Conventional Similarity Metrics Research Articles

Inverse Potts model improves accuracy of phylogenetic profiling.

MotivationPhylogenetic profiling is a powerful computational method for revealing the functions of function-unknown genes. Although conventional similarity metrics in phylogenetic profiling achieved high prediction accuracy, they have two estimation biases: an evolutionary bias and a spurious correlation bias. While previous studies reduced the evolutionary bias by considering a phylogenetic tree, few studies have analyzed the spurious correlation bias.ResultsTo reduce the spurious correlation bias, we developed metrics based on the inverse Potts model (IPM) for phylogenetic profiling. We also developed a metric based on both the IPM and a phylogenetic tree. In an empirical dataset analysis, we demonstrated that these IPM-based metrics improved the prediction performance of phylogenetic profiling. In addition, we found that the integration of several metrics, including the IPM-based metrics, had superior performance to a single metric.Availability and implementationThe source code is freely available at https://github.com/fukunagatsu/Ipm.Supplementary information Supplementary data are available at Bioinformatics online.

Can you fool AI by doing a 180? — A case study on authorship analysis of texts by Arata Osada

This paper is our attempt at answering a twofold question covering the areas of ethics and authorship analysis solutions. Firstly, since the methods used for performing authorship analysis imply that an author can be recognized by the content he or she creates, we were interested in finding out whether it would be possible for an author identification system to correctly attribute works to authors if in the course of years they have undergone a major psychological transition. Secondly – and from the point of view of the evolution of an author’s ethical values – we checked what it would mean if the authorship attribution system encounters difficulties in detecting single authorship. We set out to answer those questions through performing a binary authorship analysis task using a text classifier based on a pre-trained transformer model and a baseline method relying on conventional similarity metrics. For the test set, we chose several works of Arata Osada, a Japanese educator and specialist in the history of education, with half of them being books written before the Second World War and another half in the 1950s, in between which the author underwent a transformation in terms of political opinions. As a result, we were able to confirm that in the case of texts authored by Arata Osada in a time span of more than 10 years, while the classification accuracy drops by a large margin and is substantially lower than for texts by other non-fiction writers, confidence scores of the predictions remain at a similar level as in the case of a shorter time span, indicating that the classifier was in many instances tricked into deciding that texts written by Arata Osada over a time span of multiple years were actually written by two different people, which in turn leads us to believe that such a change can affect authorship analysis, and that historical events have great impact on a person’s ethical outlook as expressed in their writings.

Semantics-based key concepts identification for documents indexing and retrieval on the web

Bridging the semantic gap on the web remains one of the crucial challenges for current horizontal and domain-specific information retrieval systems. This challenge becomes even more pronounced when users express their information needs using short queries that are formulated using a few number of keywords, therefore relying on keywords for indexing web documents results in degrading the quality of the returned results. In this article, we introduce an approach that employs knowledge captured by large-scale knowledge resources to identify key query terms and retrieve semantically-relevant documents. In this context, key terms are mapped to their semantic correspondences and variable term weights are assigned based on the semantic and taxonomic relations for each term. To demonstrate the effectiveness of the proposed approach, we have conducted experimental evaluation using Glasgow's NPL test collections. Findings indicate that the effectiveness has improved against four conventional similarity metrics that are based on the bag-of-words similarity model.

GRACE: A Graph-Based Cluster Ensemble Approach for Single-Cell RNA-Seq Data Clustering

Rapid development of single cell RNA sequencing (scRNA-seq) technology has accelerated the exploration in biomedical researches. One of the focal interests in scRNA-seq data analysis is to classify cells into different types, which significantly assists in studying inter-cellular heterogeneity, such as cell types, cell states, and cell lineages, at the resolution of single cells. Although a number of tailored approaches have been developed for scRNA-seq data, their performance varies with different datasets and their clustering accuracy need to be improved. In this paper, we propose a novel ensemble clustering framework for scRNA-seq data called GRACE (GRAph-based Cluster Ensemble approach). First, we construct a highly reliable graph network for single cells by combining the clustering outcomes from five leading scRNA-seq data clustering methods. Then, we remeasure the relationships between cells by exploring the topology structure of network using random walk distance. Finally, we build a hierarchical cell-tree and obtain the clustering labels by cutting the tree structure into an appropriate number of sub-trees. Experimental results on twelve benchmark datasets show that GRACE has the higher clustering accuracy and is more robust among a variety of datasets than the state-of-the-art individual approaches. In addition, the graph structure of the network which is built upon the ensemble clusters is more reliable than the networks which are constructed according to the conventional similarity metrics.

