Intelligent screening systems for cervical cancer

A Corresponding Region Fusion Framework for Multi-Modal Cervical Lesion Detection

Cervical lesion detection (CLD) using colposcopic images of multi-modality (acetic and iodine) is critical to computer-aided diagnosis (CAD) systems for accurate, objective, and comprehensive cervical cancer screening. To robustly capture lesion features and conform with clinical diagnosis practice, we propose a novel corresponding region fusion network (CRFNet) for multi-modal CLD. CRFNet first extracts feature maps and generates proposals for each modality, then performs proposal shifting to obtain corresponding regions under large position shifts between modalities, and finally fuses those region features with a new corresponding channel attention to detect lesion regions on both modalities. To evaluate CRFNet, we build a large multi-modal colposcopic image dataset collected from our collaborative hospital. We show that our proposed CRFNet surpasses known single-modal and multi-modal CLD methods and achieves state-of-the-art performance, especially in terms of Average Precision.

Advancement in Deep Learning Methods for Diagnosis and Prognosis of Cervical Cancer

Cervical cancer is the leading cause of death in women, mainly in developing countries, including India. Recent advancements in technologies could allow for more rapid, cost-effective, and sensitive screening and treatment measures for cervical cancer. To this end, deep learning-based methods have received importance for classifying cervical cancer patients into different risk groups. Furthermore, deep learning models are now available to study the progression and treatment of cancerous cervical conditions. Undoubtedly, deep learning methods can enhance our knowledge toward a better understanding of cervical cancer progression. However, it is essential to thoroughly validate the deep learning-based models before they can be implicated in everyday clinical practice. This work reviews recent development in deep learning approaches employed in cervical cancer diagnosis and prognosis. Further, we provide an overview of recent methods and databases leveraging these new approaches for cervical cancer risk prediction and patient outcomes. Finally, we conclude the state-of-the-art approaches for future research opportunities in this domain.

Discriminative Cervical Lesion Detection in Colposcopic Images with Global Class Activation and Local Bin Excitation

Accurate cervical lesion detection (CLD) methods using colposcopic images are highly demanded in computer-aided diagnosis (CAD) for automatic diagnosis of High-grade Squamous Intraepithelial Lesions (HSIL). However, compared to natural scene images, the specific characteristics of colposcopic images, such as low contrast, visual similarity, and ambiguous lesion boundaries, pose difficulties to accurately locating HSIL regions and also significantly impede the performance improvement of existing CLD approaches. To tackle these difficulties and better capture cervical lesions, we develop novel feature enhancing mechanisms from both global and local perspectives, and propose a new discriminative CLD framework, called CervixNet, with a Global Class Activation (GCA) module and a Local Bin Excitation (LBE) module. Specifically, the GCA module learns discriminative features by introducing an auxiliary classifier, and guides our model to focus on HSIL regions while ignoring noisy regions. It globally facilitates the feature extraction process and helps boost feature discriminability. Further, our LBE module excites lesion features in a local manner, and allows the lesion regions to be more fine-grained enhanced by explicitly modelling the inter-dependencies among bins of proposal feature. Extensive experiments on a number of 9888 clinical colposcopic images verify the superiority of our method (AP _.75=20.45) over state-of-the-art models on four widely used metrics.

Automated Cell Nuclei Segmentation on Cervical Smear Images Using Structure Analysis

Cervical cancer is a common cancer that affects women around the world, and it is also the most common cancer in the developing countries. The cancer burden has increased due to several factors, such as population growth and ageing. In the early century, the systematization of cervical cancer cells takes some time to process manually, and the result that comes out is also inaccurate. This article presents a new nucleus segmentation on pap smear cell images based on structured analysis or morphological approach. Morphology is a broad set of image processing operations that process images based on shape, size and structure. This operation applies a structural element of the image to create an output image of the same size. The most basic of these operations are dilation and erosion. The results of the numerical analysis indicate that the proposed method achieved about 94.38% (sensitivity), 82.56% (specificity) and 93% (accuracy). Also, the resulting performance was compared to a few existing techniques such as Bradley Method, Nick Method and Sauvola Method. The results presented here may facilitate improvements in the detection method of the pap smear cell image to resolve the time-consuming issue and support better system performance to prevent low precision result of the Human Papilloma Virus (HPV) stages. The main impact of this paper is will help the doctor to identify the patient disease based on Pap smear analysis such as cervical cancer and increase the percentages of accuracy compared to the conventional method. Successful implementation of the nucleus detection techniques on Pap smear image can become a standard technique for the diagnosis of various microbiological infections such as Malaria and Tuberculosis.

Using Dynamic Features for Automatic Cervical Precancer Detection

Cervical cancer remains a major public health concern in developing countries due to financial and human resource constraints. Visual inspection with acetic acid (VIA) of the cervix was widely promoted and routinely used as a low-cost primary screening test in low- and middle-income countries. It can be performed by a variety of health workers and the result is immediate. VIA provides a transient whitening effect which appears and disappears differently in precancerous and cancerous lesions, as compared to benign conditions. Colposcopes are often used during VIA to magnify the view of the cervix and allow clinicians to visually assess it. However, this assessment is generally subjective and unreliable even for experienced clinicians. Computer-aided techniques may improve the accuracy of VIA diagnosis and be an important determinant in the promotion of cervical cancer screening. This work proposes a smartphone-based solution that automatically detects cervical precancer from the dynamic features extracted from videos taken during VIA. The proposed solution achieves a sensitivity and specificity of 0.9 and 0.87 respectively, and could be a solution for screening in countries that suffer from the lack of expensive tools such as colposcopes and well-trained clinicians.

