Background The wireless capsule endoscope (CE) is a valuable diagnostic tool in gastroenterology, offering a safe and minimally invasive visualization of the gastrointestinal tract. One of the few drawbacks identified by the gastroenterology community is the time-consuming task of analyzing CE videos. Objectives This article investigates the feasibility of a computer-aided diagnostic method to speed up CE video analysis. We aim to generate a significantly smaller CE video with all the anomalies (i.e., diseases) identified by the medical doctors in the original video. Methods The summarized video consists of the original video frames classified as anomalous by a pre-trained convolutional neural network (CNN). We evaluate our approach on a testing dataset with eight CE videos captured with five CE types and displaying multiple anomalies. Results On average, the summarized videos contain 93.33% of the anomalies identified in the original videos. The average playback time of the summarized videos is just 10 min, compared to 58 min for the original videos. Conclusion Our findings demonstrate the potential of deep learning-aided diagnostic methods to accelerate CE video analysis.

In this paper, we solve a non-linear reaction–diffusion system with Dirichlet–Neumann mixed boundary conditions using a finite difference method (FDM) in space and the implicit midpoint method in time. This type of system appears, e.g., in the mathematical modeling of light-controlled drug delivery. One of the key results of this paper is the proof that the method has superconvergence second-order in space in a discrete H1-norm and optimal second-order convergence in time in a discrete L2-norm. Our result relies on the direct analysis of a suitable error equation, avoiding the classic construction of consistency plus stability implies convergence. One advantage of such an analysis technique is the establishment of the method’s non-linear stability in an elegant way. Numerical examples support the theoretical convergence result.

In this paper, we analyze a numerical scheme for a nonlinear coupled system of partial differential equations. Our study is motivated by the mathematical modeling of lighttriggered drug delivery, a technique that can have a significant impact on cancer treatment. The numerical scheme combines a finite difference method (FDM) in space with an implicit-explicit (IMEX) method in time. For the main variable of interest - free drug concentration - we prove that the scheme is second-order supraconvergent in space in a discrete H1-norm and first-order convergent in time in a discrete L-2-norm. We give numerical results illustrating the theoretical findings and computational simulations based on a laboratory experiment concerned with light-triggered drug delivery. (c) 2022 IMACS. Published by Elsevier B.V. All rights reserved.

Convection enhanced drug delivery (CED) is a technique used to make therapeutic agents reach, through a catheter, sites of difficult access. The name of this technique comes from the convective flow originated by a pressure gradient induced at the tip of the catheter. This flow enhances passive diffusion and allows a more efficient spread of the agents by the target site. CED is particularly useful in the treatment of diseases that affect the central nervous system, where the blood–brain barrier prevents the diffusion of most therapeutic agents from the cerebral blood vessels to the brain interstitial space. In this work we deal with the numerical analysis of a coupled system of partial differential equations that can be used to simulate CED in an elastic medium like brain tissue. The model variables are the fluid velocity, the pressure, the tissue deformation, and the agents concentration. We prove the stability of the coupled problem and from the numerical point of view we propose a fully discrete piecewise linear finite element method (FEM). The convergence analysis shows that the method has second order convergence for the pressure, displacement, and concentration. Numerical experiments illustrating the theoretical convergence rates and the behavior of the system are also given.

Ultrasound enhanced drug transport is a multiphysics problem involving acoustic waves propagation, bioheat transfer, and drug transport. In this paper, we study a model for this problem that consists of a wave-type equation for acoustic pressure, a diffusion-reaction equation for bioheat transfer, and a convection-diffusionreaction equation for drug transport. We focus in particular on the numerical analysis of such a system. We propose and derive convergence estimates for a piecewise linear finite element method (FEM) with quadrature. We prove that the FEM is second order convergent for concentration in a discrete L-2-norm. Since concentration depends on the gradient of acoustic pressure, this result shows that the FEM is superconvergent. Note that one expects the FEM to be convergent of order one in the L-2-norm because the optimal convergence rate for the acoustic pressure is two in the H-1-norm. We include numerical results backing the theoretical findings and an application of the model to a laboratory experiment of ultrasound enhanced transdermal drug delivery.

