China
Africa
Explore chapters and articles related to this topic
Assessment of Quercetin Isolated from Enicostemma Littorale Against Few Cancer Targets: An in Silico Approach
Published in A. K. Haghi, Ana Cristina Faria Ribeiro, Lionello Pogliani, Devrim Balköse, Francisco Torrens, Omari V. Mukbaniani, Applied Chemistry and Chemical Engineering, 2017
Colorectal cancer, less formally known as bowel cancer, is a cancer characterized by neoplasia in the colon, rectum, or vermiform appendix. Colorectal cancer is clinically distinct from anal cancer, which affects the anus. Colorectal cancers start in the lining of the bowel. If it left untreated, it could grow into the muscle layers underneath, and then through the bowel wall. Most begin as a small growth on the bowel wall: a colorectal polyp or adenoma. These mushroom-shaped growths are usually benign, but some develop into cancer over time. Localized bowel cancer is usually diagnosed through colonoscopy. Invasive cancers that are confined within the wall of the colon (Tetranitromethane (TNM) stages I and II) are often curable with surgery. Colorectal cancer is the third most commonly diagnosed cancer in the world, but it is more common in developed countries. More than half of the people who die of colorectal cancer live in a developed region of the world (http://globocan.iarc.fr/). GLOBOSCAN estimated that, in 2008 reported 1.23 million cases with colorectal cancer of which more than 600,000 people died.
Investigate the role of PIK3CA gene expression in colorectal polyp development
Published in Egyptian Journal of Basic and Applied Sciences, 2023
Ameer Ali Imarah, Rana Ahmed Najm, Haider Ali Alnaji, Saleem Khteer Al-Hadraawy, Abbas F. Almulla, Hussein Raof Al-Gazali
A polyp is a mass that protrudes into the lumen of a hollow duct or organ. Colorectal polyps are classified according to histological properties as neoplastic (malignant potential) or non-neo-plastic, including hyperplastic, inflammatory, or hamartomatous polyps. As with any disease in the human body, when diagnosed at the early stages of development, the treatment protocol becomes easy and simple also, with low side effects when compared with the final stages of diseases development, therefore it so important to diagnose the neoplastic polyps in the early stage of development [18]. Thus, the current study attempted to show the role of PIK3CA expression in colorectal polyp development. The patient group was divided into three age groups (50–59 years), (60–69 years), and (70–80 years), including 35 patients, 7 patients, and 24 patients, respectively. In general, age classification in the current study agrees with a study that found a high prevalence of colorectal polyp cases diagnosed in the age above 50 years. The current study is compatible with the results of recent studies [19,20]. The variations of cases in each age group may occur due to many causes; colorectal polyps diagnosed accidentally through colonoscopy screening make the diagnosis don’t have a specific standard. A possible second cause may be the small sample size, which can reflect a nonspecific and real representation of the distribution according to age group.
Gastrointestinal tract disease recognition based on denoising capsule network
Published in Cogent Engineering, 2022
Yaw Afriyie, Benjamin A. Weyori, Alex A. Opoku
CNN has lately been found to be quite useful in endoscopic procedures such as esophagogastroduodenoscopy (EGD), colonoscopy, and capsule endoscopy. The anatomical position in EGD images (Takiyama et al., 2018), Helicobacter pylori (HP) infections (Shichijo et al., 2017), (Itoh et al., 2018) and gastric cancer were all challenges for a CNN-based diagnosis tool in EGD (Hirasawa et al., 2018). During a colonoscopy, a CNN-based diagnostic tool was employed to detect and characterize colorectal polyps (Komeda et al., 2017), (Byrne et al., 2019b), (R. Ruikai Zhang et al., 2017). In 2017, Komeda et al. (Komeda et al., 2017) reported a study that employed CNN to diagnose colorectal polyps utilizing 1,200 colonoscopy photographs and 10 additional video images of unlearned processes. A 10-fold cross-validation produces an accuracy of 0.751, where accuracy refers to the percent of answers that are accurate. In a study by Byrne et al. (Byrne et al., 2019a), the researchers developed a deep CNN model for real-time analysis of colorectal polyps within colonoscopic video images. Training and testing of the CNN model was done using only NBI videoframes (split evenly across relevant multi-classes) and unedited routine exam films that were not explicitly intended for CNN classification 106 sequentially encountered small polyps were used to validate the model using the second set of 125 movies. Using CNN to detect adenomas, the CNN was accurate, sensitive, specific, negative predictive, and positive predictive, respectively, with 94%, 98%, 83%, 97%, and 90%. Similar to Chang et al., Chang et al. (Y. Yuan Chang & Chen, 2019) achieved better categorization abilities across a wide range of categories using a deep attention neural network. A variety of techniques are employed to transform the data, including automatic data fusion, multi-epoch fusion, and adaptive threshold selection achieving an F1 score of 90.70%. A polyp identification convolutional neural network based on a single shot multibox detector was described by (X. Xu Zhang et al., 2019). An upgraded SSD, according to the data, can increase mean average precision (mAP) from 88.5 to 90.4%. The findings also show that when max-pooling layers are used, convolutional neural networks lose about 3/4 of their critical information. Ayidzoe et al. (Afriyie et al., 2021) suggested a capsule network variation that is less sophisticated but still robust and capable of extracting features. Their model took advantage of the Gabor filter and a proprietary preprocessing block to understand the structure and semantic information in an image, resulting in higher accuracy on the datasets studied. Several deep learning models based on CNNs have been proposed to diagnose gastrointestinal disorders. However, only a few studies have used gastrointestinal images to train capsule networks to our knowledge. We propose using CapsNets to construct a modified squash function for detecting gastrointestinal diseases as a result of our research. This paper also introduces improved methodologies that can be used as CapsNet performance indicators, enhancing the models’ dependability, explainability, and understandability.