Search

This paper presents a convolutional neural network (CNN) to classify between the conventionally and organically cultivated Memecik varieties of green olives. The image forming method called the rising paper chromatography is utilized in preparing the images of Memecik varieties of green olives for CNN. In the rising chromatography method, 20, 30, and 40% sample concentrations were determined as the suitable concentrations for both organic and conventional olives. The concentrations of AgNO3 and FeSO4 were determined as 0.25, 0.5, 0.75 and 1% for both conventional and organic samples. The visual differences used for differentiation of different types of Memecik green olives are usually determined according to the regional color differences, the vivid color occurrence, the width and the frequency of bowl occurrence, the thin line, and the picks at drop zone by the expert assessors. The testing results in this study verified the effectiveness of the CNN methodology in differentiating between the organically and conventionally cultivated Memecik green olives. The newly designed neural network achieved 100% accuracy. Furthermore, this high accuracy achieved by CNN might suggest that it can be effectively used in place of the expert assessors.

Map products, including charts and large-scale engineering drawings, contain a wealth of positional and longitudinal (time-referenced) information, available and cheap to produce for those who are constructing Geographic or Land Use Information Systems. If these map products are on stable based material and are not previously handled, the transformation of projection to digitizer coordinate systems would be a matter of determining scale, orientation and translation parameters. In this paper I discuss ways to transform projection coordinates to digitizer values, recognizing that the paper bases are not stable based. Test values are computed and compared for methods and results are interpreted with respect to the geometry of the operation.

Purpose Structure-guided total variation is a recently introduced prior that allows reconstruction of images using knowledge of the location and orientation of edges in a reference image. In this work, we demonstrate the advantages of a variant of structure-guided total variation known as directional total variation (DTV), over traditional total variation (TV), in the context of compressed-sensing reconstruction and super-resolution. Methods We compared TV and DTV in retrospectively undersampled ex vivo diffusion tensor imaging and diffusion spectrum imaging data from healthy, sham, and hypertrophic rat hearts. Results In compressed sensing at an undersampling factor of 8, the RMS error of mean diffusivity and fractional anisotropy relative to the fully sampled ground truth were 44% and 20% lower in DTV compared with TV. In super-resolution, these values were 29% and 14%, respectively. Similarly, we observed improvements in helix angle, transverse angle, sheetlet elevation, and sheetlet azimuth. The RMS error of the diffusion kurtosis in the undersampled data relative to the ground truth was uniformly lower (22% on average) with DTV compared to TV. Conclusion Acquiring one fully sampled non-diffusion-weighted image and 10 diffusion-weighted images at 8× undersampling would result in an 80% net reduction in data needed. We demonstrate efficacy of the DTV algorithm over TV in reducing data sampling requirements, which can be translated into higher apparent resolution and potentially shorter scan times. This method would be equally applicable in diffusion MRI applications outside the heart.

PURPOSE In rapidly acquired functional MRI (fast fMRI) data, the noise serial correlations (SC) can produce problematically overestimated T-statistics which lead to invalid statistical inferences. This study aims to evaluate and improve the accuracy of high-order autoregressive model (AR(p), where p is the model order) based prewhitening method in the SC correction. METHODS Fast fMRI images were acquired at rest (null data) using a multiband simultaneous multi-slice echo planar imaging pulse sequence with repetition time (TR) = 300 and 500 ms. The SC effect in the fast fMRI data was corrected using the prewhitening method based on two AR(p) models: (1) the conventional model (fixed AR(p)) which preselects a constant p for all the image voxels; (2) an improved model (ARAICc ) that employs the corrected Akaike information criterion voxel-wise to automatically select the model orders for each voxel. To evaluate accuracy of SC correction, false positive characteristics were measured by assuming the presence of block and event-related tasks in the null data without image smoothing. The performance of prewhitening was also examined in smoothed images by adding pseudo task fMRI signals into the null data and comparing the detected to simulated activations (ground truth). RESULTS The measured false positive characteristics agreed well with the theoretical curve when using the ARAICc , and the activation maps in the smoothed data matched the ground truth. The ARAICc showed improved performance than the fixed AR(p) method. CONCLUSION The ARAICc can effectively remove noise SC, and accurate statistical analysis results can be obtained with the ARAICc correction in fast fMRI.

The application of non-destructive process analytical technologies in the area of food science got a lot of attention the past years. In this work we used hyperspectral imaging to detect mould on milk agar and cheese. Principal component analysis is applied to hyperspectral data to localise and visualise mycelia on the samples’ surface. It is also shown that the PCA loadings obtained from a set of training samples can be applied to hyperspectral data from new test samples to detect the presence of mould on these. For both the agar and cheeselets, the first three principal components contained more than 99 % of the total variance. The spatial projection of the second principal component highlights the presence of mould on cheeselets. The proposed analysis methods can be adopted in industry to detect mould on cheeselets at an early stage and with further testing this application may also be extended to other food products., Graphical abstract Image 1, Highlights • Hyperspectral imaging can be used for non-destructive analysis of contamination in food products. • Principal component analysis (PCA) was applied to milk agar and cheeselet samples to localise and visualise mould growing on the samples. • The results from PCA applied to hyperspectral data shows that the technique can be used to identify and localise growth of mould on food samples.

