Comparison of conventional Papanicolaou cytology samples with liquid-based cervical cytology samples from women in Pernambuco, Brazil

Effective reduction in inadequate Pap smears by using a saline-lubricated speculum and two glass slides

OBJECTIVE

The aim of the study was to propose a method using saline lubrication and two glass slides to reduce the proportion of inadequate Pap smears.

MATERIALS AND METHODS

This was a retrospective study of patients at a medical center in eastern Taiwan that performs 5000-6000 Pap smears annually. The extracted data only detailed the number and percentage of inadequate Pap smears. We applied two modifications to the conventional Pap smear technique. The first modification was lubricating the speculum with normal saline instead of jelly. The second modification was performing the smear on two glass slides instead of just one. We used the modified technique beginning in January 2017. Therefore, we collected data from 2016 (before the modified technique was employed) and 2018 (after the modified technique was employed). The categorical data are presented as numbers (percentages). The differences in the number and percentage of inadequate smears resulting from both techniques were assessed using the Chi-square test.

RESULTS

During 2016 and 2018, 28 and 2 women received inadequate Pap smears among the total of 594 and 613 women who received Pap smears, respectively. The proportion of inadequate Pap smears was 4.71% and 0.33% in 2016 and 2018, respectively (P < 0.001).

CONCLUSIONS

The use of this modified technique effectively reduced the percentage of inadequate Pap smears.

Automatic model for cervical cancer screening based on convolutional neural network: a retrospective, multicohort, multicenter study

Background

The incidence rates of cervical cancer in developing countries have been steeply increasing while the medical resources for prevention, detection, and treatment are still quite limited. Computer-based deep learning methods can achieve high-accuracy fast cancer screening. Such methods can lead to early diagnosis, effective treatment, and hopefully successful prevention of cervical cancer. In this work, we seek to construct a robust deep convolutional neural network (DCNN) model that can assist pathologists in screening cervical cancer.

Methods

ThinPrep cytologic test (TCT) images diagnosed by pathologists from many collaborating hospitals in different regions were collected. The images were divided into a training dataset (13,775 images), validation dataset (2301 images), and test dataset (408,030 images from 290 scanned copies) for training and effect evaluation of a faster region convolutional neural network (Faster R-CNN) system.

Results

The sensitivity and specificity of the proposed cervical cancer screening system was 99.4 and 34.8%, respectively, with an area under the curve (AUC) of 0.67. The model could also distinguish between negative and positive cells. The sensitivity values of the atypical squamous cells of undetermined significance (ASCUS), the low-grade squamous intraepithelial lesion (LSIL), and the high-grade squamous intraepithelial lesions (HSIL) were 89.3, 71.5, and 73.9%, respectively. This system could quickly classify the images and generate a test report in about 3 minutes. Hence, the system can reduce the burden on the pathologists and saves them valuable time to analyze more complex cases.

Conclusions

In our study, a CNN-based TCT cervical-cancer screening model was established through a retrospective study of multicenter TCT images. This model shows improved speed and accuracy for cervical cancer screening, and helps overcome the shortage of medical resources required for cervical cancer screening.

Cytopathologic evaluation of patients submitted to radiotherapy for uterine cervix cancer

Cervical cancer is an important public health problem. Pap smear is the leading strategy of screening programs for cervical cancer worldwide. However, delayed diagnosis leads to more aggressive and less effective treatments. Patients with uterine cervix malignancies who are referred for radiotherapy have advanced-stage disease, which results in high rates of locoregional recurrence. The use of radiotherapy as a treatment for cervical cancer causes morphological changes in neoplastic and non-neoplastic epithelial cells, as well as in stromal cells, which make it difficult to diagnose the residual lesion, resulting in a dilemma in cytopathological routine. Based on the difficulties of cytopathologic evaluation for the follow-up of patients treated with radiotherapy for cervical cancer, our objective was to describe the actinic cytopathic effects. Our paper was based on a structured review including the period from June 2015 to April 2016, aiming at an exploratory-descriptive study. Bibliographic investigations were carried out through selection and analysis of articles, list of authors and keywords, selection of new articles focused on the analysis of bibliographic references to previously selected documents, as well as textbooks of recognized merit. The most incident actinic cytopathological alterations as described in the literature are: cellular gigantism, nuclear and cytoplasmic vacuolization, dyskeratosis, bi- and multinucleated (B/M) cells, macro and multiple nucleoli, anisokaryosis, anisonucleolosis and nuclear pyknosis. To date, a protocol has not been established that can precisely differentiate the morphological characteristics between benign cells with actinic effects from recurrent malignant cells on post-radiotherapy smears.