Computer-Aided Image Enhanced Endoscopy Automated System to Boost Polyp and Adenoma Detection Accuracy.

Colonoscopy is the gold standard to detect colon polyps prematurely. Early detection, characterization and resection of polyps decrease colon cancer incidence. Colon polyp missing rate remains high despite novel methods development. Narrowed-band imaging (NBI) is one of the image enhance techniques used to boost polyp detection and characterization, which uses special filters to enhance the contrast of the mucosa surface and vascular pattern of the polyp. However, the single-button-activated system is not convenient for a full-time colonoscopy operation. We selected three methods to simulate the NBI system: Color Transfer with Mean Shift (CTMS), Multi-scale Retinex with Color Restoration (MSRCR), and Gamma and Sigmoid Conversions (GSC). The results show that the classification accuracy using the original images is the lowest. All color transfer methods outperform the original images approach. Our results verified that the color transfer has a positive impact on the polyp identification and classification task. Combined analysis results of the mAP and the accuracy show an excellent performance of the MSRCR method.

Polyp detection and false-positive rates by computer-aided analysis of withdrawal-phase videos of colonoscopy of the right-sided colon segment in a randomized controlled trial comparing water exchange and air insufflation.

BACKGROUND AND AIMS: Water exchange (WE) improves lesion detection but misses polyps because of human limitations. Computer-aided detection (CADe) identifies additional polyps overlooked by the colonoscopist. Additional polyp detection rate (APDR) is the proportion of patients with at least 1 additional polyp detected by CADe. The number of false positives (because of feces and air bubble) per colonoscopy (FPPC) is a major CADe limitation, which might be reduced by salvage cleaning with WE. We compared the APDR and FPPC by CADe between videos of WE and air insufflation in the right-sided colon. METHODS: CADe used a convolutional neural network with transfer learning. We edited and coded withdrawal-phase videos in a randomized controlled trial that compared right-sided colon findings between air insufflation and WE. Two experienced blinded endoscopists analyzed the CADe-overlaid videos and identified additional polyps by consensus. An artifact triggered by CADe but not considered a polyp by the reviewers was defined as a false positive. The primary outcome was APDR. RESULTS: Two hundred forty-five coded videos of colonoscopies inserted with WE (n = 123) and air insufflation (n = 122) methods were analyzed. The APDR in the WE group was significantly higher (37 [30.1%] vs 15 [12.3%], P = .001). The mean [standard deviation] FPPC related to feces (1.78 [1.67] vs 2.09 [2.09], P = .007) and bubbles (.53 [.89] vs 1.25 [2.45], P = .001) in the WE group were significantly lower. CONCLUSIONS: CADe showed significantly higher APDR and lower number of FPPC related to feces and bubbles in the WE group. The results support the hypothesis that the strengths of CADe and WE complement the weaknesses of each other in optimizing polyp detection.

Computer-Aided Colon Polyp Detection on High Resolution Colonoscopy Using Transfer Learning Techniques.

Colonoscopies reduce the incidence of colorectal cancer through early recognition and resecting of the colon polyps. However, the colon polyp miss detection rate is as high as 26% in conventional colonoscopy. The search for methods to decrease the polyp miss rate is nowadays a paramount task. A number of algorithms or systems have been developed to enhance polyp detection, but few are suitable for real-time detection or classification due to their limited computational ability. Recent studies indicate that the automated colon polyp detection system is developing at an astonishing speed. Real-time detection with classification is still a yet to be explored field. Newer image pattern recognition algorithms with convolutional neuro-network (CNN) transfer learning has shed light on this topic. We proposed a study using real-time colonoscopies with the CNN transfer learning approach. Several multi-class classifiers were trained and mAP ranged from 38% to 49%. Based on an Inception v2 model, a detector adopting a Faster R-CNN was trained. The mAP of the detector was 77%, which was an improvement of 35% compared to the same type of multi-class classifier. Therefore, our results indicated that the polyp detection model could attain a high accuracy, but the polyp type classification still leaves room for improvement.

Computer-Aided Detection False Positives in Colonoscopy.

Randomized control trials and meta-analyses comparing colonoscopies with and without computer-aided detection (CADe) assistance showed significant increases in adenoma detection rates (ADRs) with CADe. A major limitation of CADe is its false positives (FPs), ranked 3rd in importance among 59 research questions in a modified Delphi consensus review. The definition of FPs varies. One commonly used definition defines an FP as an activation of the CADe system, irrespective of the number of frames or duration of time, not due to any polypoid or nonpolypoid lesions. Although only 0.07 to 0.2 FPs were observed per colonoscopy, video analysis studies using FPs as the primary outcome showed much higher numbers of 26 to 27 per colonoscopy. Most FPs were of short duration (91% < 0.5 s). A higher number of FPs was also associated with suboptimal bowel preparation. The appearance of FPs can lead to user fatigue. The polypectomy of FPs results in increased procedure time and added use of resources. Re-training the CADe algorithms is one way to reduce FPs but is not practical in the clinical setting during colonoscopy. Water exchange (WE) is an emerging method that the colonoscopist can use to provide salvage cleaning during insertion. We discuss the potential of WE for reducing FPs as well as the augmentation of ADRs through CADe.

