applsci-logo

Journal Browser

Journal Browser

Machine Learning in Biomedical Images, Signals and Data Processing

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Biomedical Engineering".

Deadline for manuscript submissions: closed (31 March 2023) | Viewed by 4074

Special Issue Editors


E-Mail Website
Guest Editor
Department of Electronics Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan
Interests: biomedical engineering; artificial intelligence; medical informatics; radiation therapy application
Special Issues, Collections and Topics in MDPI journals
Department of Radiation Oncology, RWJ Medical School, Monmouth Medical Center, Long Branch, NJ 07740, USA
Interests: artificial intelligent on medical physics and medical informatics; radiation oncology; radiation biophysical modeling; evolutionary optimization
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Electronic Engineering, National Kaohsiung University of Science and Technology, Kaohsiung 80778, Taiwan
Interests: machine learning; deep learning; artificial intelligence health; medical informatics; information security
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Biomedical image, signal, and data processing is making great strides in machine learning applications and offers many opportunities to improve the quality of related biomedical research. However, there are still many foreseeable challenges such as system performance, data volume, data labeling and quality analysis, etc. The goal of this Special Issue is to invite interested parties to publish original manuscripts and present state-of-the-art research regarding machine learning techniques in this field. Using artificial intelligence to analyze medical images and signals, the prediction of clinical diagnosis or prognosis will become feasible through applications of machine learning methodologies. We welcome submissions of applications of various types of biomedical images, signals, and data combined with the implementation of the latest machine and deep learning methods, and propose innovative methods to solve existing imaging/data challenges in the biomedical and health fields.

Topics of interest include, but are not limited to:

  • Machine learning or deep learning algorithms for biomedical image, signal and data processing applications;
  • Disease classification and prognosis prediction based on biomedical image,signal and data processing;
  • Segmentation and anomaly detection based on biomedical images;
  • Biomedical image denoising and quality improvement;
  • Biomedical image, signal and data processing for therapy monitoring;
  • Big data or multimodal data processing for predicting clinical outcomes;
  • Biomedical image quality assessment;
  • Disease severity assessment based on biomedical image, signal and data processing.

Prof. Dr. Tsair-Fwu Lee
Dr. Jack Yang
Dr. Chih-Hsueh Lin
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. Applied Sciences 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 2400 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

  • machine learning
  • deep learning
  • biomedical images
  • biomedical signals
  • data processing
  • big data
  • disease classification
  • prognosis prediction
  • image segmentation and anomaly detection
  • image denoising and quality improvement
  • therapy monitoring
  • image quality assessment
  • disease severity assessment

Published Papers (2 papers)

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

Research

16 pages, 3349 KiB  
Article
A Two-Step Framework to Recognize Emotion Using the Combinations of Adjacent Frequency Bands of EEG
by Zhipeng Zhang and Liyi Zhang
Appl. Sci. 2023, 13(3), 1954; https://doi.org/10.3390/app13031954 - 2 Feb 2023
Cited by 1 | Viewed by 1347
Abstract
Electroencephalography (EEG)-based emotion recognition technologies can effectively help robots to perceive human behavior, which have attracted extensive attention in human–machine interaction (HMI). Due to the complexity of EEG data, current researchers tend to extract different types of hand-crafted features and connect all frequency [...] Read more.
Electroencephalography (EEG)-based emotion recognition technologies can effectively help robots to perceive human behavior, which have attracted extensive attention in human–machine interaction (HMI). Due to the complexity of EEG data, current researchers tend to extract different types of hand-crafted features and connect all frequency bands for further study. However, this may result in the loss of some discriminative information of frequency band combinations and make the classification models unable to obtain the best results. In order to recognize emotions accurately, this paper designs a novel EEG-based emotion recognition framework using complementary information of frequency bands. First, after the features of the preprocessed EEG data are extracted, the combinations of all the adjacent frequency bands in different scales are obtained through permutation and reorganization. Subsequently, the improved classification method, homogeneous-collaboration-representation-based classification, is used to obtain the classification results of each combination. Finally, the circular multi-grained ensemble learning method is put forward to re-exact the characteristics of each result and merge the machine learning methods and simple majority voting for the decision fusion. In the experiment, the classification accuracies of our framework in arousal and valence on the DEAP database are 95.09% and 94.38% respectively, and that in the four classification problems on the SEED IV database is 96.37%. Full article
(This article belongs to the Special Issue Machine Learning in Biomedical Images, Signals and Data Processing)
Show Figures

Figure 1

15 pages, 1886 KiB  
Article
Factors Affecting Implementation of Radiological Protection Aspects of Imaging in Radiotherapy
by Colin John Martin, Sebastien Gros, Tomas Kron, Tim J. Wood, Jenia Vassileva, William Small, Jr. and Ung Ngie Min
Appl. Sci. 2023, 13(3), 1533; https://doi.org/10.3390/app13031533 - 24 Jan 2023
Cited by 2 | Viewed by 1865
Abstract
Dramatic improvements in radiotherapy equipment have allowed radiation fields to be conformed to tumours for more accurate treatment. Successful delivery often requires imaging at every treatment fraction, a method known as image guided radiation therapy (IGRT). But increased X-ray imaging exposes patients to [...] Read more.
Dramatic improvements in radiotherapy equipment have allowed radiation fields to be conformed to tumours for more accurate treatment. Successful delivery often requires imaging at every treatment fraction, a method known as image guided radiation therapy (IGRT). But increased X-ray imaging exposes patients to doses that carry risks of inducing second cancers in normal tissues. Therefore, reductions in high-dose treatment margins achieved with IGRT must be balanced against detriments from greater imaging doses. ICRP Task Group 116 has been set up to prepare guidance on radiological protection aspects of IGRT. Factors affecting the optimization of radiological protection are the modalities used, the frequency of imaging, the image acquisition parameters influencing image quality and radiation dose, and the volume of normal tissue included in the images. The Task Group has undertaken two projects: (1) a snapshot survey of radiotherapy imaging practices across six continents, which has shown that use of kV cone beam CT (CBCT) increases with Human Development Index for the country; and (2) a project looking at ways for measuring CBCT doses that could be applied more widely. The results highlight the need for raising awareness of imaging doses, and development of the dose quantities displayed on imaging equipment used in radiotherapy. Full article
(This article belongs to the Special Issue Machine Learning in Biomedical Images, Signals and Data Processing)
Show Figures

Graphical abstract

Back to TopTop