Intensive vision-guided network for radiology report generation.

Objective.Automatic radiology report generation is booming due to its huge application potential for the healthcare industry. However, existing computer vision and natural language processing approaches to tackle this problem are limited in two aspects. First, when extracting image features, most of them neglect multi-view reasoning in vision and model single-view structure of medical images, such as space-view or channel-view. However, clinicians rely on multi-view imaging information for comprehensive judgment in daily clinical diagnosis. Second, when generating reports, they overlook context reasoning with multi-modal information and focus on pure textual optimization utilizing retrieval-based methods. We aim to address these two issues by proposing a model that better simulates clinicians perspectives and generates more accurate reports.Approach.Given the above limitation in feature extraction, we propose a globally-intensive attention (GIA) module in the medical image encoder to simulate and integrate multi-view vision perception. GIA aims to learn three types of vision perception: depth view, space view, and pixel view. On the other hand, to address the above problem in report generation, we explore how to involve multi-modal signals to generate precisely matched reports, i.e. how to integrate previously predicted words with region-aware visual content in next word prediction. Specifically, we design a visual knowledge-guided decoder (VKGD), which can adaptively consider how much the model needs to rely on visual information and previously predicted text to assist next word prediction. Hence, our final intensive vision-guided network framework includes a GIA-guided visual encoder and the VKGD.Main results.Experiments on two commonly-used datasets IU X-RAY and MIMIC-CXR demonstrate the superior ability of our method compared with other state-of-the-art approaches.Significance.Our model explores the potential of simulating clinicians perspectives and automatically generates more accurate reports, which promotes the exploration of medical automation and intelligence.

Novel item selection strategies for cognitive diagnostic computerized adaptive testing: A heuristic search framework.

The computerized adaptive form of cognitive diagnostic testing, CD-CAT, has gained increasing attention in the domain of personalized measurements for its ability to categorize individual mastery status of fine-grained attributes more accurately and efficiently through administering items tailored to one's ability progressively. How to select the next item based on previous response(s) is crucial for the success of CD-CAT. Previous item selection strategies for CD-CAT have often followed a greedy or semi-greedy approach, which makes it difficult to strike a balance between diagnostic performance and item bank utilization. To address this issue, this study takes a graph perspective and transforms the item selection problem in CD-CAT into a path-searching problem, in which paths refer to possible test construction and nodes refer to individual items. A heuristic function is defined to predict the prospect of a path, indicating how well the corresponding test can diagnose the current examinee. Two search mechanisms with different biases towards item exposure control are proposed to approximate the optimal path with the best prospect. The first unused item on the resulting path is selected as the next item. The above components compose a novel CD-CAT item selection framework based on heuristic search. Simulation studies are conducted under a variety of conditions regarding bank designs, bank-quality conditions, and testing scenarios. The results are compared with different types of classic item selection strategies in CD-CAT, showing that the proposed framework can enhance bank utilization at a smaller cost of diagnostic performance.

Multiscale pharmacokinetic modeling of systemic exposure of subcutaneously injected biotherapeutics.

Subcutaneously injected formulations have been developed for many biological products including monoclonal antibodies (mAbs). A knowledge gap nonetheless remains regarding the absorption and catabolism mechanisms and kinetics of a large molecule at the administration site. A multiscale pharmacokinetic (PK) model was thus developed by coupling multiphysics simulations of subcutaneous (SC) absorption kinetics with whole-body pharmacokinetic (PK) modeling, bridged by consideration of the presystemic clearance by the initial lymph. Our local absorption simulation of SC-injected albumin enabled the estimation of its presystemic clearance and led to the whole-body PK modeling of systemic exposure. The local absorption rate of albumin was found to be influential on the PK profile. Additionally, nineteen mAbs were explored via this multiscale simulation and modeling framework. The computational results suggest that stability propensities of the mAbs are correlated with the presystemic clearance, and electrostatic charges in the complementarity-determining region influence the local absorption rate. Still, this study underscores a critical need to experimentally determine various biophysical characteristics of a large molecule and the biomechanical properties of human skin tissues.

Multiphysics Modeling and Simulation of Subcutaneous Injection and Absorption of Biotherapeutics: Sensitivity Analysis.