Contains fulltext : 219835.pdf (Publisher’s version ) (Open Access) PURPOSE: To study the influence of gradient echo-based contrasts as input channels to a 3D patch-based neural network trained for synthetic CT (sCT) generation in canine and human populations. METHODS: Magnetic resonance images and CT scans of human and canine pelvic regions were acquired and paired using nonrigid registration. Magnitude MR images and Dixon reconstructed water, fat, in-phase and opposed-phase images were obtained from a single T1 -weighted multi-echo gradient-echo acquisition. From this set, 6 input configurations were defined, each containing 1 to 4 MR images regarded as input channels. For each configuration, a UNet-derived deep learning model was trained for synthetic CT generation. Reconstructed Hounsfield unit maps were evaluated with peak SNR, mean absolute error, and mean error. Dice similarity coefficient and surface distance maps assessed the geometric fidelity of bones. Repeatability was estimated by replicating the training up to 10 times. RESULTS: Seventeen canines and 23 human subjects were included in the study. Performance and repeatability of single-channel models were dependent on the TE-related water-fat interference with variations of up to 17% in mean absolute error, and variations of up to 28% specifically in bones. Repeatability, Dice similarity coefficient, and mean absolute error were statistically significantly better in multichannel models with mean absolute error ranging from 33 to 40 Hounsfield units in humans and from 35 to 47 Hounsfield units in canines. CONCLUSION: Significant differences in performance and robustness of deep learning models for synthetic CT generation were observed depending on the input. In-phase images outperformed opposed-phase images, and Dixon reconstructed multichannel inputs outperformed single-channel inputs.

We start with the assumption that temporal and spatial knowledge usually captured by constraint networks can be represented and queried more effectively by using the scheme of indefinite constraint databases. Because query evaluation in this scheme is in general a hard computational problem, we seek tractable instances of query evaluation. We assume that we have a class of constraints C with some reasonable computational and closure properties (the computational properties of interest are that the satisfiability problem and an appropriate version of the variable elimination problem for C should be solvable in PTIME). Under this assumption, we exhibit general classes of indefinite constraint databases and first-order modal queries for which query evaluation can be done with PTIME data complexity. We then search for tractable instances of C among the subclasses of Horn disjunctive linear constraints over the rationals. From previous research we know that the satisfiability problem for Horn disjunctive linear constraints is solvable in PTIME, but not the variable elimination problem. Thus we try to discover subclasses of Horn disjunctive linear constraints with tractable variable elimination problems. The class of UTVPI≠ constraints is the largest class that we show to have this property. Finally, we restate our general tractability results with C ranging over the newly discovered tractable classes. Interesting tractable query answering problems for indefinite temporal and spatial constraint databases are identified in this way. We close our complexity analysis by precisely outlining the frontier between tractable and possibly intractable query answering problems.

COVID-19 pandemic has affected all aspects of people's lives and disrupted the economy. Forecasting the number of cases infected with this virus can help authorities make accurate decisions on the interventions that must be implemented to control the pandemic. Investigation of the studies on COVID-19 forecasting indicates that various techniques such as statistical, mathematical, and machine and deep learning have been utilized. Although deep learning models have shown promising results in this context, their performance can be improved using auxiliary features. Therefore, in this study, we propose two hybrid deep learning methods that utilize the statistical features as auxiliary inputs and associate them with their main input. Specifically, we design a hybrid method of the multihead attention mechanism and the statistical features (ATT_FE) and a combined method of convolutional neural network and the statistical features (CNN_FE) and apply them to COVID-19 data of 10 countries with the highest number of confirmed cases. The results of experiments indicate that the hybrid models outperform their conventional counterparts in terms of performance measures. The experiments also demonstrate the superiority of the hybrid ATT_FE method over the long short-term memory model.

The parameters of the models described by Rumelhart and Greeno in this journal (1971) are constrained in certain ways. Neglect of this fact in their paper leads them to an inadmissible set of parameter values, and an invalid argument and statement concerning the equivalence of two models. However, their conclusion that the Restle model fits their data better than the Luce model remains unchanged.

The generalized modus ponens is a fuzzy logic pattern of reasoning that permits inferences to be made with rules having imprecise information in both their antecedent and consequent parts. Several alternatives are available to represent the meaning one wishes to assign to a given rule. This paper first explores four of the most often encountered possibilities, in the case where a single rule is considered at a time. Second, the behavior of two of them (which seem sufficient for practical use in deduction systems) is investigated in the situation where the dependency between antecedent and consequent variables is described by a collection of rules rather than a single rule. Conjectures are made about what is semantically important in the result yielded by the exact computation of the generalized modus ponens. With these hypothesis it is shown that one can get a meaningful approximation of what is produced by the generalized modus ponens technique and also avoid the well-known inefficiency problem associated with its computation.

