applsci-logo

Journal Browser

Journal Browser

Advances in Machine Learning and Artificial Intelligence: Biomedical Devices and Applications

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (30 December 2020) | Viewed by 5982

Special Issue Editors


E-Mail Website
Guest Editor
School of Engineering and Applied Science, Aston University, Birmingham B4 7ET, UK
Interests: biophysics; biomedical engineering; polarization; orbital angular momentum; laser speckles
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Engineering and Computer Science, Victoria University of Wellington, Wellington 6140, New Zealand
Interests: design and implementation of forward and inverse algorithms of light transport in turbid tissue-like media; advanced image processing methods for the practical applications in optical sensing/diagnostics; biomedical visualization and 3D computer graphics
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
College of Engineering, Mathematics and Physical Sciences, STEMM Lab, University of Exeter, Exeter, UK
Interests: machine learning; artificial intelligence; smart nanocomposite materials; wearable technology; opto-electronic systems; photonic integrated circuits

Special Issue Information

Dear Colleagues,

Nowadays, artificial intelligence (AI) and machine learning have gained prominence through the development of computational facilities and play an important role in private and scientific life. Microchip manufacturers implement AI algorithms into hardware layers, providing unprecedented abilities in processing data “on the fly”, providing a glimpse of the future of smart sensors. One of the first available products is HiSilicon Kirin 970, that uses AI for processing of images obtained from cameras. Based on computer vision and closely related image processing and machine vision, AI has made significant progress in image and video analyses, but has not been widely and successfully used for spectroscopic data, while integration of sensors, computational units, and AI-specific ISA (instruction set architecture) into a single device has yielded autonomous hyperspectral multidimensional smart sensors which satisfy the concept of Internet of Things (IoT).

Smart sensors should be able to classify incoming data, which is a one of the tasks of machine learning (ML). The fastest implementation of ML methods for data classification is referred to as supervised learning. One aspect of ML pattern recognition is aiming to find regularities and features (patterns) in the experimentally obtained images. Support vector machine (SVM) is the well-developed and fast implementation of supervised learning which is widely used in pattern recognition. SVM is based on regression searching for such a set of hyperplanes in multidimensional space which is the furthest from each of the classes (datapoint groups) displayed in the training dataset. Data in SVM are presented in a form of n-dimensional vectors. When such a hyperplane is found, it is then used to sort incoming data into classes.

Augmented reality (AR) is a hot topic not only in entertainment but also in optics, since it allows for simultaneous visualization of features at an object together with sensing process, e.g., projecting features at an object surface while it is being viewed through a microscope. In prospective smart sensors, AR will reveal the information that is obtained and classified by the sensor itself, meaning that each sensor will have its own integrated circuit sensor and processor unit with algorithms for data.

The application of distributed computing, such as cloud computing and CUDA, speeds up data processing and helps to distribute data analyses between cloud, CPU, and GPU to ensure the best performance. Such an approach moves with the times, since smart sensors within the concept of IoT distribute the data analyses exactly in this manner. OpenCL is proposed as a main framework due to high flexibility and scalability. It can be used for programming, such GPU as CUDA, and also in embedded systems. Data transfer is proposed to be compatible with modern 3GPP communication standards as well as prospective 6G.

The aim of this Special Issue is to highlight the latest exciting developments in promoting the use of AI/ML in biomedical devices and applications by attracting leading researchers to present the results of their latest efforts. Accepted contributions will include the implementation of AI/ML tools for spectroscopic optical data analysis, processing of clinical/pre-clinical/biomedical images/data obtained with modern photonics-based technologies, automatic standalone tissue screening, biopsy pattern recognition, smart clothes and photonics sensors in concept of IoT, AI algorithms, cloud-based computing, how CUDA accelerates data/image processing, and more.

Prof. Dr. Igor Meglinski
Dr. Alexander Doronin
Dr. Ana Baldycheva
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

  • AI algorithms in biomedical imaging and optical diagnostics
  • Explosion of IOT and IOMT data with connected health
  • AI and machine learning in medical data structuring
  • Robotics and Cobotics
  • Machine learning in biophotonics
  • Optical tomography and biomedical visualization with AI
  • Smart optical biopsy
  • Automatic standalone screening of cancer and tissue characterization
  • Hyperspectral multidimensional smart sensors satisfying the concept of Internet of Things (IoT)
  • Smart optical and photonics sensors in concept of IoT
  • Smart image and video analyses
  • Support vector machine in pattern/tissues recognition
  • AI and machine learning in multimodal imaging
  • Advantages in AI algorithms for data and image processing
  • Cloud computing and the acceleration of data/image processing by CUDA

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

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

Research

19 pages, 5345 KiB  
Article
An Adaptive Federated Machine Learning-Based Intelligent System for Skin Disease Detection: A Step toward an Intelligent Dermoscopy Device
by Manzoor Ahmed Hashmani, Syed Muslim Jameel, Syed Sajjad Hussain Rizvi and Saurabh Shukla
Appl. Sci. 2021, 11(5), 2145; https://doi.org/10.3390/app11052145 - 28 Feb 2021
Cited by 28 | Viewed by 4785
Abstract
The prevalence of skin diseases has increased dramatically in recent decades, and they are now considered major chronic diseases globally. People suffer from a broad spectrum of skin diseases, whereas skin tumors are potentially aggressive and life-threatening. However, the severity of skin tumors [...] Read more.
The prevalence of skin diseases has increased dramatically in recent decades, and they are now considered major chronic diseases globally. People suffer from a broad spectrum of skin diseases, whereas skin tumors are potentially aggressive and life-threatening. However, the severity of skin tumors can be managed (by treatment) if diagnosed early. Health practitioners usually apply manual or computer vision-based tools for skin tumor diagnosis, which may cause misinterpretation of the disease and lead to a longer analysis time. However, cutting-edge technologies such as deep learning using the federated machine learning approach have enabled health practitioners (dermatologists) in diagnosing the type and severity level of skin diseases. Therefore, this study proposes an adaptive federated machine learning-based skin disease model (using an adaptive ensemble convolutional neural network as the core classifier) in a step toward an intelligent dermoscopy device for dermatologists. The proposed federated machine learning-based architecture consists of intelligent local edges (dermoscopy) and a global point (server). The proposed architecture can diagnose the type of disease and continuously improve its accuracy. Experiments were carried out in a simulated environment using the International Skin Imaging Collaboration (ISIC) 2019 dataset (dermoscopy images) to test and validate the model’s classification accuracy and adaptability. In the future, this study may lead to the development of a federated machine learning-based (hardware) dermoscopy device to assist dermatologists in skin tumor diagnosis. Full article
Show Figures

Figure 1

Back to TopTop