Cervical cancer is a very common and fatal type of cancer in women. Cytopathology images are often used to screen for this cancer. Given that there is a possibility that many errors can occur during manual screening, a computer-aided diagnosis system based on deep learning has been developed. Deep learning methods require a fixed dimension of input images, but the dimensions of clinical medical images are inconsistent. The aspect ratios of the images suffer while resizing them directly. Clinically, the aspect ratios of cells inside cytopathological images provide important information for doctors to diagnose cancer. Therefore, it is difficult to resize directly. However, many existing studies have resized the images directly and have obtained highly robust classification results. To determine a reasonable interpretation, we have conducted a series of comparative experiments. First, the raw data of the SIPaKMeD dataset are pre-processed to obtain standard and scaled datasets. Then, the datasets are resized to 224 × 224 pixels. Finally, 22 deep learning models are used to classify the standard and scaled datasets. The results of the study indicate that deep learning models are robust to changes in the aspect ratio of cells in cervical cytopathological images. This conclusion is also validated via the Herlev dataset.

Cervical cancer, one of the most common fatal cancers among women, can be prevented by regular screening to detect any precancerous lesions at early stages and treat them. Pap smear test is a widely performed screening technique for early detection of cervical cancer, whereas this manual screening method suffers from high false-positive results because of human errors. To improve the manual screening practice, machine learning (ML) and deep learning (DL) based computer-aided diagnostic (CAD) systems have been investigated widely to classify cervical Pap cells. Most of the existing studies require pre-segmented images to obtain good classification results. In contrast, accurate cervical cell segmentation is challenging because of cell clustering. Some studies rely on handcrafted features, which cannot guarantee the classification stage\'s optimality. Moreover, DL provides poor performance for a multiclass classification task when there is an uneven distribution of data, which is prevalent in the cervical cell dataset. This investigation has addressed those limitations by proposing DeepCervix, a hybrid deep feature fusion (HDFF) technique based on DL, to classify the cervical cells accurately. Our proposed method uses various DL models to capture more potential information to enhance classification performance. Our proposed HDFF method is tested on the publicly available SIPaKMeD dataset and compared the performance with base DL models and the late fusion (LF) method. For the SIPaKMeD dataset, we have obtained the state-of-the-art classification accuracy of 99.85%, 99.38%, and 99.14% for 2-class, 3-class, and 5-class classification. This method is also tested on the Herlev dataset and achieves an accuracy of 98.32% for 2-class and 90.32% for 7-class classification. The source code of the DeepCervix model is available at: https://github.com/Mamunur-20/DeepCervix.

Human papillomavirus (HPV) infection remains one of the most prominent cancer-causing DNA viruses, contributing to approximately 5% of human cancers. While association between HPV and cervical cancers has been well-established, evidence on the attribution of head and neck cancers (HNC) to HPV have been increasing in recent years. Among the cancer-causing HPV genotypes, HPV16 and 18 remain the major contributors to cancers across the globe. Nonetheless, the distribution of HPV genotypes in ethnically, geographically, and socio-economically diverse East, Southeast, and South Asia may differ from other parts of the world. In this review, we garner and provide updated insight into various aspects of HPV reported in recent years (2015-2021) in these regions. We included: (i) the HPV genotypes detected in normal cancers of the uterine cervix and head and neck, as well as the distribution of the HPV genotypes by geography and age groups; (ii) the laboratory diagnostic methods and treatment regimens used within these regions; and (iii) the oncogenic properties of HPV prototypes and their variants contributing to carcinogenesis. More importantly, we also unveil the similarities and discrepancies between these aspects, the areas lacking study, and the challenges faced in HPV studies.

OBJECTIVE: To describe cervical cancer screening participation among women in Taiwan under its population-based screening policy and to estimate the economic burden of disease attributable to avoidable disparities in cervical cancer (CC) screening.
METHODS: We identified a nationally-representative sample of females aged 30 years or above who were eligible for Pap smear testing in Taiwan from 1 January to 31 December 2013. An administrative database with detailed claims of health care utilization under the universal coverage health care system was used. Socioeconomic position of the female subjects was defined using the occupation classification, and two groups were specifically identified: general (O1) and low-income (O5) groups. Differences in screening rate, CC prevalence, and CC-attributable deaths were assessed between the two groups. Economic consequences as a result of screening inequalities were estimated using actual total health care spending (health care expenditure), monetary value per life-year and years of life lost for ill health and screening disparities (health as consumption good), and productivity losses alongside costs of social benefits (health as capital good).
RESULTS: A total of 301,057 enrolled females aged 30 years and older eligible for screening were identified. Overall, 3-year and 1-year screening rates among all subjects were 0.601 and 0.372, respectively. Impact of observed differences in screening translated to US$59,568 of health care spending in one year, 90.4% of which was specific to hospital admissions. When we viewed health as a consumption good and capital good, the impact of screening disparity on health losses through CC would be equivalent to US$78,095 and US$190,868, respectively.
CONCLUSIONS: Forgone health and economic benefits associated with inequalities in CC screening uptake can be considerable in productive women.

OBJECTIVE: Nursing is a professional job characterized by high stress. Stress could be associated with less practice of health promoting behaviors; however, no study has investigated the relationship between job stress and health screening behaviors among nurses. This study aimed to describe the rate of Pap smears in hospital nurses and examine the effects of job stress on receiving a Pap smear.
METHODS: This study was a cross-sectional survey. The study participants were 30,681 full-time female nurses who were at least 30 years of age working in 100 hospitals across Taiwan. The study participants filled out an anonymous structured questionnaire from May to July, 2011. The outcome variable was having a Pap test during the previous 3 years. The level of stress was measured by a 19-item scale, with higher scores indicating higher stress levels.
RESULTS: About 62.4% of the nurses had a Pap smear during the previous three years. Each point increase in the stress score decreased the likelihood of Pap smears (OR = .997, 95% CI: .995-.999), after adjustment for participant characteristics, health status, health behaviors, and hospital characteristics.
CONCLUSIONS: Despite more knowledge and higher accessibility, nurses were less likely to have Pap smear screening than the general population. A higher level of job stress was associated with a lower likelihood of having a Pap smear. Hospital administrators could help decrease work-related stress and improve stress adaption among nurses in order to improve their health screening behaviors.