Research

17 pages, 40887 KiB

Open AccessArticle

Deep Learning within a DICOM WSI Viewer for Histopathology

by Noelia Vallez, Jose Luis Espinosa-Aranda, Anibal Pedraza, Oscar Deniz and Gloria Bueno

Appl. Sci. 2023, 13(17), 9527; https://0-doi-org.brum.beds.ac.uk/10.3390/app13179527 - 23 Aug 2023

Cited by 2 | Viewed by 1251

Microscopy scanners and artificial intelligence (AI) techniques have facilitated remarkable advancements in biomedicine. Incorporating these advancements into clinical practice is, however, hampered by the variety of digital file formats used, which poses a significant challenge for data processing. Open-source and commercial software solutions [...] Read more.

Microscopy scanners and artificial intelligence (AI) techniques have facilitated remarkable advancements in biomedicine. Incorporating these advancements into clinical practice is, however, hampered by the variety of digital file formats used, which poses a significant challenge for data processing. Open-source and commercial software solutions have attempted to address proprietary formats, but they fall short of providing comprehensive access to vital clinical information beyond image pixel data. The proliferation of competing proprietary formats makes the lack of interoperability even worse. DICOM stands out as a standard that transcends internal image formats via metadata-driven image exchange in this context. DICOM defines imaging workflow information objects for images, patients’ studies, reports, etc. DICOM promises standards-based pathology imaging, but its clinical use is limited. No FDA-approved digital pathology system natively generates DICOM, and only one high-performance whole slide images (WSI) device has been approved for diagnostic use in Asia and Europe. In a recent series of Digital Pathology Connectathons, the interoperability of our solution was demonstrated by integrating DICOM digital pathology imaging, i.e., WSI, into PACs and enabling their visualisation. However, no system that incorporates state-of-the-art AI methods and directly applies them to DICOM images has been presented. In this paper, we present the first web viewer system that employs WSI DICOM images and AI models. This approach aims to bridge the gap by integrating AI methods with DICOM images in a seamless manner, marking a significant step towards more effective CAD WSI processing tasks. Within this innovative framework, convolutional neural networks, including well-known architectures such as AlexNet and VGG, have been successfully integrated and evaluated. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

15 pages, 1662 KiB

Open AccessArticle

A Linear Discriminant Analysis and Classification Model for Breast Cancer Diagnosis

by Marion Olubunmi Adebiyi, Micheal Olaolu Arowolo, Moses Damilola Mshelia and Oludayo O. Olugbara

Appl. Sci. 2022, 12(22), 11455; https://0-doi-org.brum.beds.ac.uk/10.3390/app122211455 - 11 Nov 2022

Cited by 16 | Viewed by 2567

Abstract

Although most cases are identified at a late stage, breast cancer is the most public malignancy amongst women globally. However, mammography for the analysis of breast cancer is not routinely available at all general hospitals. Prolonging the period between detection and treatment for [...] Read more.

Although most cases are identified at a late stage, breast cancer is the most public malignancy amongst women globally. However, mammography for the analysis of breast cancer is not routinely available at all general hospitals. Prolonging the period between detection and treatment for breast cancer may raise the likelihood of proliferating the disease. To speed up the process of diagnosing breast cancer and lower the mortality rate, a computerized method based on machine learning was created. The purpose of this investigation was to enhance the investigative accuracy of machine-learning algorithms for breast cancer diagnosis. The use of machine-learning methods will allow for the classification and prediction of cancer as either benign or malignant. This investigation applies the machine learning algorithms of random forest (RF) and the support vector machine (SVM) with the feature extraction method of linear discriminant analysis (LDA) to the Wisconsin Breast Cancer Dataset. The SVM with LDA and RF with LDA yielded accuracy results of 96.4% and 95.6% respectively. This research has useful applications in the medical field, while it enhances the efficiency and precision of a diagnostic system. Evidence from this study shows that better prediction is crucial and can benefit from machine learning methods. The results of this study have validated the use of feature extraction for breast cancer prediction when compared to the existing literature. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

12 pages, 442 KiB

Open AccessArticle

Knowledge-Based Framework for Selection of Genomic Data Compression Algorithms

by Abdullah Alourani, Muhammad Tahir, Muhammad Sardaraz and Muhammad Saud Khan

Appl. Sci. 2022, 12(22), 11360; https://0-doi-org.brum.beds.ac.uk/10.3390/app122211360 - 09 Nov 2022

Cited by 2 | Viewed by 1036

Abstract

The development of new sequencing technologies has led to a significant increase in biological data. The exponential increase in data has exceeded increases in computing power. The storage and analysis of the huge amount of data poses challenges for researchers. Data compression is [...] Read more.

