Machine Learning in Medical Signal and Image Processing

A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Evolutionary Algorithms and Machine Learning".

Deadline for manuscript submissions: closed (1 September 2023) | Viewed by 23933

Special Issue Editor

Department of Electrical and Computer Engineering, New York Institute of Technology (NYIT), NYC Campus, Room 810, 1855 Broadway, New York, NY 10023-7692, USA
Interests: signal processing; machine learning; biomedical engineering; microwave imaging; non-destructive testing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

We invite you to submit your latest research in the area of developing and applying machine learning algorithms for medical applications to this Special Issue, “Machine Learning in Medical Signal and Image Processing”. We are looking for new and innovative machine learning approaches with medical applications. Potential applications include, but are not limited to, biomedical signal processing, biomedical image processing, biosensors, bioinformatics and computational biology, neural and rehabilitation engineering, cardiovascular engineering, therapeutic and diagnostic systems, robotics, clinical engineering, healthcare information systems and telemedicine, devices and technologies, and emerging topics in biomedical engineering.

Dr. Maryam Ravan
Guest Editor

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. Algorithms is an international peer-reviewed open access monthly 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 1600 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

  • artificial intelligence
  • disease classification and prognosis prediction
  • deep learning (CNN, RNN, GAN, etc.) in brain–computer interface (BCI) and medical images
  • radiological image processing (MRI, fMRI, CT scan, PET, ultrasound, X-ray, etc.)
  • clinical data processing (electrocardiography (ECG), electromyography (EMG), electroencephalography (EEG), etc.)
  • data fusion techniques
  • statistical pattern recognition
  • advanced artifact reduction
  • wearable sensors
  • virtual reality

Related Special Issue

Published Papers (11 papers)

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

Research

17 pages, 6009 KiB  
Article
Bayesian Opportunities for Brain–Computer Interfaces: Enhancement of the Existing Classification Algorithms and Out-of-Domain Detection
by Egor I. Chetkin, Sergei L. Shishkin and Bogdan L. Kozyrskiy
Algorithms 2023, 16(9), 429; https://doi.org/10.3390/a16090429 - 08 Sep 2023
Viewed by 1004
Abstract
Bayesian neural networks (BNNs) are effective tools for a variety of tasks that allow for the estimation of the uncertainty of the model. As BNNs use prior constraints on parameters, they are better regularized and less prone to overfitting, which is a serious [...] Read more.
Bayesian neural networks (BNNs) are effective tools for a variety of tasks that allow for the estimation of the uncertainty of the model. As BNNs use prior constraints on parameters, they are better regularized and less prone to overfitting, which is a serious issue for brain–computer interfaces (BCIs), where typically only small training datasets are available. Here, we tested, on the BCI Competition IV 2a motor imagery dataset, if the performance of the widely used, effective neural network classifiers EEGNet and Shallow ConvNet can be improved by turning them into BNNs. Accuracy indeed was higher, at least for a BNN based on Shallow ConvNet with two of three tested prior distributions. We also assessed if BNN-based uncertainty estimation could be used as a tool for out-of-domain (OOD) data detection. The OOD detection worked well only in certain participants; however, we expect that further development of the method may make it work sufficiently well for practical applications. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

18 pages, 3634 KiB  
Article
CTprintNet: An Accurate and Stable Deep Unfolding Approach for Few-View CT Reconstruction
by Elena Loli Piccolomini, Marco Prato, Margherita Scipione and Andrea Sebastiani
Algorithms 2023, 16(6), 270; https://doi.org/10.3390/a16060270 - 28 May 2023
Cited by 2 | Viewed by 1179
Abstract
In this paper, we propose a new deep learning approach based on unfolded neural networks for the reconstruction of X-ray computed tomography images from few views. We start from a model-based approach in a compressed sensing framework, described by the minimization of a [...] Read more.
In this paper, we propose a new deep learning approach based on unfolded neural networks for the reconstruction of X-ray computed tomography images from few views. We start from a model-based approach in a compressed sensing framework, described by the minimization of a least squares function plus an edge-preserving prior on the solution. In particular, the proposed network automatically estimates the internal parameters of a proximal interior point method for the solution of the optimization problem. The numerical tests performed on both a synthetic and a real dataset show the effectiveness of the framework in terms of accuracy and robustness with respect to noise on the input sinogram when compared to other different data-driven approaches. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

