus (HPV) prevalence and genotypes within a cohort of endocervical adenocarcinoma patients in the context of Mozambique's recently introduced vaccination programme, considering the country's HIV-endemic setting.

METHODS

Forty consecutive cases of endocervical adenocarcinoma diagnosed at Maputo Central Hospital between 2017 and 2018, with limited clinical data available, were included. Human immunodeficiency virus (HIV) status was determined through serological data or in situ hybridisation on histopathological slides. HPV detection was performed using a multi-methodological approach, including Anyplex II, in-house polymerase chain reaction (PCR), and chromogenic and fluorescent in situ hybridisation techniques.

RESULTS

All 40 cases exhibited HPV-dependent morphology. Fourteen of the 40 patients were HIV-positive. No significant differences were observed between the two groups regarding age, stage, or histopathological type. hrHPV16, 18, or 45 were detected in all cases. Notably, multiple hrHPV infections were identified exclusively in HIV-negative cases (10/26, p = 0.0075), with hrHPV18/45 co-infection being the most common (n = 8).

CONCLUSIONS

These findings suggest that the newly implemented quadrivalent vaccination programme has the potential to prevent morbidity and mortality from endocervical adenocarcinoma, irrespective of HIV infection status, in Mozambique's HIV-endemic environment.