Artificial Intelligence in Biomedical Diagnostics and Analysis

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: closed (31 December 2023) | Viewed by 3814

Special Issue Editors

Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia
Interests: machine learning; artificial intelligence; deep learning; neural networks; data science; information and communication management
Special Issues, Collections and Topics in MDPI journals
Department of Digital Forensics Engineering, Technology Faculty, Firat University, 23119 Elazig, Turkey
Interests: image processing; signal processing; data hiding; feature engineering; visual secret sharing
Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey
Interests: feature engineering; machine learning; biomedical image and signal processing; pattern recognition; computer forensics; mobile forensics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues, 

Artificial intelligence (AI) has allowed us to propose algorithms/methods that make many tasks easier, and smart assistants have been proposed using artificial intelligence. These smart assistants, which have started to be used in daily life, are of great importance in shortening processes. As a result, the quality of services has increased, especially with smart systems used in the healthcare field.

We plan to publish articles on next-generation machine learning methods in this Special Issue. In particular, machine learning models are expected to be proposed using signals such as electroencephalograms (EEG), electromyograms (EMG), electrocardiograms (ECG), heart rate (HR) signals, computed tomography (CT), magnetic resonance (MR), X-rays and other medical images or videos. Additionally, explainable artificial intelligence (XAI) explains how machine learning methods perform classification. We hope to publish smart health applications that incorporate XAI-based next-generation methods in this Special Issue.

Artificial intelligence applications in healthcare are an important research area, and these models/architectures/networks have also been used in precision medicine applications. With the Internet of Medical Things (IoMT), precision medical data can be accessed instantly, and information can be obtained from these data by machine learning methods.

Proteins and genomes are crucial to bioinformatics. Using genomic data, disorders and their associations can be identified. Therefore, we are interested in AI-based biomedical informatics methods, since biomedical informatics is crucial to understand the causes of disorders.

We have proposed a new Special Issue to contribute to the study area of healthcare with artificial intelligence and to publish high-quality research articles. This Special Issue is called "Artificial Intelligence in Biomedical Diagnostics and Analysis". We look forward to receiving your submissions on feature engineering, deep learning, and XAI-based models and their uncertainty and implementation.

Dr. Prabal Datta Barua
Dr. Turker Tuncer
Dr. Sengul Dogan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Diagnostics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • medical signal and image processing
  • Internet of Medical Things (IoMT)
  • bioinformatics
  • explainable artificial intelligence
  • machine learning
  • uncertainty

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

19 pages, 5026 KiB  
Article
A Collaborative Platform for Advancing Automatic Interpretation in ECG Signals
by Luis Alberto Gordillo-Roblero, Jorge Alberto Soto-Cajiga, Daniela Díaz-Alonso, Francisco David Pérez-Reynoso and Hugo Jiménez-Hernández
Diagnostics 2024, 14(6), 600; https://doi.org/10.3390/diagnostics14060600 - 12 Mar 2024
Viewed by 504
Abstract
Numerous papers report the efficiency of the automatic interpretation capabilities of commercial algorithms. Unfortunately, these algorithms are proprietary, and academia has no means of directly contributing to these results. In fact, nothing at the same stage of development exists in academia. Despite the [...] Read more.
Numerous papers report the efficiency of the automatic interpretation capabilities of commercial algorithms. Unfortunately, these algorithms are proprietary, and academia has no means of directly contributing to these results. In fact, nothing at the same stage of development exists in academia. Despite the extensive research in ECG signal processing, from signal conditioning to expert systems, a cohesive single application for clinical use is not ready yet. This is due to a serious lack of coordination in the academic efforts, which involve not only algorithms for signal processing, but also the signal acquisition equipment itself. For instance, the different sampling rates and the different noise levels frequently found in the available signal databases can cause severe incompatibility problems when the integration of different algorithms is desired. Therefore, this work aims to solve this incompatibility problem by providing the academic community with a diagnostic-grade electrocardiograph. The intention is to create a new standardized ECG signals database in order to address the automatic interpretation problem and create an electrocardiography system that can fully assist clinical practitioners, as the proprietary systems do. Achieving this objective is expected through an open and coordinated collaboration platform for which a webpage has already been created. Full article
(This article belongs to the Special Issue Artificial Intelligence in Biomedical Diagnostics and Analysis)
Show Figures