26 pages, 8062 KiB  
Article
Neural Network Entropy (NNetEn): Entropy-Based EEG Signal and Chaotic Time Series Classification, Python Package for NNetEn Calculation
by Andrei Velichko, Maksim Belyaev, Yuriy Izotov, Murugappan Murugappan and Hanif Heidari
Algorithms 2023, 16(5), 255; https://doi.org/10.3390/a16050255 - 16 May 2023
Cited by 4 | Viewed by 2835
Abstract
Entropy measures are effective features for time series classification problems. Traditional entropy measures, such as Shannon entropy, use probability distribution function. However, for the effective separation of time series, new entropy estimation methods are required to characterize the chaotic dynamic of the system. [...] Read more.
Entropy measures are effective features for time series classification problems. Traditional entropy measures, such as Shannon entropy, use probability distribution function. However, for the effective separation of time series, new entropy estimation methods are required to characterize the chaotic dynamic of the system. Our concept of Neural Network Entropy (NNetEn) is based on the classification of special datasets in relation to the entropy of the time series recorded in the reservoir of the neural network. NNetEn estimates the chaotic dynamics of time series in an original way and does not take into account probability distribution functions. We propose two new classification metrics: R2 Efficiency and Pearson Efficiency. The efficiency of NNetEn is verified on separation of two chaotic time series of sine mapping using dispersion analysis. For two close dynamic time series (r = 1.1918 and r = 1.2243), the F-ratio has reached the value of 124 and reflects high efficiency of the introduced method in classification problems. The electroencephalography signal classification for healthy persons and patients with Alzheimer disease illustrates the practical application of the NNetEn features. Our computations demonstrate the synergistic effect of increasing classification accuracy when applying traditional entropy measures and the NNetEn concept conjointly. An implementation of the algorithms in Python is presented. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

13 pages, 3087 KiB  
Article
An Automatic Motion-Based Artifact Reduction Algorithm for fNIRS in Concurrent Functional Magnetic Resonance Imaging Studies (AMARA–fMRI)
by Lia Maria Hocke, Yunjie Tong and Blaise deBonneval Frederick
Algorithms 2023, 16(5), 230; https://doi.org/10.3390/a16050230 - 28 Apr 2023
Viewed by 1505
Abstract
Multimodal functional near-infrared spectroscopy–functional magnetic resonance imaging (fNIRS–fMRI) studies have been highly beneficial for both the fNIRS and fMRI field as, for example, they shed light on the underlying mechanism of each method. However, several noise sources exist in both methods. Motion artifact [...] Read more.
Multimodal functional near-infrared spectroscopy–functional magnetic resonance imaging (fNIRS–fMRI) studies have been highly beneficial for both the fNIRS and fMRI field as, for example, they shed light on the underlying mechanism of each method. However, several noise sources exist in both methods. Motion artifact removal is an important preprocessing step in fNIRS analysis. Several manual motion–artifact removal methods have been developed which require time and are highly dependent on expertise. Only a few automatic methods have been proposed. AMARA (acceleration-based movement artifact reduction algorithm) is one of the most promising automatic methods and was originally tested in an fNIRS sleep study with long acquisition times (~8 h). However, it relies on accelerometry data, which is problematic when performing concurrent fNIRS–fMIRI experiments. Most accelerometers are not MR compatible, and in any case, existing datasets do not have this data. Here, we propose a new way to retrospectively determine acceleration data for motion correction methods, such as AMARA in multimodal fNIRS–fMRI studies. We do so by considering the individual slice stack acquisition times of simultaneous multislice (SMS) acquisition and reconstructing high-resolution motion traces from each slice stack time. We validated our method on 10 participants during a memory task (2- and 3-back) with 6 fNIRS channels over the prefrontal cortex (limited field of view with fMRI). We found that this motion correction significantly improved the detection of activation in deoxyhemoglobin and outperformed up-sampled motion traces. However, we found no improvement in oxyhemoglobin. Furthermore, our data show a high overlap with fMRI activation when considering activation in channels according to both deoxyhemoglobin and oxyhemoglobin. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

