Abstract-Colonoscopy is the gold standard for colon cancer screening though still some polyps are missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection subchallenge, conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org) at the international conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks (CNNs) are the state of the art. Nevertheless it is also demonstrated that combining different methodologies can lead to an improved overall performance.
Widely used medical imaging systems in clinics currently rely on X-rays, magnetic resonance imaging, ultrasound, computed tomography, and positron emission tomography. The aforementioned technologies provide clinical data with a variety of resolution, implementation cost, and use complexity, where some of them rely on ionizing radiation. Microwave sensing and imaging (MSI) is an alternative method based on nonionizing electromagnetic (EM) signals operating over the frequency range covering hundreds of megahertz to tens of gigahertz. The advantages of using EM signals are low health risk, low cost implementation, low operational cost, ease of use, and user friendliness. Advancements made in microelectronics, material science, and embedded systems make it possible for miniaturization and integration into portable, handheld, mobile devices with networking capability. MSI has been used for tumor detection, blood clot/stroke detection, heart imaging, bone imaging, cancer detection, and localization of in-body RF sources. The fundamental notion of MSI is that it exploits the tissue-dependent dielectric contrast to reconstruct signals and images using radar-based or tomographic imaging techniques. This paper presents a comprehensive overview of the active MSI for various medical applications, for which the motivation, challenges, possible solutions, and future directions are discussed.
Automatic detection of colonic polyps is still an unsolved problem due to the large variation of polyps in terms of shape, texture, size and color, and the existence of various polyp-like mimics during colonoscopy. In this study, we apply a recent region based convolutional neural network (CNN) approach for the automatic detection of polyps in images and videos obtained from colonoscopy examinations. We use a deep-CNN model (Inception Resnet) as a transfer learning scheme in the detection system. To overcome the polyp detection obstacles and the small number of polyp images, we examine image augmentation strategies for training deep networks. We further propose two efficient post-learning methods such as, automatic false positive learning and off-line learning, both of which can be incorporated with the region based detection system for reliable polyp detection. Using the large size of colonoscopy databases, experimental results demonstrate that the suggested detection systems show better performance compared to other systems in the literature. Furthermore, we show improved detection performance using the proposed post-learning schemes for colonoscopy videos.
Automatic polyp detection has been shown to be difficult due to various polyp-like structures in the colon and high interclass variations in polyp size, color, shape, and texture. An efficient method should not only have a high correct detection rate (high sensitivity) but also a low false detection rate (high precision and specificity). The state-of-the-art detection methods include convolutional neural net-works (CNN). However, CNNs have shown to be vulnerable to small perturbations and noise; they sometimes miss the same polyp appearing in neighboring frames and produce a high number of false positives. We aim to tackle this prob-lem and improve the overall performance of the CNN-based object detectors for polyp detection in colonoscopy videos. Our method consists of two stages: a region of interest (RoI) proposal by CNN-based object detector networks and a false positive (FP) reduction unit. The FP reduction unit exploits the temporal dependencies among image frames in video by integrating the bidirectional temporal informa-tion obtained by RoIs in a set of consecutive frames. This information is used to make the final decision. The exper-imental results show that the bidirectional temporal infor-mation has been helpful in estimating polyp positions and accurately predict the FPs. This provides an overall perfor-mance improvement in terms of sensitivity, precision, and This work was supported by Research Council of Norway through the industrial Ph.D. project under the contract num-ber 271542/O30 and through the MELODY project under the contract number 225885/O70.
In this paper we deal with biomedical applications of wireless sensor networks, and propose a new quality of service (QoS) routing protocol. The protocol design relies on traffic diversity of these applications and ensures a differentiation routing using QoS metrics. It is based on modular and scalable approach, where the protocol operates in a distributed, localized, computation and memory efficient way. The data traffic is classified into several categories according to the required QoS metrics, where different routing metrics and techniques are accordingly suggested for each category. The protocol attempts for each packet to fulfill the required QoS metrics in a power-aware way, by locally selecting the best candidate. It employs memory and computation efficient estimators, and uses a multi-sink single-path approach to increase reliability. The main contribution of this paper is data traffic based QoS with regard to all the considered QoS metrics. To our best knowledge, this protocol is the first that makes use of the diversity in the data traffic while considering latency, reliability, residual energy in the sensor nodes, and transmission power between sensor nodes as QoS metrics of the multi-objective problem. The proposed algorithm can operate with any MA C protocol, provided that it employs an ACK mechanism. Performance evaluation through a simulation study, comparing the new protocol with state-of-the QoS and localized protocols, show that it outperforms all the compared protocols.
One of the major obstacles in automatic polyp detection during colonoscopy is the lack of labeled polyp training images. In this study, we propose a framework of conditional adversarial networks to increase the number of training samples by generating synthetic polyp images. Using a normal binary form of polyp mask which represents only the polyp position as an input conditioned image, realistic polyp image generation is a difficult task in generative adversarial networks approach. Therefore, we propose an edge filtering based combined input conditioned image. More importantly, our proposed framework generates synthetic polyp images from normal colonoscopy images which have the advantage of being relatively easy to obtain. This means realistic polyp images can be generated while maintaining the original structures of the colonoscopy image frames. The network architecture is based on the use of multiple dilated convolutions in each encoding part of our generator network to consider large receptive fields and avoid much contractions of feature map size. An image resizing with convolution for up sampling in the decoding layers is considered to prevent artifacts on generated images. We show that the generated polyp images are not only qualitatively look realistic but also help to improve polyp detection performance.INDEX TERMS Colonoscopy, convolutional neural network, dilated convolution, generative adversarial networks, polyp detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
334 Leonard St
Brooklyn, NY 11211
Copyright © 2023 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.