Search

BackgroundPolyDeep is a computer-aided detection and classification (CADe/x) system trained to detect and classify polyps. During colonoscopy, CADe/x systems help endoscopists to predict the histology of colonic lesions.ObjectiveTo compare the diagnostic performance of PolyDeep and expert endoscopists for the optical diagnosis of colorectal polyps on still images.MethodsPolyDeep Image Classification (PIC) is an in vitro diagnostic test study. The PIC database contains NBI images of 491 colorectal polyps with histological diagnosis. We evaluated the diagnostic performance of PolyDeep and four expert endoscopists for neoplasia (adenoma, sessile serrated lesion, traditional serrated adenoma) and adenoma characterization and compared them with the McNemar test. Receiver operating characteristic curves were constructed to assess the overall discriminatory ability, comparing the area under the curve of endoscopists and PolyDeep with the chi- square homogeneity areas test.ResultsThe diagnostic performance of the endoscopists and PolyDeep in the characterization of neoplasia is similar in terms of sensitivity (PolyDeep: 89.05%; E1: 91.23%, p=0.5; E2: 96.11%, p

Deep learning object-detection models are being successfully applied to develop computer-aided diagnosis systems for aiding polyp detection during colonoscopies. Here, we evidence the need to include negative samples for both (i) reducing false positives during the polyp-finding phase, by including images with artifacts that may confuse the detection models (e.g., medical instruments, water jets, feces, blood, excessive proximity of the camera to the colon wall, blurred images, etc.) that are usually not included in model development datasets, and (ii) correctly estimating a more realistic performance of the models. By retraining our previously developed YOLOv3-based detection model with a dataset that includes 15% of additional not-polyp images with a variety of artifacts, we were able to generally improve its F1 performance in our internal test datasets (from an average F1 of 0.869 to 0.893), which now include such type of images, as well as in four public datasets that include not-polyp images (from an average F1 of 0.695 to 0.722).

Compi is an application framework to develop end-user, pipeline-based applications with a primary emphasis on: (i) user interface generation, by automatically generating a command-line interface based on the pipeline specific parameter definitions; (ii) application packaging, with compi-dk, which is a version-control-friendly tool to package the pipeline application and its dependencies into a Docker image; and (iii) application distribution provided through a public repository of Compi pipelines, named Compi Hub, which allows users to discover, browse and reuse them easily. By addressing these three aspects, Compi goes beyond traditional workflow engines, having been specially designed for researchers who want to take advantage of common workflow engine features (such as automatic job scheduling or logging, among others) while keeping the simplicity and readability of shell scripts without the need to learn a new programming language. Here we discuss the design of various pipelines developed with Compi to describe its main functionalities, as well as to highlight the similarities and differences with similar tools that are available. An open-source distribution under the Apache 2.0 License is available from GitHub (available at https://github.com/sing-group/compi). Documentation and installers are available from https://www.sing-group.org/compi. A specific repository for Compi pipelines is available from Compi Hub (available at https://www.sing-group.org/compihub.

A better understanding of the response against Tuberculosis (TB) infection is required to accurately identify the individuals with an active or a latent TB infection (LTBI) and also those LTBI patients at higher risk of developing active TB. In this work, we have used the information obtained from studying the gene expression profile of active TB patients and their infected –LTBI- or uninfected –NoTBI- contacts, recruited in Spain and Mozambique, to build a class-prediction model that identifies individuals with a TB infection profile. Following this approach, we have identified several genes and metabolic pathways that provide important information of the immune mechanisms triggered against TB infection. As a novelty of our work, a combination of this class-prediction model and the direct measurement of different immunological parameters, was used to identify a subset of LTBI contacts (called TB-like) whose transcriptional and immunological profiles are suggestive of infection with a higher probability of developing active TB. Validation of this novel approach to identifying LTBI individuals with the highest risk of active TB disease merits further longitudinal studies on larger cohorts in TB endemic areas.