21 pages, 2129 KiB  
Article
Electromyography Gesture Model Classifier for Fault-Tolerant-Embedded Devices by Means of Partial Least Square Class Modelling Error Correcting Output Codes (PLS-ECOC)
by Pablo Sarabia, Alvaro Araujo, Luis Antonio Sarabia and María de la Cruz Ortiz
Algorithms 2023, 16(3), 149; https://doi.org/10.3390/a16030149 - 07 Mar 2023
Viewed by 1619
Abstract
Surface electromyography (sEMG) plays a crucial role in several applications, such as for prosthetic controls, human–machine interfaces (HMI), rehabilitation, and disease diagnosis. These applications are usually occurring in real-time, so the classifier tends to run on a wearable device. This edge processing paradigm [...] Read more.
Surface electromyography (sEMG) plays a crucial role in several applications, such as for prosthetic controls, human–machine interfaces (HMI), rehabilitation, and disease diagnosis. These applications are usually occurring in real-time, so the classifier tends to run on a wearable device. This edge processing paradigm imposes strict requirements on the complexity classifier. To date, research on hand gesture recognition (GR) based on sEMG uses discriminant classifiers, such as support vector machines and neural networks. These classifiers can achieve good precision; they cannot detect when an error in classification has happened. This paper proposes a novel hand gesture multiclass model based on partial least square (PLS) class modelling that uses an encoding matrix called error correcting output codes (ECOC). A dataset of eight different gestures was classified using this method where all errors were detected, proving the feasibility of PLS-ECOC as a fault-tolerant classifier. Considering the PLS-ECOC model as a classifier, its accuracy, precision, and F1 are 87.5, 91.87, and 86.34%, respectively, similar to those obtained by other authors. The strength of our work lies in the extra information provided by the PLS-ECOC that allows the application to be fault tolerant while keeping a small-size model and low complexity, making it suitable for embedded real-time classification. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

26 pages, 2819 KiB  
Article
Classification of Skin Lesions Using Weighted Majority Voting Ensemble Deep Learning
by Damilola A. Okuboyejo and Oludayo O. Olugbara
Algorithms 2022, 15(12), 443; https://doi.org/10.3390/a15120443 - 24 Nov 2022
Cited by 5 | Viewed by 1937
Abstract
The conventional dermatology practice of performing noninvasive screening tests to detect skin diseases is a source of escapable diagnostic inaccuracies. Literature suggests that automated diagnosis is essential for improving diagnostic accuracies in medical fields such as dermatology, mammography, and colonography. Classification is an [...] Read more.
The conventional dermatology practice of performing noninvasive screening tests to detect skin diseases is a source of escapable diagnostic inaccuracies. Literature suggests that automated diagnosis is essential for improving diagnostic accuracies in medical fields such as dermatology, mammography, and colonography. Classification is an essential component of an assisted automation process that is rapidly gaining attention in the discipline of artificial intelligence for successful diagnosis, treatment, and recovery of patients. However, classifying skin lesions into multiple classes is challenging for most machine learning algorithms, especially for extremely imbalanced training datasets. This study proposes a novel ensemble deep learning algorithm based on the residual network with the next dimension and the dual path network with confidence preservation to improve the classification performance of skin lesions. The distributed computing paradigm was applied in the proposed algorithm to speed up the inference process by a factor of 0.25 for a faster classification of skin lesions. The algorithm was experimentally compared with 16 deep learning and 12 ensemble deep learning algorithms to establish its discriminating prowess. The experimental comparison was based on dermoscopic images congregated from the publicly available international skin imaging collaboration databases. We propitiously recorded up to 82.52% average sensitivity, 99.00% average specificity, 98.54% average balanced accuracy, and 92.84% multiclass accuracy without prior segmentation of skin lesions to outstrip numerous state-of-the-art deep learning algorithms investigated. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

