Narrow Results

This paper presents a software tool called AVID (A VIsualization and Design) which is particularly useful for data mining with an artificial neural network known as the self-organising feature map (SOM). AVID supports network training in both the i) selection of network inputs and ii) visualisation of the trained SOM. Both these features are novel aids to SOM network training and are particularly important when consideration is given to using the SOM for data mining. Once trained the SOM produces a 2-dimensional topological ordering of the input training data and it is particularly useful for representing the relationships within multi-dimensional data. The main classes within the data can be identified from the output map. AVID is an important software tool which enables data mining with the SOM by the selection of network inputs and the subsequent visualisation of the classes within these input vectors.

The convergence of biomedical instruments and computing platforms has resulted in medical imaging equipment being subjected to the threats of malicious software (Malware) which have traditionally plagued the computing industry.

Vulnerabilities increase several-fold with implementations of Clinical Information Systems like the Picture Archival & Communication Systems (PACS), where computer-based biomedical equipment work hand in glove with computer servers.

With the increasing complexity of modern Malware, proactive monitoring and reviews of known vulnerabilities are no longer sufficient. An institute faced with an IT security attack on their medical networks will still experience extended downtime, performance degradation and increased service costs, even if equipped with an adequate security system and recovery plans.

Biomedical equipment vendors usually need more time than computing vendors to validate the security updates required for vulnerabilities before they can recommend changes for installation to their systems. This includes all system changes, patches, updates, and enhancements. However, the interval between the launch of a new Malware attack and the availability of a solution from the vendor can result in the medical network being compromised and rendered totally crippled.

In view of such new challenges, it is crucial to redesign your medical network and operating procedures to ensure continuous operation with minimum performance degradation even under a Malware attack until the biomedical equipment vendor can provide the software updates to resolve security vulnerabilities.

Such strategic implementation is not only necessary to ensure integrity and confidentiality of patient's data but also to protect the healthcare institute's reputation and business continuity.

This paper analyses the impact of the use of electronic resources and Health InterNetwork Access to Research Initiative (HINARI) services for medical research libraries in Bangladesh, emphasising the International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b). Purposeful use of e-resources, time and cost-saving benefits, research impact, and challenges of using HINARI are discussed. The basic study was conducted at icddr,b in January–February 2014, using a mixed methodology, combining qualitative and quantitative approaches, including a background literature review, usage data shared from the HINARI secretariat at the World Health Organization (WHO), questionnaires, personal observations, and interviews with staff members of icddr,b. Findings revealed that icddr,b is the heaviest user of HINARI (a major source of public health and medical e-resources) in Bangladesh, with demonstrable increases of health research journal articles after introducing HINARI in 2003.

Cancer subtyping refers to categorizing a particular cancer type into distinct subtypes or subgroups based on a range of molecular characteristics, clinical manifestations, histological features, and other relevant factors. The identification of cancer subtypes can significantly enhance precision in clinical practice and facilitate personalized diagnosis and treatment strategies. Recent advancements in the field have witnessed the emergence of numerous network fusion methods aimed at identifying cancer subtypes. The majority of these fusion algorithms, however, solely rely on the fusion network of a single core matrix for the identification of cancer subtypes and fail to comprehensively capture similarity. To tackle this issue, in this study, we propose a novel cancer subtype recognition method, referred to as PCA-constrained multi-core matrix fusion network (PCA-MM-FN). The PCA-MM-FN algorithm initially employs three distinct methods to obtain three core matrices. Subsequently, the obtained core matrices are projected into a shared subspace using principal component analysis, followed by a weighted network fusion. Lastly, spectral clustering is conducted on the fused network. The results obtained from conducting experiments on the mRNA expression, DNA methylation, and miRNA expression of five TCGA datasets and three multi-omics benchmark datasets demonstrate that the proposed PCA-MM-FN approach exhibits superior accuracy in identifying cancer subtypes compared to the existing methods.

Medical X-rays are one of the primary choices for diagnosis because of their potential to disclose previously undetected pathologic changes, non-invasive qualities, radiation dosage, and cost concerns. There are several advantages to creating computer-aided detection (CAD) technologies for X-Ray analysis. With the advancement of technology, researchers have lately used the deep learning approach to obtain high accuracy outcomes in the CAD system. With CAD, computer output may be utilized as a backup option for radiologists, assisting doctors in making the best selections. Chest X-Rays (CXRs) are commonly used to diagnose heart and lung problems. Automatically recognizing these problems with high accuracy might considerably improve real-world diagnosis processes. However, the lack of standard publicly available datasets and benchmark research makes comparing and establishing the best detection algorithms challenging. In order to overcome these difficulties, we have used the VinDr-CXR dataset, which is one of the latest public datasets including 18,000 expert-annotated images labeled into 22 local position-specific abnormalities and 6 globally suspected diseases. To improve the identification of chest abnormalities, we proposed a data preparation procedure and a novel model based on YOLOv5 and ResNet50. YOLOv5 is the most recent YOLO series, and it is more adaptable than previous one-stage detection algorithms. In our paper, the role of YOLOv5 is to locate the abnormality location. On the other side, we employ ResNet for classification, avoiding gradient explosion concerns in deep learning. Then we filter the YOLOv5 and ResNet results. The YOLOv5 detection result is updated if ResNet determines that the image is not anomalous.

Biomedical intelligence (BMI) has been studied in solos, lacking a systematic methodology. Bioinformatics has been conceptualizing biological process in terms of genomics and applying computer science (derived from disciplines such as applied modeling, data mining, machine learning and statistics) to extract knowledge from biological data. Medical Informatics, on the other hand, has been developing health care applications based on clinical observations and applying computer science to extract knowledge and information to facilitate problem solving and decision marking In this chapter, we describe how semantic computing can enhance biological and medical intelligence. Specifically, we show how structured natural language (SNL) can express many problems in BMI with a finite number of sentence patterns, and show how biological analysis tools, OLAP, data mining and statistical analysis may be linked to solve problems related to biomedical data.