Colorectal cancer is one of the most frequent malignancies. Colonoscopy is the de facto standard for precancerous lesion detection in the colon, i.e., polyps, during screening studies or after facultative recommendation. In recent years, artificial intelligence, and especially deep learning techniques such as convolutional neural networks, have been applied to polyp detection and localization in order to develop real-time CADe systems. However, the performance of machine learning models is very sensitive to changes in the nature of the testing instances, especially when trying to reproduce results for totally different datasets to those used for model development, i.e., inter-dataset testing. Here, we report the results of testing of our previously published polyp detection model using ten public colonoscopy image datasets and analyze them in the context of the results of other 20 state-of-the-art publications using the same datasets. The F1-score of our recently published model was 0.88 when evaluated on a private test partition, i.e., intra-dataset testing, but it decayed, on average, by 13.65% when tested on ten public datasets. In the published research, the average intra-dataset F1-score is 0.91, and we observed that it also decays in the inter-dataset setting to an average F1-score of 0.83.

Abstract Background Large-sequencing cancer genome projects have shown that tumors have thousands of molecular alterations and their frequency is highly heterogeneous. In such scenarios, physicians and oncologists routinely face lists of cancer genomic alterations where only a minority of them are relevant biomarkers to drive clinical decision-making. For this reason, the medical community agrees on the urgent need of methodologies to establish the relevance of tumor alterations, assisting in genomic profile interpretation, and, more importantly, to prioritize those that could be clinically actionable for cancer therapy. Results We present PanDrugs, a new computational methodology to guide the selection of personalized treatments in cancer patients using the variant lists provided by genome-wide sequencing analyses. PanDrugs offers the largest database of drug-target associations available from well-known targeted therapies to preclinical drugs. Scoring data-driven gene cancer relevance and drug feasibility PanDrugs interprets genomic alterations and provides a prioritized evidence-based list of anticancer therapies. Our tool represents the first drug prescription strategy applying a rational based on pathway context, multi-gene markers impact and information provided by functional experiments. Our approach has been systematically applied to TCGA patients and successfully validated in a cancer case study with a xenograft mouse model demonstrating its utility. Conclusions PanDrugs is a feasible method to identify potentially druggable molecular alterations and prioritize drugs to facilitate the interpretation of genomic landscape and clinical decision-making in cancer patients. Our approach expands the search of druggable genomic alterations from the concept of cancer driver genes to the druggable pathway context extending anticancer therapeutic options beyond already known cancer genes. The methodology is public and easily integratable with custom pipelines through its programmatic API or its docker image. The PanDrugs webtool is freely accessible at http://www.pandrugs.org.

Last decade, biomedical and bioinformatics researchers have been demanding advanced and user-friendly applications for real use in practice. In this context, the Artificial Intelligence Workbench, an open-source Java desktop application framework for scientific software development, emerged with the goal of provid-ing support to both fundamental and applied research in the domain of transla-tional biomedicine and bioinformatics. AIBench automatically provides function-alities that are common to scientific applications, such as user parameter defini-tion, logging facilities, multi-threading execution, experiment repeatability, work-flow management, and fast user interface development, among others. Moreover, AIBench promotes a reusable component based architecture, which also allows assembling new applications by the reuse of libraries from existing projects or third-party software. Ten years have passed since the first release of AIBench, so it is time to look back and check if it has fulfilled the purposes for which it was conceived to and how it evolved over time.

Modern bioinformatics and computational biology are fields of study driven by the availability of effective software required for conducting appropriate research tasks. Apart from providing reliable and fast implementations of different data analysis algorithms, these software applications should also be clear and easy to use through proper user interfaces, providing appropriate data management and visualization capabilities. In this regard, the user experience obtained by interacting with these applications via their Graphical User Interfaces (GUI) is a key factor for their final success and real utility for researchers. Despite the existence of different packages and applications focused on advanced data visualization, there is a lack of specific libraries providing pertinent GUI components able to help scientific bioinformatics software developers. To that end, this paper introduces GC4S, a bioinformatics-oriented collection of high-level, extensible, and reusable Java GUI elements specifically designed to speed up bioinformatics software development. Within GC4S, developers of new applications can focus on the specific GUI requirements of their projects, relying on GC4S for generalities and abstractions. GC4S is free software distributed under the terms of GNU Lesser General Public License and both source code and documentation are publicly available at http://www.sing-group.org/gc4s.