The development of new sequencing technologies has led to a significant increase in biological data. The exponential increase in data has exceeded increases in computing power. The storage and analysis of the huge amount of data poses challenges for researchers. Data compression is used to reduce the size of data, which ultimately reduces the cost of data transmission over the Internet. The field comprises experts from two domains, i.e., computer scientists and biological scientists. Computer scientists develop programs to solve biological problems, whereas biologists use these programs. Computer programs need parameters that are usually provided as input by the users. Users need to know different parameters while operating these programs. Users need to configure parameters manually, which leads to being more time-consuming and increased chances of errors. The program selected by the user may not be an efficient solution according to the desired parameter. This paper focuses on automatic program selection for biological data compression. Forward chaining is employed to develop an expert system to solve this problem. The system takes different parameters related to compression programs from the user and selects compression programs according to the desired parameters. The proposed solution is evaluated by testing it with benchmark datasets using programs available in the literature. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

17 pages, 2171 KiB

Open AccessArticle

Analyzing the Data Completeness of Patients’ Records Using a Random Variable Approach to Predict the Incompleteness of Electronic Health Records

by Varadraj P. Gurupur, Paniz Abedin, Sahar Hooshmand and Muhammed Shelleh

Appl. Sci. 2022, 12(21), 10746; https://0-doi-org.brum.beds.ac.uk/10.3390/app122110746 - 24 Oct 2022

Cited by 2 | Viewed by 2193

Abstract

The purpose of this article is to illustrate an investigation of methods that can be effectively used to predict the data incompleteness of a dataset. Here, the investigators have conceptualized data incompleteness as a random variable, with the overall goal behind experimentation providing [...] Read more.

The purpose of this article is to illustrate an investigation of methods that can be effectively used to predict the data incompleteness of a dataset. Here, the investigators have conceptualized data incompleteness as a random variable, with the overall goal behind experimentation providing a 360-degree view of this concept conceptualizing incompleteness of a dataset both as a continuous, discrete random variable depending on the aspect of the required analysis. During the course of the experiments, the investigators have identified Kolomogorov–Smirnov goodness of fit, Mielke distribution, and beta distributions as key methods to analyze the incompleteness of a dataset for the datasets used for experimentation. A comparison of these methods with a mixture density network was also performed. Overall, the investigators have provided key insights into the use of methods and algorithms that can be used to predict data incompleteness and have provided a pathway for further explorations and prediction of data incompleteness. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

15 pages, 4227 KiB

Open AccessArticle

Computer-Aided Surgical Simulation through Digital Dynamic 3D Skeletal Segments for Correcting Torsional Deformities of the Lower Limbs in Children with Cerebral Palsy

by Leonardo Frizziero, Giovanni Trisolino, Gian Maria Santi, Giulia Alessandri, Simone Agazzani, Alfredo Liverani, Grazia Chiara Menozzi, Giovanni Luigi Di Gennaro, Giuseppina Maria Grazia Farella, Alida Abbruzzese, Paolo Spinnato, Lisa Berti and Maria Grazia Benedetti

Appl. Sci. 2022, 12(15), 7918; https://0-doi-org.brum.beds.ac.uk/10.3390/app12157918 - 07 Aug 2022

Cited by 5 | Viewed by 1996

Abstract

Torsional deformities of the lower limb are common in children with cerebral palsy (CP)-determining gait problems. The mechanisms underlying transverse plane gait deviations arise from a combination of dynamic and static factors. The dynamic elements may be due to spasticity, contractures and muscle [...] Read more.

