Given the increased interest in utilizing artificial intelligence as an assistive tool in the medical sector, colorectal polyp detection and classification using deep learning techniques has been an active area of research in recent years. The motivation for researching this topic is that physicians miss polyps from time to time due to fatigue and lack of experience carrying out the procedure. Unidentified polyps can cause further complications and ultimately lead to colorectal cancer (CRC), one of the leading causes of cancer mortality. Although various techniques have been presented recently, several key issues, such as the lack of enough training data, white light reflection, and blur affect the performance of such methods. This paper presents a survey on recently proposed methods for detecting polyps from colonoscopy. The survey covers benchmark dataset analysis, evaluation metrics, common challenges, standard methods of building polyp detectors and a review of the latest work in the literature. We conclude this paper by providing a precise analysis of the gaps and trends discovered in the reviewed literature for future work.
Automatic age estimation from facial images is an exciting machine learning topic that has attracted researchers’ attention over the past several years. Numerous human–computer interaction applications, such as targeted marketing, content access control, or soft-biometrics systems, employ age estimation models to carry out secondary tasks such as user filtering or identification. Despite the vast array of applications that could benefit from automatic age estimation, building an automatic age estimation system comes with issues such as data disparity, the unique ageing pattern of each individual, and facial photo quality. This paper provides a survey on the standard methods of building automatic age estimation models, the benchmark datasets for building these models, and some of the latest proposed pieces of literature that introduce new age estimation methods. Finally, we present and discuss the standard evaluation metrics used to assess age estimation models. In addition to the survey, we discuss the identified gaps in the reviewed literature and present recommendations for future research.
This paper investigates the performance of the coefficient of variation chart in the presence of measurement errors for finite production horizon. We study a two-sided Shewhart coefficient of variation chart with measurement errors for detecting both increase and decrease in the coefficient of variation for short run processes using an error model with linear covariate. The performance of the coefficient of variation chart is evaluated by the truncated average run length and the expected value of the truncated average run length. The numerical results indicate that the precision error and the accuracy error have negative effect of the measurement errors on the performance of the coefficient of variation chart. In addition, the constant coefficient B in the linear covariate error model reduces the negative effect of the measurement errors on the performance of the coefficient of variation chart. However, taking multiple measurements per item in each sample is not an effective method to enhance the performance of the coefficient of variation chart. An example is provided to illustrate the implementation of the coefficient of variation chart. In addition, the economic criterion is also added to study the effect of measurement errors on the expected inspection cost. The result shows that an increase in the precision error reduces the expected inspection cost.
Colorectal polyps is a prevalent medical condition that could lead to colorectal cancer, a leading cause of cancer-related mortality globally, if left undiagnosed. Colonoscopy remains the gold standard for detection and diagnosis of colorectal neoplasia; however, a significant proportion of neoplastic lesions are missed during routine examinations, particularly diminutive and flat lesions. Deep learning techniques have been employed to improve polyp detection rates in colonoscopy images and have proven successful in reducing the miss rate. However, accurate segmentation of small and flat polyps remains a major challenge to existing models as they struggle to differentiate polypoid and non-polypoid regions apart. To address this issue, we present an enhanced version of the Multi-Scale Attention Network (MA-NET) that incorporates a modified Mix-ViT transformer as the feature extractor. The modified Mix-ViT facilitates ultra-fine-grained visual categorization to improve the segmentation accuracy of polypoid and non-polypoid regions. Additionally, we introduce a pre-processing layer that performs histogram equalization on input images in the CIEL*A*B* color space to enhance their features. Our model was trained on a combined dataset comprising Kvasir-SEG and CVC-ColonDB and cross-validated on CVC-ClinicDB and ETIS-LaribDB. The proposed method demonstrates superior performance compared to existing methods, particularly in the detection of small and flat polyps.
In Evidence-Based Medicine (EBM), medical literature is an essential resource used by clinicians and researchers. It contains research claims that summarize the critical findings of a study. However, research claims on the same topic can be contradicting. Given a clinical question, if two claims that answer the question have conflicting assertion values (Yes or No), they are considered contradictory claims. Hence, discovering the claim assertion value of a research claim is the key to detecting contradictory research claims in medical literature. In this study, we explored the usage of deep neural network (DNN) to recognize contradictory research claims in medical literature. The DNN model should determine the assertion value of a research claim against its clinical question. The model was evaluated using a publicly available corpus containing contradictory research claims from 24 systematic reviews on cardiovascular topic. Different DNN techniques such as the Global Vectors for Word Representation (GLoVe), bidirectional Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers (BERT) were implemented in building the claim assertion model. The evaluation results suggest that the BERT model performs better than LSTM and GloVe model and outperforms the previous studies’ models.