Near-infrared light-controlled transdermal drug delivery (NIRTDD) has several advantages over traditional delivery methods, and it is now undergoing extensive research. One promi-nent aspect of NIRTDD is the possibility of keeping the drug concentration in its optimal therapeutic window using a suitable near-infrared light protocol. The problem is that this ideal protocol is usually unknown. In this paper, we propose a computational tool that aims at solving this issue. The computational tool relies on an optimization problem in-volving the numerical simulation of a two-dimensional mathematical model for NIRTDD. We also analyze the convergence and stability of a finite difference spatial scheme for a generalized version of this mathematical model. (c) 2022 Elsevier Inc. All rights reserved.

Wireless Capsule Endoscopy (WCE) is a non-invasive medical procedure devised for painless in vivo inspection of the gastrointestinal (GI) tract. It is especially valuable for the examination of the small intestine since it is difficult to reach by traditional endoscopic procedures. The setup includes a camera with an embedded light source and a circuit capable of acquiring and transmitting the video. The main challenge of this technology is the identification of the position and trajectory of the capsule as it travels through the GI tract, which is particularly relevant during the detection of anomalies in the tissue. Given only the information provided by the recorded images, it is possible to estimate the 3D motion of the camera capsule and provide a full trajectory reconstruction. A critical yet difficult step in this process is the image registration between sequential frames. Therefore, being able to determine accurate correspondences between points, regions or features in two consecutive frames is crucial for the computation of the relative rotation and translation of the capsule. This paper comprises a comparative assessment of methodologies to address this problem with a porcine colon dataset obtained with our experimental setup.

Unmanned Aerial Systems (UAS, aka drones) are being used to map marine macro-litter on the coast. Within the UAS4Litter project, the application of UAS has been applied on three sandy beach-dune systems on the wave-dominated North Atlantic Portuguese coast. Several technical solutions have been tested in terms of drone mapping performance, manual image screening and marine litter map analysis. The conceptualization and implementation of a multidisciplinary framework allowed to improve and making more efficient the mapping of marine litter items with UAS on coastal environment. The location of major marine litter loads within the monitored areas were found associated to beach slope and water level dynamics on the beach profiles. Moreover, the abundance of marine pollution was related to the geographical location and level of urbanization of the study sites. The testing of machine learning techniques underlined that automated technique returned reliable abundance map of marine litter, while manual image screening was required for a detailed categorization of the items. As marine litter pollution on coastal dunes has received limited scientific attention when compared with sandy shores, a novel non-intrusive UAS-based marine litter survey have been also applied to quantify the level of contamination on coastal dunes. The results showed the influence of the different dune plant communities in trapping distinct type of marine litter, and the role played by wind and overwash events in defining the items pathways through the dune blowouts. The experiences on the Portuguese coast show that UAS allows an integrated approach for marine litter mapping, beach morphodynamic and nearshore hydrodynamic, setting the ground for marine litter dynamic modelling on the shore. Besides, UAS can give a new impulse to coastal dune litter monitoring, where the long residence time of marine debris threat the bio-ecological equilibrium of these ecosystems.

Most available bank asset allocation models use several risk measures as constraints; as a consequence, the comparison of the risk between different asset allocation strategies is often difficult, since each strategy is subject to several risks. With this research, we create a simulation-optimization methodology that measures interest rate, credit and liquidity risks in a unified manner. The associated risk events, such as interest rate increases, liquidity outflows or spikes in defaults are generated using the same simulation engine, giving as output a single risk measure (the probability of failure, used by ratings agencies) that aggregates those risks under the same simulation engine. Finally, we use our methodology to determine Pareto fronts for the optimal balance sheet allocations and minimum-risk strategies. As a result, several findings emerge, such as: 1) Risk is dependent on the income stream; 2) Allocation to book value assets is preferable; 3) Under low rate environments, a full allocation to cash is very risky and is not the minimum risk strategy; 4) Banks can make investments in stocks in environments of high prospective returns and low leverage.

The use of Unmanned Aerial Systems (UAS, aka drones) images for mapping macro-litter in the environment have been exponentially increasing in the recent years. In this work, we developed a multi-class Neural Network (NN) to automatically identify stranded plastic litter categories on an UAS-derived orthophoto. The best results were assessed for items that did not have substantial intra-class colour variability, such as octopus pots and fishing ropes (F-score = 61%, on average). Instead, performance was poor (37%) for plastic bottles and fragments, due to their changing intra-class colours. On average, the performance improved 24% when the binary detection (litter/non-litter, F-Score = 73%) was considered, however this approach did not discriminate the litter categories. This work gives a new perspective for the automated litter detection on drone images, suggesting that colourbased approach can be used to improve the categorization of stranded litter on UAS orthophoto.