18 pages, 3776 KiB  
Article
Stimulation Montage Achieves Balanced Focality and Intensity
by Yushan Wang, Jonathan Brand and Wentai Liu
Algorithms 2022, 15(5), 169; https://doi.org/10.3390/a15050169 - 20 May 2022
Cited by 1 | Viewed by 2062
Abstract
Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique to treat brain disorders by using a constant, low current to stimulate targeted cortex regions. Compared to the conventional tDCS that uses two large pad electrodes, multiple electrode tDCS has recently received more [...] Read more.
Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique to treat brain disorders by using a constant, low current to stimulate targeted cortex regions. Compared to the conventional tDCS that uses two large pad electrodes, multiple electrode tDCS has recently received more attention. It is able to achieve better stimulation performance in terms of stimulation intensity and focality. In this paper, we first establish a computational model of tDCS, and then propose a novel optimization algorithm using a regularization matrix λ to explore the balance between stimulation intensity and focality. The simulation study is designed such that the performance of state-of-the-art algorithms and the proposed algorithm can be compared via quantitative evaluation. The results show that the proposed algorithm not only achieves desired intensity, but also smaller target error and better focality. Robustness analysis indicates that the results are stable within the ranges of scalp and cerebrospinal fluid (CSF) conductivities, while the skull conductivity is most sensitive and should be carefully considered in real clinical applications. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

19 pages, 5004 KiB  
Article
Deep Transfer Learning for Parkinson’s Disease Monitoring by Image-Based Representation of Resting-State EEG Using Directional Connectivity
by Emad Arasteh, Ailar Mahdizadeh, Maryam S. Mirian, Soojin Lee and Martin J. McKeown
Algorithms 2022, 15(1), 5; https://doi.org/10.3390/a15010005 - 24 Dec 2021
Cited by 8 | Viewed by 4434
Abstract
Parkinson’s disease (PD) is characterized by abnormal brain oscillations that can change rapidly. Tracking neural alternations with high temporal resolution electrophysiological monitoring methods such as EEG can lead to valuable information about alterations observed in PD. Concomitantly, there have been advances in the [...] Read more.
Parkinson’s disease (PD) is characterized by abnormal brain oscillations that can change rapidly. Tracking neural alternations with high temporal resolution electrophysiological monitoring methods such as EEG can lead to valuable information about alterations observed in PD. Concomitantly, there have been advances in the high-accuracy performance of deep neural networks (DNNs) using few-patient data. In this study, we propose a method to transform resting-state EEG data into a deep latent space to classify PD subjects from healthy cases. We first used a general orthogonalized directed coherence (gOPDC) method to compute directional connectivity (DC) between all pairwise EEG channels in four frequency bands (Theta, Alpha, Beta, and Gamma) and then converted the DC maps into 2D images. We then used the VGG-16 architecture (trained on the ImageNet dataset) as our pre-trained model, enlisted weights of convolutional layers as initial weights, and fine-tuned all layer weights with our data. After training, the classification achieved 99.62% accuracy, 100% precision, 99.17% recall, 0.9958 F1 score, and 0.9958 AUC averaged for 10 random repetitions of training/evaluating on the proposed deep transfer learning (DTL) network. Using the latent features learned by the network and employing LASSO regression, we found that latent features (as opposed to the raw DC values) were significantly correlated with five clinical indices routinely measured: left and right finger tapping, left and right tremor, and body bradykinesia. Our results demonstrate the power of transfer learning and latent space derivation for the development of oscillatory biomarkers in PD. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

12 pages, 2172 KiB  
Article
Variation Trends of Fractal Dimension in Epileptic EEG Signals
by Zhiwei Li, Jun Li, Yousheng Xia, Pingfa Feng and Feng Feng
Algorithms 2021, 14(11), 316; https://doi.org/10.3390/a14110316 - 29 Oct 2021
Cited by 1 | Viewed by 1812
Abstract
Epileptic diseases take EEG as an important basis for clinical judgment, and fractal algorithms were often used to analyze electroencephalography (EEG) signals. However, the variation trends of fractal dimension (D) were opposite in the literature, i.e., both D decreasing and increasing [...] Read more.
Epileptic diseases take EEG as an important basis for clinical judgment, and fractal algorithms were often used to analyze electroencephalography (EEG) signals. However, the variation trends of fractal dimension (D) were opposite in the literature, i.e., both D decreasing and increasing were reported in previous studies during seizure status relative to the normal status, undermining the feasibility of fractal algorithms for EEG analysis to detect epileptic seizures. In this study, two algorithms with high accuracy in the D calculation, Higuchi and roughness scaling extraction (RSE), were used to study D variation of EEG signals with seizures. It was found that the denoising operation had an important influence on D variation trend. Moreover, the D variation obtained by RSE algorithm was larger than that by Higuchi algorithm, because the non-fractal nature of EEG signals during normal status could be detected and quantified by RSE algorithm. The above findings in this study could be promising to make more understandings of the nonlinear nature and scaling behaviors of EEG signals. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