Novel Ultrasound Texture Based Similarity Metric Using Autoregressive Modelling.

Designing an ultrasound (US) specific similarity metric is essential in integrating advanced techniques like image segmentation and registration to US based interventional procedures. Applying conventional similarity metrics to ultrasound images is hampered by intrinsic noise patterns in an US image. In this work, we propose a texture based similarity metric (TexSimAR) using Autoregressive (AR) modelling. The key idea is to treat an US image as data resulting from a dynamical process which can be parametrically modelled. Using this approach it is possible to compute a parametric spectrum of individual US images and subsequently use it to estimate a similarity value between them. For evaluation, we used thyroid US images and similarity values were calculated between thyroid and non-thyroid regions. A cost function was designed to compare TexSimAR with other conventional similarity metrics. TexSimAR clearly distinguished between thyroid and non-thyroid regions outperfoming the conventional similarity metrics.

A robust non-local total-variation based image registration method under illumination changes in medical applications

Abstract Independence of neighboring pixels and image stationarity are major concepts in conventional similarity metrics, used in image registration tasks. The accuracy of image registration decreases due to the presence of spatially varying intensity distortion in images. In this study, we hypothesized that changes in image illumination have limited total variation (TV). Accordingly, we introduced a similarity metric by reducing the weighted TV in the residual image. The primal dual method was then chosen to solve the proposed registration problem. The efficiency of the proposed method was compared to conventional methods, including the residual complexity (RC) method, the robust Huber similarity measure (RHSM), and the local linear reconstruction method (LLRM) which have been very successful in this field. The efficacy of the proposed method was confirmed by experimental findings on real-world and synthetic images.

WE-AB-BRA-01: 3D-2D Image Registration for Target Localization in Spine Surgery: Comparison of Similarity Metrics Against Robustness to Content Mismatch

Purpose: In image-guided spine surgery, mapping 3D preoperative images to 2D intraoperative images via 3D-2D registration can provide valuable assistance in target localization. However, the presence of surgical instrumentation, hardware implants, and soft-tissue resection/displacement causes mismatches in image content, confounding existing registration methods. Manual/semi-automatic methods to mask such extraneous content is time consuming, user-dependent, error prone, and disruptive to clinical workflow. We developed and evaluated 2 novel similarity metrics within a robust registration framework to overcome such challenges in target localization. Methods: An IRB-approved retrospective study in 19 spine surgery patients included 19 preoperative 3D CT images and 50 intraoperative mobile radiographs in cervical, thoracic, and lumbar spine regions. A neuroradiologist provided truth definition of vertebral positions in CT and radiography. 3D-2D registration was performed using the CMA-ES optimizer with 4 gradient-based image similarity metrics: (1) gradient information (GI); (2) gradient correlation (GC); (3) a novel variant referred to as gradient orientation (GO); and (4) a second variant referred to as truncated gradient correlation (TGC). Registration accuracy was evaluated in terms of the projection distance error (PDE) of the vertebral levels. Results: Conventional similarity metrics were susceptible to gross registration error and failure modes associated with the presence of surgical instrumentation: for GI, the median PDE and interquartile range was 33.0±43.6 mm; similarly for GC, PDE = 23.0±92.6 mm respectively. The robust metrics GO and TGC, on the other hand, demonstrated major improvement in PDE (7.6 ±9.4 mm and 8.1± 18.1 mm, respectively) and elimination of gross failure modes. Conclusion: The proposed GO and TGC similarity measures improve registration accuracy and robustness to gross failure in the presence of strong image content mismatch. Such registration capability could offer valuable assistance in target localization without disruption of clinical workflow. G. Kleinszig and S. Vogt are employees of Siemens Healthcare.

A SIMILARITY METRIC IN IMAGE SEARCHING

Similarity metric is a key component in query-by-example image searching with visual features. After extraction of image visual features, the scheme of computing their similarities can affect the system performance dramatically — the image searching results are normally displayed in decreasing order of similarity (alternatively, increasing order of distance) on the graphical interface for end users. Unfortunately, conventional similarity metrics, in image searching with visual features, usually encounter several difficulties, namely, lighting, background, and viewpoint problems. From the signal processing point of view, this paper introduces a novel similarity metric and therefore reduces the above three problems to some extent. The effectiveness of this newly developed similarity metric is demonstrated by a set of experiments upon a small image ground truth.