In this paper a new approach towards temporal reasoning is presented that scales up from the temporal relations commonly used in Allen's qualitative interval calculus and in quantitative temporal constraint satisfaction problems to include interval relations with distances, temporal rules and other non-binary relations into the reasoning scheme. For this purpose, we generalize well-known methods for constraint propagation, determination of consistency and computation of the minimal network from simpler schemes that only allow for binary relations. Thereby, we find that levels of granularity play a major role for applying these techniques in our more expressive framework. Indeed, the technical preliminaries we provide are especially apt to investigate the switching between different granularities of representation, hence illucitating and exploiting the tradeoff between expressiveness and efficiency of temporal reasoning schemes on the one side and between expressiveness and understandability on the other side.

We show that slight technical changes in the definition transform the probability of fuzzy events introduced by R. R. Yager [16] into a new concept of such probabilities having nice properties, both from an intuitive and from a mathematical point of view: monotonicity, additivity, and continuity.

On each trial Ss viewed one of the patterns of six connected squares that result when the faces of a cube are unfolded onto a flat surface. The Ss tried, as rapidly as possible, to decide whether two arrows, each marked on an edge of a (different) square, would or would not meet if the squares were folded back up into the cube. The time required to make such decisions increased linearly (from 2 to about 15 sec) with the sum of the number of squares that would be involved in each fold, if those folds were actually performed physically.

Background Margin reflex distance 1 (MRD1), margin reflex distance 2 (MRD2), and levator muscle function (LF) are crucial metrics for ptosis evaluation and management. However, manual measurements of MRD1, MRD2, and LF are time-consuming, subjective, and prone to human error. Smartphone-based artificial intelligence (AI) image processing is a potential solution to overcome these limitations. Objective We propose the first smartphone-based AI-assisted image processing algorithm for MRD1, MRD2, and LF measurements. Methods This observational study included 822 eyes of 411 volunteers aged over 18 years from August 1, 2020, to April 30, 2021. Six orbital photographs (bilateral primary gaze, up-gaze, and down-gaze) were taken using a smartphone (iPhone 11 Pro Max). The gold-standard measurements and normalized eye photographs were obtained from these orbital photographs and compiled using AI-assisted software to create MRD1, MRD2, and LF models. Results The Pearson correlation coefficients between the gold-standard measurements and the predicted values obtained with the MRD1 and MRD2 models were excellent (r=0.91 and 0.88, respectively) and that obtained with the LF model was good (r=0.73). The intraclass correlation coefficient demonstrated excellent agreement between the gold-standard measurements and the values predicted by the MRD1 and MRD2 models (0.90 and 0.84, respectively), and substantial agreement with the LF model (0.69). The mean absolute errors were 0.35 mm, 0.37 mm, and 1.06 mm for the MRD1, MRD2, and LF models, respectively. The 95% limits of agreement were –0.94 to 0.94 mm for the MRD1 model, –0.92 to 1.03 mm for the MRD2 model, and –0.63 to 2.53 mm for the LF model. Conclusions We developed the first smartphone-based AI-assisted image processing algorithm for eyelid measurements. MRD1, MRD2, and LF measures can be taken in a quick, objective, and convenient manner. Furthermore, by using a smartphone, the examiner can check these measurements anywhere and at any time, which facilitates data collection.

Nine latent fingerprint examiners participated in a collaborative study in the use of a steam iron to accelerate chemical development of latent images on bond and newsprint papers treated with a 0.5% solution of ninhydrin in acetone. Four latent images were placed on each paper by the Associate Referee during an 8 hr period. The papers were paired and numbered 1, 2, and 3. Three pairs were mailed to each collaborator who treated Pair 1 by dipping, Pair 2 by brushing or swabbing, and Pair 3 by spraying. After air-drying, the papers were subjected to heat and steam from a household steam iron until the images developed. The average time for developing all images was 5.8 min/paper. Of the total images available, 92.1% were developed to some degree; 47.9% of these images or 43.5% of all images were identified by the collaborators. The method has been adopted as official first action.

PURPOSE Intravoxel incoherent motion (IVIM) analysis gives information on tissue diffusion and perfusion and may thus have a potential for e.g. tumor tissue characterization. This work aims to study if clustering based on IVIM parameter maps can identify tumor subregions, and to assess the relevance of obtained subregions by histological analysis. METHODS Fourteen mice with human neuroendocrine tumors were examined with diffusion-weighted imaging to obtain IVIM parameter maps. Gaussian mixture models with IVIM maps from all tumors as input were used to partition voxels into k clusters, where k = 2 was chosen for further analysis based on goodness of fit. Clustering was performed with and without the perfusion-related IVIM parameter D* , and with and without including spatial information. The validity of the clustering was assessed by comparison with corresponding histologically stained tumor sections. A Ki-67-based index quantifying the degree of tumor proliferation was considered appropriate for the comparison based on the obtained cluster characteristics. RESULTS The clustering resulted in one class with low diffusion and high perfusion and another with slightly higher diffusion and low perfusion. Strong agreement was found between tumor subregions identified by clustering and subregions identified by histological analysis, both regarding size and spatial agreement. Neither D* nor spatial information had substantial effects on the clustering results. CONCLUSIONS The results of this study show that IVIM parameter maps can be used to identify tumor subregions using a data-driven framework based on Gaussian mixture models. In the studied tumor model, the obtained subregions showed agreement with proliferative activity.

