Recognizing software names in biomedical literature using machine learning.

Software tools now are essential to research and applications in the biomedical domain. However, existing software repositories are mainly built using manual curation, which is time-consuming and unscalable. This study took the initiative to manually annotate software names in 1,120 MEDLINE abstracts and titles and used this corpus to develop and evaluate machine learning-based named entity recognition systems for biomedical software. Specifically, two strategies were proposed for feature engineering: (1) domain knowledge features and (2) unsupervised word representation features of clustered and binarized word embeddings. Our best system achieved an F-measure of 91.79% for recognizing software from titles and an F-measure of 86.35% for recognizing software from both titles and abstracts using inexact matching criteria. We then created a biomedical software catalog with 19,557 entries using the developed system. This study demonstrates the feasibility of using natural language processing methods to automatically build a high-quality software index from biomedical literature.

Biomedical Informatics - How to Choose the Best Tool for Each Task.

The ever-increasing number of bioinformatics software tools that are publicly available, is leading to greater expectations about its regular use in clinical practice. However, from the end-users' perspective, they face many time the challenge of choosing the right tool for each task, from a panoply of solutions that have been developed over the years. In this paper, we propose a benchmarking methodology, based on a set of performance indicators, which can be used to identify the best methods and tools for each particular use case, both in research as in clinical practice.

A lightweight rapid application development framework for biomedical image analysis.

Biomedical imaging analysis typically comprises a variety of complex tasks requiring sophisticated algorithms and visualising high dimensional data. The successful integration and deployment of the enabling software to clinical (research) partners, for rigorous evaluation and testing, is a crucial step to facilitate adoption of research innovations within medical settings. In this paper, we introduce the Simple Medical Imaging Library Interface (SMILI), an object oriented open-source framework with a compact suite of objects geared for rapid biomedical imaging (cross-platform) application development and deployment. SMILI supports the development of both command-line (shell and Python scripting) and graphical applications utilising the same set of processing algorithms. It provides a substantial subset of features when compared to more complex packages, yet it is small enough to ship with clinical applications with limited overhead and has a license suitable for commercial use. After describing where SMILI fits within the existing biomedical imaging software ecosystem, by comparing it to other state-of-the-art offerings, we demonstrate its capabilities in creating a clinical application for manual measurement of cam-type lesions of the femoral head-neck region for the investigation of femoro-acetabular impingement (FAI) from three dimensional (3D) magnetic resonance (MR) images of the hip. This application for the investigation of FAI proved to be convenient for radiological analyses and resulted in high intra (ICC=0.97) and inter-observer (ICC=0.95) reliabilities for measurement of α-angles of the femoral head-neck region. We believe that SMILI is particularly well suited for prototyping biomedical imaging applications requiring user interaction and/or visualisation of 3D mesh, scalar, vector or tensor data.

Current trends for customized biomedical software tools.

In the past, biomedical scientists were solely dependent on expensive commercial software packages for various applications. However, the advent of user-friendly programming languages and open source platforms has revolutionized the development of simple and efficient customized software tools for solving specific biomedical problems. Many of these tools are designed and developed by biomedical scientists independently or with the support of computer experts and often made freely available for the benefit of scientific community. The current trends for customized biomedical software tools are highlighted in this short review.

General guidelines for biomedical software development.

Most bioinformatics tools available today were not written by professional software developers, but by people that wanted to solve their own problems, using computational solutions and spending the minimum time and effort possible, since these were just the means to an end. Consequently, a vast number of software applications are currently available, hindering the task of identifying the utility and quality of each. At the same time, this situation has hindered regular adoption of these tools in clinical practice. Typically, they are not sufficiently developed to be used by most clinical researchers and practitioners. To address these issues, it is necessary to re-think how biomedical applications are built and adopt new strategies that ensure quality, efficiency, robustness, correctness and reusability of software components. We also need to engage end-users during the development process to ensure that applications fit their needs. In this review, we present a set of guidelines to support biomedical software development, with an explanation of how they can be implemented and what kind of open-source tools can be used for each specific topic.

Dimensional error of three-dimensional images generated by different software.

The aim of this study was to evaluate the accuracy of three-dimensional (3D) reconstructions generated by different software, computed tomography (CT) scanners and slice thicknesses. Ten human dry mandibles were scanned by CT and cone beam CT (CBCT). Digital files were processed in different software systems and 3D reconstructions were performed. Linear measures were made and compared. The results showed significant differences in linear distances between the human dry mandibles and their 3D reconstructions. The relative error from CBCT images ranged from 3.10 to 4.82% and from 3.40 to 5.92% in CT images. It is important to consider that the performance of the software is not just related to the algorithm used, but mostly with its handling, that can facilitate or not the measurement by the operator. In conclusion, the discrepancies were not greater than 0.58 mm, so they should not affect the image quality.