Torsional deformities of the lower limb are common in children with cerebral palsy (CP)-determining gait problems. The mechanisms underlying transverse plane gait deviations arise from a combination of dynamic and static factors. The dynamic elements may be due to spasticity, contractures and muscle imbalances, while the static ones may result from excessive femoral anteversion, which decreases the efficiency of the hip abductors by reducing the muscular lever arms. A therapeutic approach has been identified in multi-level functional surgery for the lower limb. Treating the malalignments of the lower limb with femoral or tibial derotation provides optimal results, especially when supported by adequate biomechanical planning. This planning requires an integrated static-dynamic approach of morphological and functional evaluation, based on radiological measurements, physical examination and gait analysis. Instrumented gait analysis has been confirmed as essential in the evaluation and surgical decision making process for children affected by CP with transverse plane deformities. Computational simulations based on musculoskeletal models that integrate patient-specific CT morphological data into gait analysis can be used for the implementation of a surgical simulation system in pre-operative planning to test the possible effects of the different surgical treatment options on the torsional defects of the lower limbs. Recently, a computer-aided simulation process has been implemented in the preoperative planning of complex osteotomies for limb deformities in children. Three-dimensional (3D) digital models were generated from Computed Tomography (CT) scans, using free open-source software. The aim of this study is to integrate the patient-specific CT musculoskeletal model with morphological data and gait analysis data, with the personalized calculation of kinematic and kinetic parameters, which allow us to generate an “avatar” of the patient for a more in-depth evaluation of the gait abnormalities. The computational simulation platform proposed provides a realistic movable musculoskeletal model in a virtual environment, with the possibility of planning and monitoring the effects of virtual three-dimensional surgical corrections. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

15 pages, 4360 KiB

Open AccessArticle

Transcriptional Profiling of Hippocampus Identifies Network Alterations in Alzheimer’s Disease

by Veronica Quarato, Salvatore D’Antona, Petronilla Battista, Roberta Zupo, Rodolfo Sardone, Isabella Castiglioni, Danilo Porro, Marco Frasca and Claudia Cava

Appl. Sci. 2022, 12(10), 5035; https://0-doi-org.brum.beds.ac.uk/10.3390/app12105035 - 16 May 2022

Cited by 1 | Viewed by 2216

Abstract

Alzheimer’s disease (AD) is a neurodegenerative disease characterized by rapid brain cell degeneration affecting different areas of the brain. Hippocampus is one of the earliest involved brain regions in the disease. Modern technologies based on high-throughput data have identified transcriptional profiling of several [...] Read more.

Alzheimer’s disease (AD) is a neurodegenerative disease characterized by rapid brain cell degeneration affecting different areas of the brain. Hippocampus is one of the earliest involved brain regions in the disease. Modern technologies based on high-throughput data have identified transcriptional profiling of several neurological diseases, including AD, for a better comprehension of genetic mechanisms of the disease. In this study, we investigated differentially expressed genes (DEGs) from six Gene Expression Omnibus (GEO) datasets of hippocampus of AD patients. The identified DEGs were submitted to Weighted correlation network analysis (WGCNA) and ClueGo to explore genes with a higher degree centrality and to comprehend their biological role. Subsequently, MCODE was used to identify subnetworks of interconnected DEGs. Our study found 40 down-regulated genes and 36 up-regulated genes as consensus DEGs. Analysis of the co-expression network revealed ACOT7, ATP8A2, CDC42, GAD1, GOT1, INA, NCALD, and WWTR1 to be genes with a higher degree centrality. ClueGO revealed the pathways that were mainly enriched, such as clathrin coat assembly, synaptic vesicle endocytosis, and DNA damage response signal transduction by p53 class mediator. In addition, we found a subnetwork of 12 interconnected genes (AMPH, CA10, CALY, NEFL, SNAP25, SNAP91, SNCB, STMN2, SV2B, SYN2, SYT1, and SYT13). Only CA10 and CALY are targets of known drugs while the others could be potential novel drug targets. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

Review

Jump to: Research, Other

14 pages, 848 KiB

Open AccessReview

Agile Software Development in Healthcare: A Synthetic Scoping Review

by Peter Kokol

Appl. Sci. 2022, 12(19), 9462; https://0-doi-org.brum.beds.ac.uk/10.3390/app12199462 - 21 Sep 2022

Cited by 4 | Viewed by 4293

Abstract

Even though software can be found everywhere, software development has encountered many problems, resulting in the emergence of new alternative development paradigms. Among them, agile approaches are the most popular. While much research has been published about agile software development (ASD) in general, [...] Read more.