Purpose To obtain a fast and robust fat-water separation with simultaneous estimation of water T1 , fat T1 , and fat fraction maps. Methods We modified an MR fingerprinting (MRF) framework to use a single dictionary combination of a water and fat dictionary. A variable TE acquisition pattern with maximum TE = 4.8 ms was used to increase the fat-water separability. Radiofrequency (RF) spoiling was used to reduce the size of the dictionary by reducing T2 sensitivity. The technique was compared both in vitro and in vivo to an MRF method that incorporated 3-point Dixon (DIXON MRF), as well as Cartesian IDEAL with different acquisition parameters. Results The proposed dictionary-based fat-water separation technique (DBFW MRF) successfully provided fat fraction, water, and fat T1 , B0 , and B1+ maps both in vitro and in vivo. The fat fraction and water T1 values obtained with DBFW MRF show excellent agreement with DIXON MRF as well as with the reference values obtained using a Cartesian IDEAL with a long TR (concordance correlation coefficient: 0.97/0.99 for fat fraction-water T1 ). Whereas fat fraction values with Cartesian IDEAL were degraded in the presence of T1 saturation, MRF methods successfully estimated and accounted for T1 in the fat fraction estimates. Conclusion The DBFW MRF technique can successfully provide T1 and fat fraction quantification in under 20 s per slice, intrinsically correcting T1 biases typical of fast Dixon techniques. These features could improve the diagnostic quality and use of images in presence of fat.

Significance: The Mueller matrix decomposition method is widely used for the analysis of biological samples. However, its presumed sequential appearance of the basic optical effects (e.g., dichroism, retardance, and depolarization) limits its accuracy and application. Aim: An approach is proposed for detecting and classifying human melanoma and non-melanoma skin cancer lesions based on the characteristics of the Mueller matrix elements and a random forest (RF) algorithm. Approach: In the proposal technique, 669 data points corresponding to the 16 elements of the Mueller matrices obtained from 32 tissue samples with squamous cell carcinoma (SCC), basal cell carcinoma (BCC), melanoma, and normal features are input into an RF classifier as predictors. Results: The results show that the proposed model yields an average precision of 93%. Furthermore, the classification results show that for biological tissues, the circular polarization properties (i.e., elements m44, m34, m24, and m14 of the Mueller matrix) dominate the linear polarization properties (i.e., elements m13, m31, m22, and m41 of the Mueller matrix) in determining the classification outcome of the trained classifier. Conclusions: Overall, our study provides a simple, accurate, and cost-effective solution for developing a technique for classification and diagnosis of human skin cancer.

Background Advanced prediction of the daily incidence of COVID-19 can aid policy making on the prevention of disease spread, which can profoundly affect people's livelihood. In previous studies, predictions were investigated for single or several countries and territories. Objective We aimed to develop models that can be applied for real-time prediction of COVID-19 activity in all individual countries and territories worldwide. Methods Data of the previous daily incidence and infoveillance data (search volume data via Google Trends) from 215 individual countries and territories were collected. A random forest regression algorithm was used to train models to predict the daily new confirmed cases 7 days ahead. Several methods were used to optimize the models, including clustering the countries and territories, selecting features according to the importance scores, performing multiple-step forecasting, and upgrading the models at regular intervals. The performance of the models was assessed using the mean absolute error (MAE), root mean square error (RMSE), Pearson correlation coefficient, and Spearman correlation coefficient. Results Our models can accurately predict the daily new confirmed cases of COVID-19 in most countries and territories. Of the 215 countries and territories under study, 198 (92.1%) had MAEs 0.8. For the 215 countries and territories, the mean MAE was 5.42 (range 0.26-15.32), the mean RMSE was 9.27 (range 1.81-24.40), the mean Pearson correlation coefficient was 0.89 (range 0.08-0.99), and the mean Spearman correlation coefficient was 0.84 (range 0.2-1.00). Conclusions By integrating previous incidence and Google Trends data, our machine learning algorithm was able to predict the incidence of COVID-19 in most individual countries and territories accurately 7 days ahead.

We evaluated the performance of a newly developed three-dimensional (3D) model-based global-to-local registration of multiple organs, by comparing it with a 3D model-based global registration in the prostate region. This study included 220 prostate cancer patients who underwent intensity-modulated radiotherapy or volumetric-modulated arc therapy. Our registration proceeded sequentially, i.e. global registration including affine and piece-wise affine transformation followed by local registration. As a local registration, Laplacian-based and finite element method-based registration was implemented in Algorithm A and B, respectively. Algorithm C was for global registration alone. The template models for the prostate, seminal vesicles, rectum and bladder were constructed from the first 20 patients, and then three different registrations were performed on these organs for the remaining 200 patients, to assess registration accuracy. The 75th percentile Hausdorff distance was 1 mm in Algorithm B, except for the prostate; and 3.9 mm for the prostate and >7.8 mm for other organs in Algorithm C. The median computation time to complete registration was