Unmanned aerial systems (UAS, aka drones) are being used to map macro-litter on the environment. Sixteen qualified researchers (operators), with different expertise and nationalities, were invited to identify, mark and categorize the litter items (manual image screening, MS) on three UAS images collected at two beaches. The coefficient of concordance (W) among operators varied between 0.5 and 0.7, depending on the litter parameter (type, material and colour) considered. Highest agreement was obtained for the type of items marked on the highest resolution image, among experts in litter surveys (W = 0.86), and within territorial subgroups (W = 0.85). Therefore, for a detailed categorization of litter on the environment, the MS should be performed by experienced and local operators, familiar with the most common type of litter present in the target area. This work provides insights for future operational improvements and optimizations of UAS-based images analysis to survey environmental pollution.

Ultrasound enhanced drug transport is a multiphysics problem that involves acoustic waves propagation, bioheat transfer and drug transport. The numerical modeling of this problem requires the solution of a coupled system of partial differential equations. A wave-type equation for acoustic pressure and two nonlinear parabolic-type equations: a diffusion-reaction equation for bioheat transfer and a convection-diffusion-reaction equation for drug transport. In this paper we focus on the numerical analysis of such coupled system. We propose and derive convergence estimates for a piecewise linear finite element method (FEM) with quadrature. We prove that the FEM is second order convergent for concentration with respect to a discrete L2-norm. Since concentration depends on the gradient of acoustic pressure, this result shows that the FEM is superconvergent. In fact, piecewise linear FEM have optimal order one in the H1-norm then, the optimal convergence rate for concentration in a L2-norm should be at most one. Numerical results backing the theoretical findings are included.

This paper describes a novel method for fast colonic polyp detection in colonoscopy images. Firstly, polyp detection is formulated as a similarity-based anomaly detection method, which formally involves non-dominated sorting based on multiple objectives. The chosen objectives rely on the main physical and visible differences, observed in colonoscopy images, between regions containing colonic polyps and the surrounding normal mucosa. These differences are defined primarily according to the contrast in shape, texture, and color. Secondly, as non-dominated sorting is of combinatorial nature and is costly to compute, it is replaced by a fast algorithm that approximates the sorting in the continuum limit. The fast algorithm involves numerical solutions to a particular Hamilton-Jacobi equation. The proposed similarity-based anomaly detection is thus reformulated into a fast polyp detection method. Several experiments were conducted with a proprietary medical data set, containing 1640 instances of 41 different polyps. The results show that the proposed Hamilton-Jacobi approach to non-dominated sorting speeds up the non-dominated sorting procedure, by more than 500%, and, when compared with other existing methods, it is also faster without lost of accuracy. Moreover, the tests conducted for streaming data, reveal an outstanding performance, in terms of sensitivity and specificity, as well as, a fast auto-adaptability, which demonstrate the power of the proposed approach towards a real-time and automatic detection, undoubtedly beneficial for clinical practice. (C) 2020 Elsevier Ltd. All rights reserved.

The fractional Klein-Kramers equation describes the process of subdiffusion in the presence of an external force field in phase space and incorporates a fractional operator in time of order alpha, 0 < alpha < 1. We present a family of finite volume schemes for the fractional Klein-Kramers equation, that includes first or second-order schemes in phase space, and implicit or explicit schemes in time with an order of accuracy that can change between alpha and 2 - alpha. It is proved, for the open domain, that the schemes satisfy the positivity preserving property. The positivity preserving property for the explicit schemes imposes a strong condition in the relation between time step, space step and phase step, for small values of a, highlighting the advantage of using implicit schemes in these cases. For a bounded domain in space, two types of boundary conditions are considered, absorbing boundary conditions and reflecting boundary conditions. The inclusion of boundary conditions leads to some technical complications that require changes in the schemes near the boundary. The positivity preserving property holds for the new formulation and the overall accuracy is ensured with the use of non-uniform meshes. Numerical tests are presented in the end to show the convergence of the finite volume schemes. (C) 2020 Elsevier B.V. All rights reserved.