Convolutional neural networks in medical image understanding: a survey

Imaging techniques are used to capture anomalies of the human body. The captured images must be understood for diagnosis, prognosis and treatment planning of the anomalies. Medical image understanding is generally performed by skilled medical professionals. However, the scarce availability of human experts and the fatigue and rough estimate procedures involved with them limit the effectiveness of image understanding performed by skilled medical professionals. Convolutional neural networks (CNNs) are effective tools for image understanding. They have outperformed human experts in many image understanding tasks. This article aims to provide a comprehensive survey of applications of CNNs in medical image understanding. The underlying objective is to motivate medical image understanding researchers to extensively apply CNNs in their research and diagnosis. A brief introduction to CNNs has been presented. A discussion on CNN and its various award-winning frameworks have been presented. The major medical image understanding tasks, namely image classification, segmentation, localization and detection have been introduced. Applications of CNN in medical image understanding of the ailments of brain, breast, lung and other organs have been surveyed critically and comprehensively. A critical discussion on some of the challenges is also presented.

A Review of Computational Methods for Cervical Cells Segmentation and Abnormality Classification

Cervical cancer is the one of the most common cancers in women worldwide, affecting around 570,000 new patients each year. Although there have been great improvements over the years, current screening procedures can still suffer from long and tedious workflows and ambiguities. The increasing interest in the development of computer-aided solutions for cervical cancer screening is to aid with these common practical difficulties, which are especially frequent in the low-income countries where most deaths caused by cervical cancer occur. In this review, an overview of the disease and its current screening procedures is firstly introduced. Furthermore, an in-depth analysis of the most relevant computational methods available on the literature for cervical cells analysis is presented. Particularly, this work focuses on topics related to automated quality assessment, segmentation and classification, including an extensive literature review and respective critical discussion. Since the major goal of this timely review is to support the development of new automated tools that can facilitate cervical screening procedures, this work also provides some considerations regarding the next generation of computer-aided diagnosis systems and future research directions.

Assessment of knowledge, attitudes, and behaviors regarding breast and cervical cancer among women in western Turkey

Objective

We aimed to assess knowledge, attitudes, and practices regarding breast and cervical cancer and screening methods among women living western Turkey.

Methods

A questionnaire survey was administered to women aged ≥21 years. Data were collected using a 12-item questionnaire measuring women's knowledge, attitudes, and practice levels, including among participants who were health workers.

Results

A total 668 women were included in the study. The average age was 37.48 ± 11.85 years. Most women had a primary-level education (43.4%) and most (50.3%) were homemakers; 27.1% of participants were health care workers. The differences in age, education, and occupation among participants were evaluated according to whether participants perform breast self-examination and have undergone Pap testing. The distribution of women according to age group showed that with increased age, the frequency of performing these two behaviors decreased, with women over 55 years old accounting for a significantly higher proportion than other age groups.

Conclusions

In our study, the level of knowledge and attitudes regarding breast and cervical cancers among women was similar to that in previous studies and was higher than expected, especially among women who were health workers. However, all women had inadequate frequency of performing screening tests.

Multi-feature based Benchmark for Cervical Dysplasia Classification Evaluation

Cervical cancer is one of the most common types of cancer in women worldwide. Most deaths due to the disease occur in less developed areas of the world. In this work, we introduce a new image dataset along with expert annotated diagnoses for evaluating image-based cervical disease classification algorithms. A large number of Cervigram^® images are selected from a database provided by the US National Cancer Institute. For each image, we extract three complementary pyramid features: Pyramid histogram in L*A*B* color space (PLAB), Pyramid Histogram of Oriented Gradients (PHOG), and Pyramid histogram of Local Binary Patterns (PLBP). Other than hand-crafted pyramid features, we investigate the performance of convolutional neural network (CNN) features for cervical disease classification. Our experimental results demonstrate the effectiveness of both our hand-crafted and our deep features. We intend to release this multi-feature dataset and our extensive evaluations using seven classic classifiers can serve as the baseline.

Lifetime Distributions from Tracking Individual BC3H1 Cells Subjected to Yessotoxin

This work shows examples of lifetime distributions for individual BC3H1 cells after start of exposure to the marine toxin yessotoxin (YTX) in an experimental dish. The present tracking of many single cells from time-lapse microscopy data demonstrates the complexity in individual cell fate and which can be masked in aggregate properties. This contribution also demonstrates the general practicality of cell tracking. It can serve as a conceptually simple and non-intrusive method for high throughput early analysis of cytotoxic effects to assess early and late time points relevant for further analyzes or to assess for variability and sub-populations of interest. The present examples of lifetime distributions seem partly to reflect different cell death modalities. Differences between cell lifetime distributions derived from populations in different experimental dishes can potentially provide measures of inter-cellular influence. Such outcomes may help to understand tumor-cell resistance to drug therapy and to predict the probability of metastasis.