Strategies used in artificial grammar learning can shed light into the abilities of different species to extract regularities from the environment. In the A(X)nB rule, A and B items are linked but assigned to different positional categories and separated by distractor items. Open questions are how widespread is the ability to extract positional regularities from A(X)nB patterns, which strategies are used to encode positional regularities and whether individuals exhibit preferences for absolute or relative position encoding. We used visual arrays to investigate whether cotton-top tamarins (Saguinus oedipus) can learn this rule and which strategies they use. After training on a subset of exemplars, half of the tested monkeys successfully generalized to novel combinations. These tamarins discriminated between categories of tokens with different properties (A, B, X) and detected a positional relationship between non-adjacent items even in the presence of novel distractors. Generalization, though, was incomplete, since we observed a failure with items that during training had always been presented in reinforced arrays. The pattern of errors revealed that successful subjects used visual similarity with training stimuli to solve the task, and that tamarins extracted the relative position of As and Bs rather than their absolute position, similarly to what observed in other species. Relative position encoding appears to be the default strategy in different tasks and taxa.

Accurate information of the lung shape analysis and its anatomical variations is very noticeable in medical imaging. The normal variations of the lung shape can be interpreted as a normal lung. In contrast, abnormal variations of the lung shape can be a result of one of the pulmonary diseases. The goal of this study is twofold: (1) represent two lung shape models which are different at the reference points in registration process considering to show their impact on estimating the inter-patient 2D lung shape variations and (2) using the obtained models in lung field segmentation by utilizing active shape model (ASM) technique. The represented models which showed the inter-patient 2D lung shape variations in two different forms are fully compared and evaluated. The results show that the models along with standard principal component analysis (PCA) can be able to explain more than 95% of total variations in all cases using only first 7 principal component (PC) modes for both lungs. Both models are used in ASM-based segmentation technique for lung field segmentation. The segmentation results are evaluated using leave-one-out cross validation technique. According to the experimental results, the proposed method has average dice similarity coefficient of 97.1% and 96.1% for the right and the left lung, respectively. The results show that the proposed segmentation method is more stable and accurate than other model-based techniques to inter-patient lung field segmentation.

Rupture risk assessment of abdominal aortic aneurysms (AAAs) by means of quantifying wall stress is a common biomechanical strategy. However, the clinical translation of this approach has been greatly limited due to the complexity associated with the computational tools required for its implementation. Thus, being able to estimate wall stress using nonbiomechanical markers that can be quantified as a direct outcome of clinical image segmentation would be advantageous in improving the potential implementation of said strategy. In the present work, we investigated the use of geometric indices to predict patient-specific AAA wall stress by means of a novel neural network (NN) modeling approach. We conducted a retrospective review of existing clinical images of two patient groups: 98 asymptomatic and 50 symptomatic AAAs. The images were subject to a protocol consisting of image segmentation, processing, volume meshing, finite element modeling, and geometry quantification, from which 53 geometric indices and the spatially averaged wall stress (SAWS) were calculated. SAWS estimated from finite element analysis was considered the gold standard for the predictions. We developed feed-forward NN models composed of an input layer, two dense layers, and an output layer using Keras, a deep learning library in python. The NN models were trained, tested, and validated independently for both AAA groups using all geometric indices, as well as a reduced set of indices resulting from a variable reduction procedure. We compared the performance of the NN models with two standard machine learning algorithms (MARS: multivariate adaptive regression splines and GAM: generalized additive model) and a linear regression model (GLM: generalized linear model). With the reduced sets of indices, the NN-based approach exhibited the highest mean goodness-of-fit (for the symptomatic group 0.71 and for the asymptomatic group 0.79) and lowest mean relative error (17% for both groups). In contrast, MARS yielded a mean goodness-of-fit of 0.59 for the symptomatic group and 0.77 for the asymptomatic group, with relative errors of 17% for the symptomatic group and 22% for the asymptomatic group. GAM had a mean goodness-of-fit of 0.70 for the symptomatic group and 0.80 for the asymptomatic group, with relative errors of 16% for the symptomatic group and 20% for the asymptomatic group. GLM did not perform as well as the other algorithms, with a mean goodness-of-fit of 0.53 for the symptomatic group and 0.70 for the asymptomatic group, with relative errors of 19% for the symptomatic group and 23% for the asymptomatic group. Nevertheless, the NN models required a reduced set of 15 and 13 geometric indices to predict SAWS for the symptomatic and asymptomatic AAA groups, respectively. This was in contrast to the reduced set of nine and eight geometric indices required to predict SAWS with the MARS and GAM algorithms for each AAA group, respectively. The use of NN modeling represents a promising alternative methodology for the estimation of AAA wall stress using geometric indices as surrogates, in lieu of finite element modeling. The performance metrics of NN models are expected to improve with significantly larger group sizes, given the suitability of NN modeling for “big data” applications.

It is shown that when two images are registered by cross-correlating one image with a functional of the other image the minimum registration error variance results when the operation performed cofresponds to that of matched filtering.