Figure 1

11 pages, 3545 KiB  
Article
Deep Convolutional Neural Networks Provide Motion Grading for High-Resolution Peripheral Quantitative Computed Tomography of the Scaphoid
by Stefan Benedikt, Philipp Zelger, Lukas Horling, Kerstin Stock, Johannes Pallua, Michael Schirmer, Gerald Degenhart, Alexander Ruzicka and Rohit Arora
Diagnostics 2024, 14(5), 568; https://doi.org/10.3390/diagnostics14050568 - 06 Mar 2024
Viewed by 543
Abstract
In vivo high-resolution peripheral quantitative computed tomography (HR-pQCT) studies on bone characteristics are limited, partly due to the lack of standardized and objective techniques to describe motion artifacts responsible for lower-quality images. This study investigates the ability of such deep-learning techniques to assess [...] Read more.
In vivo high-resolution peripheral quantitative computed tomography (HR-pQCT) studies on bone characteristics are limited, partly due to the lack of standardized and objective techniques to describe motion artifacts responsible for lower-quality images. This study investigates the ability of such deep-learning techniques to assess image quality in HR-pQCT datasets of human scaphoids. In total, 1451 stacks of 482 scaphoid images from 53 patients, each with up to six follow-ups within one year, and each with one non-displaced fractured and one contralateral intact scaphoid, were independently graded by three observers using a visual grading scale for motion artifacts. A 3D-CNN was used to assess image quality. The accuracy of the 3D-CNN to assess the image quality compared to the mean results of three skilled operators was between 92% and 96%. The 3D-CNN classifier reached an ROC-AUC score of 0.94. The average assessment time for one scaphoid was 2.5 s. This study demonstrates that a deep-learning approach for rating radiological image quality provides objective assessments of motion grading for the scaphoid with a high accuracy and a short assessment time. In the future, such a 3D-CNN approach can be used as a resource-saving and cost-effective tool to classify the image quality of HR-pQCT datasets in a reliable, reproducible and objective way. Full article
(This article belongs to the Special Issue Artificial Intelligence in Biomedical Diagnostics and Analysis)
Show Figures

Figure 1

14 pages, 3769 KiB  
Article
Error Consistency for Machine Learning Evaluation and Validation with Application to Biomedical Diagnostics
by Jacob Levman, Bryan Ewenson, Joe Apaloo, Derek Berger and Pascal N. Tyrrell
Diagnostics 2023, 13(7), 1315; https://doi.org/10.3390/diagnostics13071315 - 01 Apr 2023
Cited by 2 | Viewed by 1052
Abstract
Supervised machine learning classification is the most common example of artificial intelligence (AI) in industry and in academic research. These technologies predict whether a series of measurements belong to one of multiple groups of examples on which the machine was previously trained. Prior [...] Read more.
Supervised machine learning classification is the most common example of artificial intelligence (AI) in industry and in academic research. These technologies predict whether a series of measurements belong to one of multiple groups of examples on which the machine was previously trained. Prior to real-world deployment, all implementations need to be carefully evaluated with hold-out validation, where the algorithm is tested on different samples than it was provided for training, in order to ensure the generalizability and reliability of AI models. However, established methods for performing hold-out validation do not assess the consistency of the mistakes that the AI model makes during hold-out validation. Here, we show that in addition to standard methods, an enhanced technique for performing hold-out validation—that also assesses the consistency of the sample-wise mistakes made by the learning algorithm—can assist in the evaluation and design of reliable and predictable AI models. The technique can be applied to the validation of any supervised learning classification application, and we demonstrate the use of the technique on a variety of example biomedical diagnostic applications, which help illustrate the importance of producing reliable AI models. The validation software created is made publicly available, assisting anyone developing AI models for any supervised classification application in the creation of more reliable and predictable technologies. Full article
(This article belongs to the Special Issue Artificial Intelligence in Biomedical Diagnostics and Analysis)
Show Figures

Figure 1

Review

Jump to: Research

23 pages, 1177 KiB  
Review
Pancreatic Adenocarcinoma: Imaging Modalities and the Role of Artificial Intelligence in Analyzing CT and MRI Images
by Cristian Anghel, Mugur Cristian Grasu, Denisa Andreea Anghel, Gina-Ionela Rusu-Munteanu, Radu Lucian Dumitru and Ioana Gabriela Lupescu
Diagnostics 2024, 14(4), 438; https://doi.org/10.3390/diagnostics14040438 - 16 Feb 2024
Viewed by 698
Abstract
Pancreatic ductal adenocarcinoma (PDAC) stands out as the predominant malignant neoplasm affecting the pancreas, characterized by a poor prognosis, in most cases patients being diagnosed in a nonresectable stage. Image-based artificial intelligence (AI) models implemented in tumor detection, segmentation, and classification could improve [...] Read more.
Pancreatic ductal adenocarcinoma (PDAC) stands out as the predominant malignant neoplasm affecting the pancreas, characterized by a poor prognosis, in most cases patients being diagnosed in a nonresectable stage. Image-based artificial intelligence (AI) models implemented in tumor detection, segmentation, and classification could improve diagnosis with better treatment options and increased survival. This review included papers published in the last five years and describes the current trends in AI algorithms used in PDAC. We analyzed the applications of AI in the detection of PDAC, segmentation of the lesion, and classification algorithms used in differential diagnosis, prognosis, and histopathological and genomic prediction. The results show a lack of multi-institutional collaboration and stresses the need for bigger datasets in order for AI models to be implemented in a clinically relevant manner. Full article
(This article belongs to the Special Issue Artificial Intelligence in Biomedical Diagnostics and Analysis)
Show Figures

Figure 1

Back to TopTop