Attention based automated radiology report generation using CNN and LSTM

The automated generation of radiology reports provides X-rays and has tremendous potential to enhance the clinical diagnosis of diseases in patients. A new research direction is gaining increasing attention that involves the use of hybrid approaches based on natural language processing and computer vision techniques to create auto medical report generation systems. The auto report generator, producing radiology reports, will significantly reduce the burden on doctors and assist them in writing manual reports. Because the sensitivity of chest X-ray (CXR) findings provided by existing techniques not adequately accurate, producing comprehensive explanations for medical photographs remains a difficult task. A novel approach to address this issue was proposed, based on the continuous integration of convolutional neural networks and long short-term memory for detecting diseases, followed by the attention mechanism for sequence generation based on these diseases. Experimental results obtained by using the Indiana University CXR and MIMIC-CXR datasets showed that the proposed model attained the current state-of-the-art efficiency as opposed to other solutions of the baseline. BLEU-1, BLEU-2, BLEU-3, and BLEU-4 were used as the evaluation metrics.

An ANNs-Based Method for Automated Labelling of Schematic Metro Maps

Schematic maps are popular for representing transport networks. In the last two decades, some researchers have been working toward automated generation of network layouts (i.e., the network geometry of schematic maps), while automated labelling of schematic maps is not well considered. The descriptive-statistics-based labelling method, which models the labelling space by defining various station-based line relations in advance, has been specially developed for schematic maps. However, if a certain station-based line relation is not predefined in the database, this method may not be able to infer suitable labelling positions under this relation. It is noted that artificial neural networks (ANNs) have the ability to infer unseen relations. In this study, we aim to develop an ANNs-based method for the labelling of schematic metro maps. Samples are first extracted from representative schematic metro maps, and then they are employed to train and test ANNs models. Five types of attributes (e.g., station-based line relations) are used as inputs, and two types of attributes (i.e., directions and positions of labels) are used as outputs. Experiments show that this ANNs-based method can generate effective and satisfactory labelling results in the testing cases. Such a method has potential to be extended for the labelling of other transport networks.

ADG: automated generation and evaluation of many-body diagrams

The goal of the present paper is twofold. First, a novel expansion many-body method applicable to superfluid open-shell nuclei, the so-called Bogoliubov in-medium similarity renormalization group (BIMSRG) theory, is formulated. This generalization of standard single-reference IMSRG theory for closed-shell systems parallels the recent extensions of coupled cluster, self-consistent Green’s function or many-body perturbation theory. Within the realm of IMSRG theories, BIMSRG provides an interesting alternative to the already existing multi-reference IMSRG (MR-IMSRG) method applicable to open-shell nuclei. The algebraic equations for low-order approximations, i.e., BIMSRG(1) and BIMSRG(2), can be derived manually without much difficulty. However, such a methodology becomes already impractical and error prone for the derivation of the BIMSRG(3) equations, which are eventually needed to reach high accuracy. Based on a diagrammatic formulation of BIMSRG theory, the second objective of the present paper is thus to describe the third version (v3.0) of the code that automatically (1) generates all valid BIMSRG(n) diagrams and (2) evaluates their algebraic expressions in a matter of seconds. This is achieved in such a way that equations can easily be retrieved for both the flow equation and the Magnus expansion formulations of BIMSRG. Expanding on this work, the first future objective is to numerically implement BIMSRG(2) (eventually BIMSRG(3)) equations and perform ab initio calculations of mid-mass open-shell nuclei.