Quantitative metrics in lung computed tomography (CT) images have been widely used, often without a clear connection with physiology. This work proposes a patient-independent model for the estimation of well-aerated volume of lungs in CT images (WAVE). A Gaussian fit, with mean (Mu.f) and width (Sigma.f) values, was applied to the lower CT histogram data points of the lung to provide the estimation of the well-aerated lung volume (WAVE.f). Independence from CT reconstruction parameters and respiratory cycle was analysed using healthy lung CT images and 4DCT acquisitions. The Gaussian metrics and first order radiomic features calculated for a third cohort of COVID-19 patients were compared with those relative to healthy lungs. Each lung was further segmented in 24 subregions and a new biomarker derived from Gaussian fit parameter Mu.f was proposed to represent the local density changes. WAVE.f resulted independent from the respiratory motion in 80% of the cases. Differences of 1%, 2% and up to 14% resulted comparing a moderate iterative strength and FBP algorithm, 1 and 3 mm of slice thickness and different reconstruction kernel. Healthy subjects were significantly different from COVID-19 patients for all the metrics calculated. Graphical representation of the local biomarker provides spatial and quantitative information in a single 2D picture. Unlike other metrics based on fixed histogram thresholds, this model is able to consider the inter-and intra-subject variability. In addition, it defines a local biomarker to quantify the severity of the disease, independently of the observer., 31 pages, 7 figures, accepted in EJMP

Motivation Protein fold recognition is a key step for template-based modeling approaches to protein structure prediction. Although closely related folds can be easily identified by sequence homology search in sequence databases, fold recognition is notoriously more difficult when it involves the identification of distantly related homologs. Recent progress in residue–residue contact and distance prediction opens up the possibility of improving fold recognition by using structural information contained in predicted distance and contact maps. Results Here we propose to use the congruence coefficient as a metric of similarity between maps. We prove that this metric has several interesting mathematical properties which allow one to compute in polynomial time its exact mean and variance over all possible (exponentially many) alignments between two symmetric matrices, and assess the statistical significance of similarity between aligned maps. We perform fold recognition tests by recovering predicted target contact/distance maps from the two most recent Critical Assessment of Structure Prediction editions and over 27 000 non-homologous structural templates from the ECOD database. On this large benchmark, we compare fold recognition performances of different alignment tools with their own similarity scores against those obtained using the congruence coefficient. We show that the congruence coefficient overall improves fold recognition over other methods, proving its effectiveness as a general similarity metric for protein map comparison. Availability and implementation The congruence coefficient software CCpro is available as part of the SCRATCH suite at: http://scratch.proteomics.ics.uci.edu/. Supplementary information Supplementary data are available at Bioinformatics online.

Funder: Cantab Capital Institute for the Mathematics of Information, Funder: Alan Turing Institute; doi: https://doi.org/10.13039/100012338, In recent years the use of convolutional layers to encode an inductive bias (translational equivariance) in neural networks has proven to be a very fruitful idea. The successes of this approach have motivated a line of research into incorporating other symmetries into deep learning methods, in the form of group equivariant convolutional neural networks. Much of this work has been focused on roto-translational symmetry of R d , but other examples are the scaling symmetry of R d and rotational symmetry of the sphere. In this work, we demonstrate that group equivariant convolutional operations can naturally be incorporated into learned reconstruction methods for inverse problems that are motivated by the variational regularisation approach. Indeed, if the regularisation functional is invariant under a group symmetry, the corresponding proximal operator will satisfy an equivariance property with respect to the same group symmetry. As a result of this observation, we design learned iterative methods in which the proximal operators are modelled as group equivariant convolutional neural networks. We use roto-translationally equivariant operations in the proposed methodology and apply it to the problems of low-dose computerised tomography reconstruction and subsampled magnetic resonance imaging reconstruction. The proposed methodology is demonstrated to improve the reconstruction quality of a learned reconstruction method with a little extra computational cost at training time but without any extra cost at test time.

Publisher Summary This chapter focuses on connection theory of children's language and linguistic theory. It discusses the problem of a child's recognition of nonuniversal aspects of deep structure. It is not the case that deep structure is the same for all languages. Grammatical relations are, by hypothesis, universal, but the order of elements is not. It is not the case that simple, active, declarative sentences always reflect deep structure order directly. It is not the case that the most frequent forms in surface structure reflect deep structure. Traditionally, the determination of base word order depends upon analysis of the transformational component. The most important transformation in German is the verb-second transformation which transfers an element from final position to second position in the creation of declarative sentences. It is the broad applicability of this transformation that makes elegantly simple a description of German that uses a verb-final base structure. The subordinate-clause strategy is a powerful mechanism for the discovery of deep structure.

A digester, one of the major units of Kraft process, has a function for conversion of wood into wood pulp. It is controlled by monitoring Kappa number with nonlinear reaction and has a long resident time. This paper aims to present the prediction of kappa number in pulp digester in advance for 1-3 hours by using Long Short-Term Memory (LSTM) neural network. The structures of LSTM inputs consists of effective alkali, temperature, and outlet lignin content. The prediction has been developed with nonlinear simulations of digester reactions. The results reveal that a kappa prediction can be predicted in advance for 1, 2 and 3 hours with percentages of error 1.1, 1.9 and 2.9 respectively. It could be beneficial for an operator to decide on feedforward compensation before it is out of control.