22 pages, 3491 KiB  
Article
Closed-Loop Cognitive-Driven Gain Control of Competing Sounds Using Auditory Attention Decoding
by Ali Aroudi, Eghart Fischer, Maja Serman, Henning Puder and Simon Doclo
Algorithms 2021, 14(10), 287; https://doi.org/10.3390/a14100287 - 30 Sep 2021
Cited by 4 | Viewed by 2278
Abstract
Recent advances have shown that it is possible to identify the target speaker which a listener is attending to using single-trial EEG-based auditory attention decoding (AAD). Most AAD methods have been investigated for an open-loop scenario, where AAD is performed in an offline [...] Read more.
Recent advances have shown that it is possible to identify the target speaker which a listener is attending to using single-trial EEG-based auditory attention decoding (AAD). Most AAD methods have been investigated for an open-loop scenario, where AAD is performed in an offline fashion without presenting online feedback to the listener. In this work, we aim at developing a closed-loop AAD system that allows to enhance a target speaker, suppress an interfering speaker and switch attention between both speakers. To this end, we propose a cognitive-driven adaptive gain controller (AGC) based on real-time AAD. Using the EEG responses of the listener and the speech signals of both speakers, the real-time AAD generates probabilistic attention measures, based on which the attended and the unattended speaker are identified. The AGC then amplifies the identified attended speaker and attenuates the identified unattended speaker, which are presented to the listener via loudspeakers. We investigate the performance of the proposed system in terms of the decoding performance and the signal-to-interference ratio (SIR) improvement. The experimental results show that, although there is a significant delay to detect attention switches, the proposed system is able to improve the SIR between the attended and the unattended speaker. In addition, no significant difference in decoding performance is observed between closed-loop AAD and open-loop AAD. The subjective evaluation results show that the proposed closed-loop cognitive-driven system demands a similar level of cognitive effort to follow the attended speaker, to ignore the unattended speaker and to switch attention between both speakers compared to using open-loop AAD. Closed-loop AAD in an online fashion is feasible and enables the listener to interact with the AGC. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Figure 1

17 pages, 5105 KiB  
Article
Long-Term EEG Component Analysis Method Based on Lasso Regression
by Hongjian Bo, Haifeng Li, Boying Wu, Hongwei Li and Lin Ma
Algorithms 2021, 14(9), 271; https://doi.org/10.3390/a14090271 - 17 Sep 2021
Cited by 1 | Viewed by 2200
Abstract
At present, there are very few analysis methods for long-term electroencephalogram (EEG) components. Temporal information is always ignored by most of the existing techniques in cognitive studies. Therefore, a new analysis method based on time-varying characteristics was proposed. First of all, a regression [...] Read more.
At present, there are very few analysis methods for long-term electroencephalogram (EEG) components. Temporal information is always ignored by most of the existing techniques in cognitive studies. Therefore, a new analysis method based on time-varying characteristics was proposed. First of all, a regression model based on Lasso was proposed to reveal the difference between acoustics and physiology. Then, Permutation Tests and Gaussian fitting were applied to find the highest correlation. A cognitive experiment based on 93 emotional sounds was designed, and the EEG data of 10 volunteers were collected to verify the model. The 48-dimensional acoustic features and 428 EEG components were extracted and analyzed together. Through this method, the relationship between the EEG components and the acoustic features could be measured. Moreover, according to the temporal relations, an optimal offset of acoustic features was found, which could obtain better alignment with EEG features. After the regression analysis, the significant EEG components were found, which were in good agreement with cognitive laws. This provides a new idea for long-term EEG components, which could be applied in other correlative subjects. Full article
(This article belongs to the Special Issue Machine Learning in Medical Signal and Image Processing)
Show Figures

Graphical abstract

Back to TopTop