IMPROVEMENT OF SVD ALGORITHM TO INCREASE THE EFFICIENCY OF RECOMMENDATION SYSTEMS

Many existing websites use recommendation systems for their users. They generate various offers for them, for example, similar products or recommend the people registered on this site with similar interests. Such referral mechanisms process vast amounts of information to identify potential user preferences. Recommendation systems are programs that try to determine what users want to find, what might interest them, and recommend it to them. These mechanisms have improved the interaction between the user and the site. Instead of static information, they provide dynamic information that changes: recommendations are generated separately for each user, based on his previous activity on this web resource. Information from other visitors may also be taken into account. The methods of collecting information provided by the Internet have greatly simplified the use of human thought through collaborative filtering. But, on the other hand, the large amount of information complicates the implementation of this possibility. For example, the behavior of some people is quite clearly amenable to modeling, while others behave completely unpredictably. And it is the latter that affect the shift of the results of the recommendation system and reduce its effectiveness. An analysis of Internet resources has shown that most of the recommendation systems do not provide recommendations to users, and the part that does, for example, offers products to the user, selects recommendations manually. Therefore, the task of developing methods for automated generation of recommendations for a limited set of input data is quite relevant. The problems of data sparseness, new user problem, scalability of the widely used SVD algorithm for the development of such recommendation systems are proposed to be eliminated by improving this algorithm by the method of the nearest k-neighbors. This method will allow you to easily segment and cluster system data, which will save system resources.

Automated Generation of Core Outcome Measures for Clinical Trials

Common outcome sets are vital for ensuring usability of clinical trial results and enabling inter-study comparisons. The task of identifying clinical outcomes for a particular field is cumbersome and time-consuming. The aim of this work was to develop an automated pipeline for identifying common outcomes by analyzing outcomes from relevant trials reported at ClinicalTrials.gov and to assess the pipeline accuracy. We validated the output of our pipeline by comparing the outcomes it identified for acute coronary syndromes and coronary artery disease with the set of outcomes recommended for these conditions by a panel of experts in a widely cited report. We found that our pipeline identified the same or similar outcomes for 100% of the outcomes recommended in the experts’ report. The coverage of the pipeline’s results dropped only slightly (to 21 out of 23 outcome domains, 91%) when we restricted the pipeline to trials posted before the publication of the report, indicating a great potential for this pipeline to be used in aiding and informing the future development of core outcome measures in clinical trials.

3D fluorescence microscopy data synthesis for segmentation and benchmarking

Automated image processing approaches are indispensable for many biomedical experiments and help to cope with the increasing amount of microscopy image data in a fast and reproducible way. Especially state-of-the-art deep learning-based approaches most often require large amounts of annotated training data to produce accurate and generalist outputs, but they are often compromised by the general lack of those annotated data sets. In this work, we propose how conditional generative adversarial networks can be utilized to generate realistic image data for 3D fluorescence microscopy from annotation masks of 3D cellular structures. In combination with mask simulation approaches, we demonstrate the generation of fully-annotated 3D microscopy data sets that we make publicly available for training or benchmarking. An additional positional conditioning of the cellular structures enables the reconstruction of position-dependent intensity characteristics and allows to generate image data of different quality levels. A patch-wise working principle and a subsequent full-size reassemble strategy is used to generate image data of arbitrary size and different organisms. We present this as a proof-of-concept for the automated generation of fully-annotated training data sets requiring only a minimum of manual interaction to alleviate the need of manual annotations.

ChemSpaX: Exploration of Chemical Space by Automated Functionalization of Molecular Scaffold

Exploration of the local chemical space of molecular scaffolds by post-functionalization (PF) is a promising route to discover novel molecules with desired structure and function. PF with rationally chosen substituents based on known electronic and steric properties is a commonly used experimental and computational strategy in screening, design and optimization of catalytic scaffolds. Automated generation of reasonably accurate geometric representations of post-functionalized molecular scaffolds is highly desirable for data-driven applications. However, automated PF of transition metal (TM) complexes remains challenging. In this work a Python-based workflow, ChemSpaX, that is aimed at automating the PF of a given molecular scaffold with special emphasis on TMcomplexes, is introduced. In three representative applications of ChemSpaX by comparing with DFT and DFT-B calculations, we show that the generated structures have a reasonable quality for use in computational screening applications. Furthermore, we show thatChemSpaXgenerated geometries can be used in machine learning applications to accurately predict DFT computed HOMO-LUMO gaps for transition metal complexes.ChemSpaXis open-source and aims to bolster and democratize the efforts of the scientific community towards data-driven chemical discovery.