// Qi Zhao 1, 2 , Di Xie 1 , Hongsheng Liu 2, 3 , Fan Wang 4, 5 , Gui-Ying Yan 6 and Xing Chen 7 1 School of Mathematics, Liaoning University, Shenyang, China 2 Research Center for Computer Simulating and Information Processing of Bio-Macromolecules of Liaoning Province, Shenyang, China 3 School of Life Science, Liaoning University, Shenyang, China 4 School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, China 5 Jiangsu Key Laboratory of Mine Mechanical and Electrical Equipment, China University of Mining and Technology, Xuzhou, China 6 Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China 7 School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China Correspondence to: Qi Zhao, email: zhaoqi@lnu.edu.cn Xing Chen, email: xingchen@amss.ac.cn Keywords: microRNA; disease; association prediction; spy strategy; super cluster strategy Received: July 18, 2017 Accepted: October 30, 2017 Published: December 01, 2017 ABSTRACT In the biological field, the identification of the associations between microRNAs (miRNAs) and diseases has been paid increasing attention as an extremely meaningful study for the clinical medicine. However, it is expensive and time-consuming to confirm miRNA-disease associations by experimental methods. Therefore, in recent years, several effective computational models for predicting the potential miRNA-disease associations have been developed. In this paper, we proposed the Spy and Super Cluster strategy for MiRNA-Disease Association prediction (SSCMDA) based on known miRNA-disease associations, integrated disease similarity and integrated miRNA similarity. For problems of mixed unknown miRNA-disease pairs containing both potential associations and real negative associations, which will lead to inaccurate prediction, spy strategy is adopted by SSCMDA to identify reliable negative samples from the unknown miRNA-disease pairs. Moreover, the super-cluster strategy could gather as many positive samples as possible to improve the accuracy of the prediction by overcoming the shortage of lacking sufficient positive training samples. As a result, the AUCs of global leave-one-out cross validation (LOOCV), local LOOCV and 5-fold cross validation were 0.9007, 0.8747 and 0.8806+/-0.0025, respectively. According to the AUC results, SSCMDA has shown a significant improvement compared with some previous models. We further carried out case studies based on various version of HMDD database to test the prediction performance robustness of SSCMDA. We also implemented case study to examine whether SSCMDA was effective for new diseases without any known associated miRNAs. As a result, a large proportion of the predicted miRNAs have been verified by experimental reports.

Jacquet-Lagreze’s article on semiorders in multi-attribute utility theory (MAUT) is innovative and useful. Innovative, because it combines two previously separate concepts in utility theory, that of semiorders and that of multi-attribute preferences in modeling multi-criteria decision making. Useful, because it describes detailed techniques for assessing multi-attribute preferences that can be applied whenever traditional models are not feasible because of a failure of the weak order assumption. The perspective of Jacquet-Lagreze’s paper is mainly technological, dealing with the ‘how’ of preference assessment rather than with an axiomatic formulation of his models. To understand the following comments it is crucial to know that they were written from a different perspective toward the treatment of semiorders in MAUT. The orientation of these comments is measurement theoretic asking for a justification of models rather than for the techniques of their implementation.

This paper extends the applications of belief-networks to include the revision of belief commitments , i.e., the categorical acceptance of a subset of hypotheses which, together, constitute the most satisfactory explanation of the evidence at hand. A coherent model of non-monotonic reasoning is established and distributed algorithms for belief revision are presented. We show that, in singly-connected networks, the most satisfactory explanation can be found in linear time by a message-passing algorithm similar to the one used in belief updating. In multiply-connected networks, the problem may be exponentially hard but, if the network is sparse, topological considerations can be used to render the interpretation task tractable. In general, finding the most probable combination of hypotheses is no more complex than computing the degree of belief for any individual hypothesis. Applications to medical diagnosis are illustrated.

We explore the problem of variable selection in a case‐control setting with mass spectrometry proteomic data consisting of paired measurements. Each pair corresponds to a distinct isotope cluster and each component within pair represents a summary of isotopic expression based on either the intensity or the shape of the cluster. Our objective is to identify a collection of isotope clusters associated with the disease outcome and at the same time assess the predictive added‐value of shape beyond intensity while maintaining predictive performance. We propose a Bayesian model that exploits the paired structure of our data and utilizes prior information on the relative predictive power of each source by introducing multiple layers of selection. This allows us to make simultaneous inference on which are the most informative pairs and for which—and to what extent—shape has a complementary value in separating the two groups. We evaluate the Bayesian model on pancreatic cancer data. Results from the fitted model show that most predictive potential is achieved with a subset of just six (out of 1289) pairs while the contribution of the intensity components is much higher than the shape components. To demonstrate how the method behaves under a controlled setting we consider a simulation study. Results from this study indicate that the proposed approach can successfully select the truly predictive pairs and accurately estimate the effects of both components although, in some cases, the model tends to overestimate the inclusion probability of the second component.