A Location Privacy Attack Based on the Location Sharing Mechanism with Erroneous Distance in Geosocial Networks.

Geographical social networks (GSN) is an emerging research area. For example, Foursquare, Yelp, and WeChat are all well-known service providers in this field. These applications are also known as location-based services (LBS). Previous studies have suggested that these location-based services may expose user location information. In order to ensure the privacy of the user's location data, the service provider may provide corresponding protection mechanisms for its applications, including spatial cloaking, fuzzy location information, etc., so that the user's real location cannot be easily cracked. It has been shown that if the positioning data provided by the user is not accurate enough, it is still difficult for an attacker to obtain the user's true location. Taking this factor into consideration, our attack method is divided into two stages for the entire attack process: (1) Search stage: cover the area where the targeted user is located with unit discs, and then calculate the minimum dominating set. Use the triangle positioning method to find the minimum precision disc. (2) Inference phase: Considering the existence of errors, an Error-Adjusted Space Partition Attack Algorithm (EASPAA) was proposed during the inference phase. Improved the need for accurate distance information to be able to derive the user's true location. In this study, we focus on the Location Sharing Mechanism with Maximal Coverage Limit to implement the whole attack. Experimental results show that the proposed method still can accurately infer the user's real location even when there is an error in the user's location information.

Enhancing the quality of protein conformation ensembles with relative populations.

The function and dynamics of many proteins are best understood not from a single structure but from an ensemble. A high quality ensemble is necessary for accurately delineating protein dynamics. However, conformations in an ensemble are generally given equal weights. Few attempts were made to assign relative populations to the conformations, mainly due to the lack of right experimental data. Here we propose a method for assigning relative populations to ensembles using experimental residue dipolar couplings (RDC) as constraints, and show that relative populations can significantly enhance an ensemble's ability in representing the native states and dynamics. The method works by identifying conformation states within an ensemble and assigning appropriate relative populations to them. Each of these conformation states is represented by a sub-ensemble consisting of a subset of the conformations. Application to the ubiquitin X-ray ensemble clearly identifies two key conformation states, with relative populations in excellent agreement with previous work. We then apply the method to a reprotonated ERNST ensemble that is enhanced with a switched conformation, and show that as a result of population reweighting, not only the reproduction of RDCs is significantly improved, but common conformational features (particularly the dihedral angle distributions of ϕ 53 and ψ 52) also emerge for both the X-ray ensemble and the reprotonated ERNST ensemble.

Generalized spring tensor models for protein fluctuation dynamics and conformation changes.

BACKGROUND: In the last decade, various coarse-grained elastic network models have been developed to study the large-scale motions of proteins and protein complexes where computer simulations using detailed all-atom models are not feasible. Among these models, the Gaussian Network Model (GNM) and Anisotropic Network Model (ANM) have been widely used. Both models have strengths and limitations. GNM can predict the relative magnitudes of protein fluctuations well, but due to its isotropy assumption, it cannot be applied to predict the directions of the fluctuations. In contrast, ANM adds the ability to do the latter, but loses a significant amount of precision in the prediction of the magnitudes. RESULTS: In this book chapter, we present a single model, called generalized spring tensor model (STeM), that is able to predict well both the magnitudes and the directions of the fluctuations. Specifically, STeM performs equally well in B-factor predictions as GNM and has the ability to predict the directions of fluctuations as ANM. This is achieved by employing a physically more realistic potential, the Go-like potential. The potential, which is more sophisticated than that of either GNM or ANM, though adds complexity to the derivation process of the Hessian matrix (which fortunately has been done once for all and the MATLAB code is freely available electronically at http://www.cs.iastate.edu/~gsong/STeM ), causes virtually no performance slowdown. In addition, we show that STeM can be further extended to an all-atom model and protein fluctuation dynamics computed by all-atom STeM matches closely with that by Normal Mode Analysis (NMA). CONCLUSIONS: Derived from a physically more realistic potential, STeM proves to be a natural solution in which advantages that used to exist in two separate models, namely GNM and ANM, are achieved in one single model. It thus lightens the burden to work with two separate models and to relate the modes of GNM with those of ANM at times. By examining the contributions of different interaction terms in the Go potential to the fluctuation dynamics, STeM reveals, (i) a physical explanation for why the distance-dependent, inverse distance square (i.e., 1/r (2)) spring constants perform better than the uniform ones, and (ii), the importance of three-body and four-body interactions to properly modeling protein dynamics.STeM is not limited to coarse-grained protein models that use a single bead, usually the alpha carbon, to represent each residue. The core idea of STeM, deriving the Hessian matrix directly from a physically realistic potential, can be extended to all-atom models as well. We did this and discovered that all-atom STeM model represents a highly close approximation of NMA, yet without the need for energy minimization.