The skin is the largest organ of the human body, offering an accessible interface for the administration of drugs. The main obstacle to transdermal drug delivery is the skin's barrier properties, due essentially to the stratum corneum, the skin's outermost layer, which is impermeable to most drugs. There are several techniques used to modify the barrier properties of the stratum corneum and to enhance the permeation of drugs through the skin. One popular approach to overcome this barrier is iontophoresis, a technique where electric fields are applied to enhance the transport, by adding an electric potential gradient to a concentration gradient. Several factors affect iontophoresis transdermal drug delivery (TDD). Among them the mechanical properties of skin play an important role. The skin behaves like a viscoelastic material, and it is well known that transport in viscoelastic media is non-Fickian. Consequently, the traditional Fickian advection-diffusion iontophoretic models are inappropriate. As aging induces huge modifications in the mechanical properties of the skin, the models presented in this paper can provide clinicians with guidelines for personalized TDD. The paper is concerned with the analysis and numerical simulation of a non-Fickian viscoelastic model for iontophoretic transdermal drug transport. A multilayer approach is followed, where the polymeric drug reservoir and the properties of the main skin layers are taken into account. Numerical simulations illustrate the effect of aging in TDD and shed light on how to include it in personalized TDD protocols.

Recent works have shown the feasibility of Unmanned Aerial Systems (UAS) for monitoring marine pollution.We provide a comparison among techniques to detect and map marine litter objects on an UAS-derived orthophoto of a sandy beach-dune system. Manual image screening technique allowed a detailed description of marine litter categories. Random forest classifier returned the best-automated detection rate (F-score 70%), while convolutional neural network performed slightly worse (F-score 60%) due to a higher number of false positive detections.We show that automatic methods allow faster and more frequent surveys, while still providing a reliable density map of the marine litter load. Image manual screening should be preferred when the characterization of marine litter type and material is required.Our analysis suggests that the use of UAS-derived orthophoto is appropriate to obtain a detailed geolocation of marine litter items, requires much less human effort and allows a wider area coverage.

Background and study aims Detection of polyps during colonoscopy is essential for screening colorectal cancer and computer-aided-diagnosis (CAD) could be helpful for this objective. The goal of this study was to assess the efficacy of CADin detection of polyps in video colonoscopy by using three methods we have proposed and applied for diagnosis of polyps in wireless capsule colonoscopy. Patients and methods Forty-two patients were included in the study, each one bearing one polyp.A dataset was generated with a total of 1680 polyp instances and 1360 frames of normal mucosa. We used three methods, that are all binary classifiers, labelling a frame as either containing a polyp or not. Two of the methods (Methods 1 and 2) are threshold-based and address the problem of polyp detection (i.e. separation between normal mucosa frames and polyp frames) and the problem of polyp localization (i.e. the ability to locate the polyp in a frame). The third method (Method 3) belongs to the class of machine learning methods and only addresses the polyp detection problem. The mathematical techniques underlying these three methods rely on appropriate fusion of information about the shape, color and texture content of the objects presented in the medical images. Results Regarding polyp localization, the best method is Method 1 with a sensitivity of 71.8%. Comparing the performance of the three methods in the detection of polyps, independently of the precision in the location of the lesions, Method 3 stands out, achieving a sensitivity of 99.7%, an accuracy of 91.1%, and a specificity of 84.9%. Conclusion CAD, using the three studied methods, showed good accuracy in the detection of polyps with white light colonoscopy.

Colon cancer prevention, diagnosis, and prognosis are directly related to the identification of colonic polyps, in colonoscopy video sequences. In addition, diagnosing colon cancer in the early stages improves significantly the chance of surviving and effective treatment. Due to the large number of images that come from colonoscopy, the identification of polyps needs to be automated for effciency. In this paper, we propose a strategy for automatic polyp recognition, based on a recent multi-objective anomaly detection concept, which itself is based on Pareto Depth Analysis (PDA). Clinically, in medical images, polyps are diagnosed based on a few criteria, such as texture, shape and color. Few works use multi-criteria classification in a systematic way for polyp detection. In the present paper we use a PDA approach, to act as a binary classifier for the identification of colonic polyps. The results obtained in a medical dataset, of conventional colonoscopy images, consisting of short videos from 34 different patients, and 34 different polyps, with a total of 1360 different polyp frames, confirm that the proposed method clearly outperforms the single performance of each criterion.

We present results concerning the validation of a novel approach for wireless capsule endoscope localization, using as ground truth a simulated biological/mechanical environment experiment. The approach relies essentially on image-based methods. It involves a hybrid multi-scale affine and elastic image registration procedure which is afterwards appropriately complemented with calibration and visual odometry techniques. The capsule was fixed at the extremity of a robotic arm and moved along a part of an ex-vivo mammalian bowel. The first validation results indicate a good correlation between the ground truth velocity and distance traveled by the capsule and the velocity and distance given by the proposed approach.