Background Pill image recognition systems are difficult to develop due to differences in pill color, which are influenced by external factors such as the illumination from and the presence of a flash. Objective In this study, the differences in color between reference images and real-world images were measured to determine the accuracy of a pill recognition system under 12 real-world conditions (ie, different background colors, the presence and absence of a flash, and different exposure values [EVs]). Methods We analyzed 19 medications with different features (ie, different colors, shapes, and dosages). The average color difference was calculated based on the color distance between a reference image and a real-world image. Results For images with black backgrounds, as the EV decreased, the top-1 and top-5 accuracies increased independently of the presence of a flash. The top-5 accuracy for images with black backgrounds increased from 26.8% to 72.6% when the flash was on and increased from 29.5% to 76.8% when the flash was off as the EV decreased. However, the top-5 accuracy increased from 62.1% to 78.4% for images with white backgrounds when the flash was on. The best top-1 accuracy was 51.1% (white background; flash on; EV of +2.0). The best top-5 accuracy was 78.4% (white background; flash on; EV of 0). Conclusions The accuracy generally increased as the color difference decreased, except for images with black backgrounds and an EV of −2.0. This study revealed that background colors, the presence of a flash, and EVs in real-world conditions are important factors that affect the performance of a pill recognition model.

Since the outbreak of the pandemic Coronavirus Disease 2019, the world is in search of novel non-invasive methods for safer and early detection of lung diseases. The pulmonary pathological symptoms reflected through the lung sound opens a possibility of detection through auscultation and of employing spectral, fractal, nonlinear time series and principal component analyses. Thirty-five signals of vesicular and expiratory wheezing breath sound, subjected to spectral analyses shows a clear distinction in terms of time duration, intensity, and the number of frequency components. An investigation of the dynamics of air molecules during respiration using phase portrait, Lyapunov exponent, sample entropy, fractal dimension, and Hurst exponent helps in understanding the degree of complexity arising due to the presence of mucus secretions and constrictions in the respiratory airways. The feature extraction of the power spectral density data and the application of principal component analysis helps in distinguishing vesicular and expiratory wheezing and thereby, giving a ray of hope in accomplishing an early detection of pulmonary diseases through sound signal analysis.

“Bad channels” are common phenomena during scalp electroencephalography (EEG) recording that arise due to various technique-related reasons, and reconstructing signals from bad channels is an inevitable choice in EEG processing. However, current interpolation methods are all based on purely mathematical interpolation theory, ignoring the neurophysiological basis of the EEG signals, and their performance needs to be further improved, especially when there are many scattered or adjacent bad channels. Therefore, a new interpolation method, named the reference electrode standardization interpolation technique (RESIT), was developed for interpolating scalp EEG channels. Resting-state and event-related EEG datasets were used to investigate the performance of the RESIT. The main results showed that (1) assuming 10% bad channels, RESIT can reconstruct the bad channels well; (2) as the percentage of bad channels increased (from 2% to 85%), the absolute and relative errors between the true and RESIT-reconstructed signals generally increased, and the correlations between the true and RESIT signals decreased; (3) for a range of bad channel percentages (2% ~ 85%), the RESIT had lower absolute error (approximately 2.39% ~ 33.5% reduction), lower relative errors (approximately 1.3% ~ 35.7% reduction) and higher correlations (approximately 2% ~ 690% increase) than traditional interpolation methods, including neighbor interpolation (NI) and spherical spline interpolation (SSI). In addition, the RESIT was integrated into the EEG preprocessing pipeline on the WeBrain cloud platform (https://webrain.uestc.edu.cn/). These results suggest that the RESIT is a promising interpolation method for both separate and simultaneous EEG preprocessing that benefits further EEG analysis, including event-related potential (ERP) analysis, EEG network analysis, and strict group-level statistics.

The usual trichromatic equation for a colour match is converted into an algebraic equation consisting of the sum of the contrasts determined by the intensity ratios between the matching stimuli and arbitrary fractions of the proband. The senescence of the preretinal media is shown to affect colour matches monotonically, but discrimination steps are affected differently: it is suggested that the senescence observed in tasks involving chromatic discrimination can be explained in terms of that of the nervous mechanisms subserving other types of contrast discrimination. The possibility of either simplifying or refining some clinical tests is also discussed.

Publisher Summary This chapter explores the incomplete-theory problem in which a learning system has an explicit domain theory that cannot generate an explanation for every example. The general method is to use the existing domain theory to generate a plausible explanation of the example and to extract from it one or more rules that may then be added to the domain theory. This method is an application of abductive reasoning in that it is attempting to account for a known conclusion (the goal concept) by proposing various hypotheses, which, together with the existing domain theory, may account for it. If a complete explanation can be created for an example, the domain theory is adequate and need not be extended. If the example cannot be completely explained, there are usually many partial explanations that can be generated to explain it. The chapter presents the implementation of a prototype system that is able to extend its domain theory this way. The goal of this method is to increase the explanatory power of the domain theory rather than to acquire a specific way of recognizing instances of the goal concept.