PURPOSE: A multiphysics simulation model was recently developed to capture major physical and mechanical processes of local drug transport and absorption kinetics of subcutaneously injected monoclonal antibody (mAb) solutions. To further explore the impact of individual drug attributes and tissue characteristics on the tissue biomechanical response and drug mass transport upon injection, sensitivity analysis was conducted and reported. METHOD: Various configurations of injection conditions, drug-associated attributes, and tissue properties were simulated with the developed multiphysics model. Simulation results were examined with regard to tissue deformation, porosity change, and spatiotemporal distributions of pressure, interstitial fluid flow, and drug concentration in the tissue. RESULTS: Injection conditions and tissue properties were found influential on the mechanical response of tissue and interstitial fluid velocity to various extents, leading to distinct drug concentration profiles. Intrinsic tissue porosity, lymphatic vessel density, and drug permeability through the lymphatic membrane were particularly essential in determining the local absorption rate of an mAb injection. CONCLUSION: The sensitivity analysis study may shed light on the product development of an mAb formulation, as well as on the future development of the simulation method.

Multiphysics Modeling and Simulation of Subcutaneous Injection and Absorption of Biotherapeutics: Model Development.

PURPOSE: Many monoclonal antibodies (mAbs) are administered via subcutaneous (SC) injection. Local transport and absorption kinetics and mechanisms, however, remain poorly understood. A multiphysics computational model was developed to simulate the injection and absorption processes of a protein solution in the SC tissue. METHODS: Quantitative relationships among tissue properties and transport behaviors of an injected solution were described by respective physical laws. SC tissue was treated as a 3-dimensional homogenous, poroelastic medium, in which vasculatures and lymphatic vessels were implicitly treated. Tissue deformation was considered, and interstitial fluid flow was modeled by Darcy's law. Transport of the drug mass was described based on diffusion and advection, which was integrated with tissue mechanics and interstitial fluid dynamics. RESULTS: Injection and absorption of albumin and IgG solutions were simulated. Upon injection, a sharp rise in tissue pressure, porosity, and fluid velocity could be observed at the injection tip. Largest tissue deformation appeared at the model surface. Transport of drug mass out of the injection zone was minimal. Absorption by local lymphatics was found to last several weeks. CONCLUSIONS: A bottom-up method was developed to simulate drug transport and absorption of protein solutions in skin tissue base on physical principles. The results appear to match experimental observations.

Accurately Discriminating COVID-19 from Viral and Bacterial Pneumonia According to CT Images Via Deep Learning.

Computed tomography (CT) is one of the most efficient diagnostic methods for rapid diagnosis of the widespread COVID-19. However, reading CT films brings a lot of concentration and time for doctors. Therefore, it is necessary to develop an automatic CT image diagnosis system to assist doctors in diagnosis. Previous studies devoted to COVID-19 in the past months focused mostly on discriminating COVID-19 infected patients from healthy persons and/or bacterial pneumonia patients, and have ignored typical viral pneumonia since it is hard to collect samples for viral pneumonia that is less frequent in adults. In addition, it is much more challenging to discriminate COVID-19 from typical viral pneumonia as COVID-19 is also a kind of virus. In this study, we have collected CT images of 262, 100, 219, and 78 persons for COVID-19, bacterial pneumonia, typical viral pneumonia, and healthy controls, respectively. To the best of our knowledge, this was the first study of quaternary classification to include also typical viral pneumonia. To effectively capture the subtle differences in CT images, we have constructed a new model by combining the ResNet50 backbone with SE blocks that was recently developed for fine image analysis. Our model was shown to outperform commonly used baseline models, achieving an overall accuracy of 0.94 with AUC of 0.96, recall of 0.94, precision of 0.95, and F1-score of 0.94. The model is available in https://github.com/Zhengfudan/COVID-19-Diagnosis-and-Pneumonia-Classification .

Monepantel is a non-competitive antagonist of nicotinic acetylcholine receptors from Ascaris suum and Oesophagostomum dentatum.

Zolvix® is a recently introduced anthelmintic drench containing monepantel as the active ingredient. Monepantel is a positive allosteric modulator of DEG-3/DES-2 type nicotinic acetylcholine receptors (nAChRs) in several nematode species. The drug has been reported to produce hypercontraction of Caenorhabditis elegans and Haemonchus contortus somatic muscle. We investigated the effects of monepantel on nAChRs from Ascaris suum and Oesophagostomum dentatum heterologously expressed in Xenopus laevis oocytes. Using two-electrode voltage-clamp electrophysiology, we studied the effects of monepantel on a nicotine preferring homomeric nAChR subtype from A. suum comprising of ACR-16; a pyrantel/tribendimidine preferring heteromeric subtype from O. dentatum comprising UNC-29, UNC-38 and UNC-63 subunits; and a levamisole preferring subtype (O. dentatum) comprising UNC-29, UNC-38, UNC-63 and ACR-8 subunits. For each subtype tested, monepantel applied in isolation produced no measurable currents thereby ruling out an agonist action. When monepantel was continuously applied, it reduced the amplitude of acetylcholine induced currents in a concentration-dependent manner. In all three subtypes, monepantel acted as a non-competitive antagonist on the expressed receptors. ACR-16 from A. suum was particularly sensitive to monepantel inhibition (IC50 values: 1.6 ±â€¯3.1 nM and 0.2 ±â€¯2.3 µM). We also investigated the effects of monepantel on muscle flaps isolated from adult A. suum. The drug did not significantly increase baseline tension when applied on its own. As with acetylcholine induced currents in the heterologously expressed receptors, contractions induced by acetylcholine were antagonized by monepantel. Further investigation revealed that the inhibition was a mixture of competitive and non-competitive antagonism. Our findings suggest that monepantel is active on multiple nAChR subtypes.