Three-in-one agonists for PPAR-α, PPAR-γ, and PPAR-δ from traditional Chinese medicine.

Nowadays, the occurrence of metabolic syndrome, which is characterized by obesity and clinical disorders, has been increasing rapidly over the world. It induces several serious chronic diseases such as cardiovascular disease, dyslipidemia, gall bladder disease, hypertension, osteoarthritis, sleep apnea, stroke, and type 2 diabetes mellitus. Peroxisome proliferator-activated receptors (PPARs), which have three isoforms: PPAR-α, PPAR-γ, and PPAR-δ, are key regulators of adipogenesis, lipid and carbohydrate metabolism, and are potential drug targets for treating metabolic syndrome. The traditional Chinese medicine (TCM) compounds from TCM Database@Taiwan ( http://tcm.cmu.edu.tw/ ) were employed to virtually screen for potential PPAR agonists, and structure-based pharmacophore models were generated to identify the key interactions for each PPAR protein. In addition, molecular dynamics (MD) simulation was performed to evaluate the stability of the PPAR-ligand complexes in a dynamic state. (S)-Tryptophan-betaxanthin and berberrubine, which have higher Dock Score than controls, form stable interactions during MD, and are further supported by the structure-based pharmacophore models in each PPAR protein. Key features include stable H-bonds with Thr279 and Ala333 of PPAR-α, with Thr252, Thr253 and Lys331 of PPAR-δ, and with Arg316 and Glu371 of PPAR-γ. Hence, we propose the top two TCM candidates as potential lead compounds in developing agonists targeting PPARs protein for treating metabolic syndrome.

Efficient mapping of ligand migration channel networks in dynamic proteins.

For many proteins such as myoglobin, the binding site lies in the interior, and there is no obvious route from the exterior to the binding site in the average structure. Although computer simulations for a limited number of proteins have found some transiently open channels, it is not clear if there exist more channels elsewhere or how the channels are regulated. A systematic approach that can map out the whole ligand migration channel network is lacking. Ligand migration in a dynamic protein resembles closely a well-studied problem in robotics, namely, the navigation of a mobile robot in a dynamic environment. In this work, we present a novel robotic motion planning inspired approach that can map the ligand migration channel network in a dynamic protein. The method combines an efficient spatial mapping of protein inner space with a temporal exploration of protein structural heterogeneity, which is represented by a structure ensemble. The spatial mapping of each conformation in the ensemble produces a partial map of protein inner cavities and their inter-connectivity. These maps are then merged to form a super map that contains all the channels that open dynamically. Results on the pathways in myoglobin for gaseous ligands demonstrate the efficiency of our approach in mapping the ligand migration channel networks. The results, obtained in a significantly less amount of time than trajectory-based approaches, are in agreement with previous simulation results. Additionally, the method clearly illustrates how and what conformational changes open or close a channel.

Generalized spring tensor models for protein fluctuation dynamics and conformation changes.

BACKGROUND: In the last decade, various coarse-grained elastic network models have been developed to study the large-scale motions of proteins and protein complexes where computer simulations using detailed all-atom models are not feasible. Among these models, the Gaussian Network Model (GNM) and Anisotropic Network Model (ANM) have been widely used. Both models have strengths and limitations. GNM can predict the relative magnitudes of protein fluctuations well, but due to its isotropy assumption, it can not be applied to predict the directions of the fluctuations. In contrast, ANM adds the ability to do the latter, but loses a significant amount of precision in the prediction of the magnitudes. RESULTS: In this article, we develop a single model, called generalized spring tensor model (STeM), that is able to predict well both the magnitudes and the directions of the fluctuations. Specifically, STeM performs equally well in B-factor predictions as GNM and has the ability to predict the directions of fluctuations as ANM. This is achieved by employing a physically more realistic potential, the Go-like potential. The potential, which is more sophisticated than that of either GNM or ANM, though adds complexity to the derivation process of the Hessian matrix (which fortunately has been done once for all and the MATLAB code is freely available electronically at http://www.cs.iastate.edu/~gsong/STeM), causes virtually no performance slowdown. CONCLUSIONS: Derived from a physically more realistic potential, STeM proves to be a natural solution in which advantages that used to exist in two separate models, namely GNM and ANM, are achieved in one single model. It thus lightens the burden to work with two separate models and to relate the modes of GNM with those of ANM at times. By examining the contributions of different interaction terms in the Go potential to the fluctuation dynamics, STeM reveals, (i) a physical explanation for why the distance-dependent, inverse distance square (i.e., 1/(r)2) spring constants perform better than the uniform ones, and (ii), the importance of three-body and four-body interactions to properly modeling protein dynamics.