RÉSUMÉ
PURPOSE: The integration of deep learning in image segmentation technology markedly improves the automation capabilities of medical diagnostic systems, reducing the dependence on the clinical expertise of medical professionals. However, the accuracy of image segmentation is still impacted by various interference factors encountered during image acquisition. METHODS: To address this challenge, this paper proposes a loss function designed to mine specific pixel information which dynamically changes during training process. Based on the triplet concept, this dynamic change is leveraged to drive the predicted boundaries of images closer to the real boundaries. RESULTS: Extensive experiments on the PH2 and ISIC2017 dermoscopy datasets validate that our proposed loss function overcomes the limitations of traditional triplet loss methods in image segmentation applications. This loss function not only enhances Jaccard indices of neural networks by 2.42 % and 2.21 % for PH2 and ISIC2017, respectively, but also neural networks utilizing this loss function generally surpass those that do not in terms of segmentation performance. CONCLUSION: This work proposed a loss function that mined the information of specific pixels deeply without incurring additional training costs, significantly improving the automation of neural networks in image segmentation tasks. This loss function adapts to dermoscopic images of varying qualities and demonstrates higher effectiveness and robustness compared to other boundary loss functions, making it suitable for image segmentation tasks across various neural networks.
RÉSUMÉ
Since December 2019, digital health applications (DiGA) have been included in standard care in Germany and are therefore reimbursed by the statutory health insurance funds to support patients in the treatment of diseases or impairments. There are 48 registered DiGA listed in the directory of the Federal Institute of Drugs and Medical Devices (BfArM), mainly in the areas of mental health; hormones and metabolism; and muscles, bones, and joints. In this article, the "Digital Health" specialist group of the German Informatics Society describes the current developments around DiGA as well as the current sentiment on topics such as user-centricity, patient and practitioner acceptance, and innovation potential. In summary, over the past three years, DiGA have experienced a positive development, characterized by a gradually increasing availability of various DiGA and coverage areas as well as prescription numbers. Nevertheless, significant regulatory adjustments are still required in some areas to establish DiGA as a well-established instrument in long-term routine healthcare. Key challenges include user-centeredness and the sustainable use of the applications.
Sujet(s)
Académies et instituts , , Humains , AllemagneRÉSUMÉ
BACKGROUND: Gene expression profiling is a widely adopted method in areas like drug development or functional gene analysis. Microarray data of gene expression experiments is still commonly used and widely available for retrospective analyses. However, due to to changes of the underlying technologies data sets from different technologies are often difficult to compare and thus a multitude of already available data becomes difficult to use. We present a web application that abstracts away mathematical and programmatical details in order to enable a convenient and customizable analysis of microarray data for large-scale reproducibility studies. In addition, the web application provides a feature that allows easy access to large microarray repositories. RESULTS: Our web application consists of three basic steps which are necessary for a differential gene expression analysis as well as Gene Ontology (GO) enrichment analysis and the comparison of multiple analysis results. Genealyzer can handle Affymetrix data as well as one-channel and two-channel Agilent data. All steps are visualized with meaningful plots. The application offers flexible analysis while being intuitively operable. CONCLUSIONS: Our web application provides a unified platform for analysing microarray data, while allowing users to compare the results of different technologies and organisms. Beyond reproducibility, this also offers many possibilities for gaining further insights from existing study data, especially since data from different technologies or organisms can also be compared. The web application can be accessed via this URL: https://genealyzer.item.fraunhofer.de/ . Login credentials can be found at the end.
Sujet(s)
Analyse de profil d'expression de gènes , Logiciel , Séquençage par oligonucléotides en batterie/méthodes , Reproductibilité des résultats , Études rétrospectives , Analyse de profil d'expression de gènes/méthodes , Expression des gènes , InternetRÉSUMÉ
BACKGROUND: Medical databases normally contain large amounts of data in a variety of forms. Although they grant significant insights into diagnosis and treatment, implementing data exploration into current medical databases is challenging since these are often based on a relational schema and cannot be used to easily extract information for cohort analysis and visualization. As a consequence, valuable information regarding cohort distribution or patient similarity may be missed. With the rapid advancement of biomedical technologies, new forms of data from methods such as Next Generation Sequencing (NGS) or chromosome microarray (array CGH) are constantly being generated; hence it can be expected that the amount and complexity of medical data will rise and bring relational database systems to a limit. DESCRIPTION: We present Graph4Med, a web application that relies on a graph database obtained by transforming a relational database. Graph4Med provides a straightforward visualization and analysis of a selected patient cohort. Our use case is a database of pediatric Acute Lymphoblastic Leukemia (ALL). Along routine patients' health records it also contains results of latest technologies such as NGS data. We developed a suitable graph data schema to convert the relational data into a graph data structure and store it in Neo4j. We used NeoDash to build a dashboard for querying and displaying patients' cohort analysis. This way our tool (1) quickly displays the overview of patients' cohort information such as distributions of gender, age, mutations (fusions), diagnosis; (2) provides mutation (fusion) based similarity search and display in a maneuverable graph; (3) generates an interactive graph of any selected patient and facilitates the identification of interesting patterns among patients. CONCLUSION: We demonstrate the feasibility and advantages of a graph database for storing and querying medical databases. Our dashboard allows a fast and interactive analysis and visualization of complex medical data. It is especially useful for patients similarity search based on mutations (fusions), of which vast amounts of data have been generated by NGS in recent years. It can discover relationships and patterns in patients cohorts that are normally hard to grasp. Expanding Graph4Med to more medical databases will bring novel insights into diagnostic and research.
Sujet(s)
Logiciel , Enfant , Humains , Bases de données factuellesRÉSUMÉ
Using results from genome-wide association studies for understanding complex traits is a current challenge. Here we review how genotype data can be used with different machine learning (ML) methods to predict phenotype occurrence and severity from genotype data. We discuss common feature encoding schemes and how studies handle the often small number of samples compared to the huge number of variants. We compare which ML methods are being applied, including recent results using deep neural networks. Further, we review the application of methods for feature explanation and interpretation.
Sujet(s)
Étude d'association pangénomique , Génotype , Humains , Apprentissage machineRÉSUMÉ
Along with digitization, automatic data-driven decision support systems become increasingly popular. Mortality prediction is a vital part of that decision process. With more data available, sophisticated machine learning models like (Artificial) Neural Networks (NNs) can be applied and promise favorable performance. We evaluate the reproducibility of a published mortality prediction approach using NNs along with the possibility to generalize it to a bigger and more generic dataset. We describe an extensive preprocessing pipeline, as well as the evaluation of different sampling techniques and NN architectures. Through training on a loss function that optimizes both, precision and recall, in combination with a good set of hyperparameters and a set of new features, we use a NN to predict in-hospital mortality with accuracy, sensitivity, and area under the receiver operating characteristic score of greater than 0.8.