(S)-5-ethynyl-anabasine, a novel compound, is a more potent agonist than other nicotine alkaloids on the nematode Asu-ACR-16 receptor.

Nematode parasites infect ∼2 billion people world-wide. Infections are treated and prevented by anthelmintic drugs, some of which act on nicotinic acetylcholine receptors (nAChRs). There is an unmet need for novel therapeutic agents because of concerns about the development of resistance. We have selected Asu-ACR-16 from a significant nematode parasite genus, Ascaris suum, as a pharmaceutical target and nicotine as our basic moiety (EC50 6.21 ± 0.56 µM, Imax 82.39 ± 2.52%) to facilitate the development of more effective anthelmintics. We expressed Asu-ACR-16 in Xenopus oocytes and used two-electrode voltage clamp electrophysiology to determine agonist concentration-current-response relationships and determine the potencies (EC50s) of the agonists. Here, we describe the synthesis of a novel agonist, (S)-5-ethynyl-anabasine, and show that it is more potent (EC50 0.14 ± 0.01 µM) than other nicotine alkaloids on Asu-ACR-16. Agonists acting on ACR-16 receptors have the potential to circumvent drug resistance to anthelmintics, like levamisole, that do not act on the ACR-16 receptors.

The Ascaris suum nicotinic receptor, ACR-16, as a drug target: Four novel negative allosteric modulators from virtual screening.

Soil-transmitted helminth infections in humans and livestock cause significant debility, reduced productivity and economic losses globally. There are a limited number of effective anthelmintic drugs available for treating helminths infections, and their frequent use has led to the development of resistance in many parasite species. There is an urgent need for novel therapeutic drugs for treating these parasites. We have chosen the ACR-16 nicotinic acetylcholine receptor of Ascaris suum (Asu-ACR-16), as a drug target and have developed three-dimensional models of this transmembrane protein receptor to facilitate the search for new bioactive compounds. Using the human α7 nAChR chimeras and Torpedo marmorata nAChR for homology modeling, we defined orthosteric and allosteric binding sites on the Asu-ACR-16 receptor for virtual screening. We identified four ligands that bind to sites on Asu-ACR-16 and tested their activity using electrophysiological recording from Asu-ACR-16 receptors expressed in Xenopus oocytes. The four ligands were acetylcholine inhibitors (SB-277011-A, IC50, 3.12 ± 1.29 µM; (+)-butaclamol Cl, IC50, 9.85 ± 2.37 µM; fmoc-1, IC50, 10.00 ± 1.38 µM; fmoc-2, IC50, 16.67 ± 1.95 µM) that behaved like negative allosteric modulators. Our work illustrates a structure-based in silico screening method for seeking anthelmintic hits, which can then be tested electrophysiologically for further characterization.

Anthelmintics: The best way to predict the future is to create it.

'The best way to predict the future is to create it.' When we look at drugs that are used to control parasites, we see that new knowledge has been created (discovered) about their modes of action. This knowledge will allow us to predict combinations of drugs which can be used together rationally to increase the spectrum of action and to slow the development of anthelmintic resistance. In this paper we comment on some recent observations of ours on the modes of action of emodepside, diethylcarbamazine and tribendimidine. Emodepside increases the activation of a SLO-1 K(+) current inhibiting movement, and diethylcarbamazine has a synergistic effect on the effect of emodepside on the SLO-1 K(+) current, increasing the size of the response. The combination may be considered for further testing for therapeutic use. Tribendimidine is a selective cholinergic nematode B-subtype nAChR agonist, producing muscle depolarization and contraction. It has different subtype selectivity to levamisole and may be effective in the presence of some types of levamisole resistance. The new information about the modes of action may aid the design of rational drug combinations designed to slow the development of resistance or increase the spectrum of action.