Even though software can be found everywhere, software development has encountered many problems, resulting in the emergence of new alternative development paradigms. Among them, agile approaches are the most popular. While much research has been published about agile software development (ASD) in general, there is a lack of documented knowledge about its use in healthcare. Consequently, it is not clear how ASD is used in healthcare, how it performs, and what the reasons are for not using it. To fill this gap, we performed a quantitative and qualitative knowledge synthesis of the research literature harvested from Scopus and Web of Science databases, employing the triangulation of bibliometrics and thematic analysis to answer the research question What is state of the art in using ASD in the healthcare sector? Results show that the research literature production trend is positive. The most productive countries are leading software development countries: the United States, China, the United Kingdom, Canada, and Germany. The research is mainly published in health informatics source titles. It is focused on improving the software process, quality of healthcare software, reduction of development resources, and general improvement of healthcare delivery. More research has to be done on scaling agile approaches to large-scale healthcare software development projects. Despite barriers, ASD can improve software development in healthcare settings and strengthen cooperation between healthcare and software development professionals. This could result in more successful digital health transformation and consequently more equitable access to expert-level healthcare, even on a global level. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

Other

Jump to: Research, Review

15 pages, 1737 KiB

Open AccessSystematic Review

Dual-Hormone Insulin-and-Pramlintide Artificial Pancreas for Type 1 Diabetes: A Systematic Review

by Alezandra Torres-Castaño, Amado Rivero-Santana, Lilisbeth Perestelo-Pérez, Andrea Duarte-Díaz, Analia Abt-Sacks, Vanesa Ramos-García, Yolanda Álvarez-Pérez, Ana M. Wäagner, Mercedes Rigla and Pedro Serrano-Aguilar

Appl. Sci. 2022, 12(20), 10262; https://0-doi-org.brum.beds.ac.uk/10.3390/app122010262 - 12 Oct 2022

Viewed by 1626

Abstract

The artificial pancreas (AP) is equipped with a glucose monitoring sensor, an insulin pump and an integrated mathematical algorithm that determines insulin infusion based on the glucose levels detected by the sensor. Research has shown that AP can help patients with type-1 Diabetes [...] Read more.

The artificial pancreas (AP) is equipped with a glucose monitoring sensor, an insulin pump and an integrated mathematical algorithm that determines insulin infusion based on the glucose levels detected by the sensor. Research has shown that AP can help patients with type-1 Diabetes Mellitus (T1DM) to improve the control of their glucose levels, but the occurrence of postprandial hyperglycemia is still considerable. The addition of pramlintide (a synthetic derivative analog of amylin) in a dual-hormone AP could improve postprandial glycemic control. This systematic review aims to evaluate and synthesize the evidence on the safety, efficacy and cost-effectiveness of the dual insulin- and pramlintide-releasing AP. The electronic databases MEDLINE, Embase, Web of Science and ClinicalTrials.gov were consulted up to 6 June 2021. We identified four small crossover studies (n = 59) and two ongoing crossover trials, all of them carried out by the same research group. The four studies observed more gastrointestinal adverse effects with the dual system. One study found that the dual system improved outcomes compared to insulin alone, with precise carbohydrate counting (CC) in both groups. Another study showed that a fully closed-loop system (without CC) was equivalent to an insulin-alone AP (with CC) on time in the target range but performed worse in hyperglycemia during the daytime. These preliminary results suggest that the control of postprandial hyperglycemia remains a challenge. Full article

(This article belongs to the Special Issue Recent Advances in Bioinformatics and Health Informatics)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Recent Advances in Bioinformatics and Health Informatics

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI