Search

This paper presents a novel technique called correspondence selection for rigid transformations in order to effectively refine keypoint matches in rigid image registration. The proposed technique mainly lies in the following two components. First, keypoint matches are ranked and selected by the distance ratio between the best match and the second best match. Second, keypoint matches are further selected by ranking the geometric similarity between corresponding keypoint triplets. These two components enhance the discriminative power of potential keypoint matches in a progressive way. The proposed technique is generally applicable to affine rigid image registration. Experiments have been conducted using a set of benchmark datasets in the field of image registration, indicating that the proposed technique is very effective and achieves the state-of-the-art performance in refining keypoint matches for affine rigid image registration.

The production of the first permanent, publicly available sunflower (Helianthus annuus L.) association mapping population (UGA-SAM1) provided material to test the usability of morphological descriptors for discriminating germplasm accessions. The objective of this study was to evaluate the phenotypic diversity in the UGA-SAM1 population and evaluate the usefulness of qualitative traits for the discrimination of genotypes. The SAM1 population consists of 285 accessions characterized for 20 morphological traits. The Shannon–Weaver diversity index (H′) was used to determine phenotypic diversity, whereas HOMALS (homogeneity analysis by alternating least squares) and association statistics were used to determine discriminative power of the descriptors. Phenotypic diversity was moderately high for the traits (0.74). The highest diversity was found in the less developed genotypes followed by non-oil genotypes. Pronounced associations in individual genotype groups and category traits, most notably for the maturity trait in the restorer line (RHA) oil group, resulted in both high association and diversity index values. The association test proved to be a useful addition to HOMALS analysis for determining the trait discriminative power. Adequate selection of traits used in germplasm evaluation can improve the efficiency of breeding programs, whereas the loss of variability could be lowered if diversity focused traits were used including leaf, seed, and certain flower traits, instead of only focusing on yield and quality. This is the peer-reviewed version of the following article: Terzić S., Zorić M., Seiler G. Qualitative traits in sunflower breeding: UGA-SAM1 phenotyping case study. Crop Science 2020, 60 (1), 303 – 319. [https://doi.org/10.1002/csc2.20059]

Hyper-parameters tuning is a crucial task to make a model perform at its best. However, despite the well-established methodologies, some aspects of the tuning remain unexplored. As an example, it may affect not just accuracy but also novelty as well as it may depend on the adopted dataset. Moreover, sometimes it could be sufficient to concentrate on a single parameter only (or a few of them) instead of their overall set. In this paper we report on our investigation on hyper-parameters tuning by performing an extensive 10-Folds Cross-Validation on MovieLens and Amazon Movies for three well-known baselines: User-kNN, Item-kNN, BPR-MF. We adopted a grid search strategy considering approximately 15 values for each parameter, and we then evaluated each combination of parameters in terms of accuracy and novelty. We investigated the discriminative power of nDCG, Precision, Recall, MRR, EFD, EPC, and, finally, we analyzed the role of parameters on model evaluation for Cross-Validation., Comment: 5 pages RecSys 2019

Background Neuroinflammation has gained increasing attention as a potential contributing factor in Alzheimer’s disease (AD) pathology. A clinical cerebrospinal fluid biomarker capable of monitoring this process during the course of the disease has yet to emerge, chiefly owing to contradictory research findings. In this study, we sought to clarify the utility of inflammatory biomarkers in diagnostic procedures of AD in three steps: (1) to screen for proteins that are robustly detectable in cerebrospinal fluid; (2) based on this analysis, to explore any associations between the analytically robust markers and salient pathological features of AD; and (3) to determine the discriminative power of these markers in the clinical diagnosis of AD. Methods From a total of 46 proteins, 15 that were robustly detectable in cerebrospinal fluid were identified. A subsequent analysis of these markers in a cohort of 399 patients (nondemented subjects, patients with mild cognitive impairment [MCI], and patients with AD, supplemented by smaller cohorts of other diseases) was conducted. Fluid biomarker data were related to AD pathology and neuropsychological markers and adjusted for confounders such as age, sex, apolipoprotein E genotype, and biobank storage time. Results Cerebrospinal fluid levels of C-reactive protein and soluble TREM2 differed between nondemented subjects, patients with MCI, or patients with AD and were associated with amyloid and tau pathology. Several markers were associated with tau pathology only or with other neurodegenerative diseases. Correlations between neuropsychological performance and inflammatory markers were weak, but they were most prominent in AD and for the most challenging cognitive tests. All investigated covariates had significant influence, with varying effects across the markers. Still, none of the markers achieved discriminative power of more than 70% to distinguish between patient groups defined by clinical or neuropathological categories. Conclusions Basic analytical considerations proved indispensable for this type of study because only one-third of the tested markers were robustly detectable in cerebrospinal fluid. Detectable inflammatory protein markers were associated in multiple ways with AD pathology. Yet, even significantly associated markers were not powerful enough in terms of effect strength, sensitivity, and specificity, and hence they were not suited for direct use in clinical diagnostic practice. Targets other than those most commonly considered in this field of research might provide results with better clinical applicability. Electronic supplementary material The online version of this article (10.1186/s13195-018-0353-3) contains supplementary material, which is available to authorized users.

Background/purpose: Visual characteristics such as color and shape of skin lesions play an important role in the diagnostic process. In this contribution, we quantify the discriminative power of such attributes using an information theoretical approach.Methods: We estimate the probability of occurrence of each attribute as a function of the skin diseases. We use the distribution of this probability across the studied diseases and its entropy to define the discriminative power of the attribute. The discriminative power has a maximum value for attributes that occur (or do not occur) for only one disease and a minimum value for those which are equally likely to be observed among all diseases.Results: Verrucous surface, red and brown colors, and the presence of more than 10 lesions are among the most informative attributes. A ranking of attributes is also carried out and used together with a naive Bayesian classifier, yielding results that confirm the soundness of the proposed method.Conclusion: The proposed measure is proven to be a reliable way of assessing the discriminative power of dermatological attributes, and it also helps generate a condensed dermatological lexicon. Therefore, it can be of added value to the manual or computer-aided diagnostic process.

AIMS/HYPOTHESIS: We determined whether single nucleotide polymorphisms (SNPs) previously associated with diabetogenic traits improve the discriminative power of a type 2 diabetes genetic risk score. METHODS: Participants (n = 2,751) were genotyped for 73 SNPs previously associated with type 2 diabetes, fasting glucose/insulin concentrations, obesity or lipid levels, from which five genetic risk scores (one for each of the four traits and one combining all SNPs) were computed. Type 2 diabetes patients and non-diabetic controls (n = 1,327/1,424) were identified using medical records in addition to an independent oral glucose tolerance test. RESULTS: Model 1, including only SNPs associated with type 2 diabetes, had a discriminative power of 0.591 (p < 1.00 x 10(-20) vs null model) as estimated by the area under the receiver operator characteristic curve (ROC AUC). Model 2, including only fasting glucose/insulin SNPs, had a significantly higher discriminative power than the null model (ROC AUC 0.543; p = 9.38 x 10(-6) vs null model), but lower discriminative power than model 1 (p = 5.92 x 10(-5)). Model 3, with only lipid-associated SNPs, had significantly higher discriminative power than the null model (ROC AUC 0.565; p = 1.44 x 10(-9)) and was not statistically different from model 1 (p = 0.083). The ROC AUC of model 4, which included only obesity SNPs, was 0.557 (p = 2.30 x 10(-7) vs null model) and smaller than model 1 (p = 0.025). Finally, the model including all SNPs yielded a significant improvement in discriminative power compared with the null model (p < 1.0 x 10(-20)) and model 1 (p = 1.32 x 10(-5)); its ROC AUC was 0.626. CONCLUSIONS/INTERPRETATION: Adding SNPs previously associated with fasting glucose, insulin, lipids or obesity to a genetic risk score for type 2 diabetes significantly increases the power to discriminate between people with and without clinically manifest type 2 diabetes compared with a model including only conventional type 2 diabetes loci.

To be eligible for the protection in form of the Plant Breeders’ Rights (PBR), a potential new variety must meet the criteria of Distinctness, Uniformity, and Stability (DUS). In most of the European countries, testing for DUS is, or will become, the consistent part of variety trials. It is based on a set of traits suggested by UPOV, which are traditionally, and predominantly, morphological characters that should have some agronomic relevance. Being affected by environmental factors, morphological markers require repeated testing over years. Multiplied by the growing numbers of candidate varieties, it would inevitably cause either dramatic increase of trial costs, or equal decrease of trial precision. Necessity of the cost reduction, due to general limitation of resources, raises the need for the alternative system of DUS testing. Proven to have high discriminative power, unaffected by environmental factors, molecular markers become the obvious candidates. However, they are still not widely accepted for use in DUS testing, due to non-uniformity within varieties, often observed at the molecular level. In this study total of 41 maize inbred lines were scored for 32 DUS characters prescribed by UPOV. The same set of inbred lines was genotyped at 28 SSR loci. The aim of the study is to compare the results obtained by using DUS data and SSR markers to discriminate maize inbred lines. Further comparisons will be done with available pedigree information, in order to assess power of both data types to detect the degree of relatedness between lines. We will also try to establish parallels between morphological and molecular markers, and point out morphological traits that could be associated with the variability at the molecular level. Suitability of the SSR markers for DUS testing will be reviewed from the aspects of their discriminative power, cost reduction, and others.