Applications In Medical Diagnosis Research Articles

Using SERS-based microfluidic paper-based device (μPAD) for calibration-free quantitative measurement of AMI cardiac biomarkers

Recently, surface enhanced Raman scattering (SERS) has attracted much attention in medical diagnosis applications owing to better detection sensitivity and lower limit of detection (LOD) than colorimetric detection. In this paper, a novel calibration-free SERS−based μPAD with multi-reaction zones for simultaneous quantitative detection of multiple cardiac biomarkers — GPBB, CK−MB and cTnT for early diagnosis and prognosis of acute myocardial infarction (AMI) are presented. Three distinct Raman probes were synthesised, subsequently conjugated with respective detecting antibodies and used as SERS nanotags for cardiac biomarker detection. Using a conventional calibration curve, quantitative simultaneous measurement of multiple cardiac biomarkers on SERS-based μPAD was performed based on the characteristic Raman spectral features of each reporter used in different nanotags. However, a calibration free point-of-care testing device is required for fast screening to rule-in and rule-out AMI patients. Partial least squares predictive models were developed and incorporated into the immunosensing system, to accurately quantify the three unknown cardiac biomarkers levels in serum based on the previously obtained Raman spectral data. This method allows absolute quantitative measurement when conventional calibration curve fails to provide accurate estimation of cardiac biomarkers, especially at low and high concentration ranges. Under an optimised condition, the LOD of our SERS-based μPAD was identified at 8, 10, and 1 pg mL−1, for GPBB, CK−MB and cTnT, respectively, which is well below the clinical cutoff values. Therefore, this proof-of-concept technique shows significant potential for highly sensitive quantitative detection of multiplex cardiac biomarkers in human serum to expedite medical decisions for enhanced patient care.

Label-free, rapid, and sensitive detection of carboxylesterase using surfactant-doped liquid crystal sensor

Carboxylesterases (CES) has been regarded as a most effective biomarker candidate of the hepatoma cells and fruitfully used in the early detection. For this reason, establishing a reliable and simple system to detect CES has become attractive in the practical applications of medical diagnosis and treatment. In this study, a novel strategy for monitoring CES based on the aqueous/liquid crystals (LCs) interface was reported. A cleavable surfactant, N-octadecyloxycarbonylmethyl-N, N, N-trimethylammonium bromide (OTB) was synthesized and utilized to control the orientation of 4-cyano-4′-pentylbiphenyl (5CB) molecules on aqueous/LCs interface. The formation of OTB self-assembly monolayer promotes the alignment of the LCs, on average, normal to the surface (homotropic), whereas a corresponding black image was observed by polarized optical microscopy (POM). Subsequently, the doping of CES induces the hydrolysis of the OTB, resulting in the disruption of OTB monolayer and thereby an obvious dark-to-bright transition in the optical response. This optical transition provides a quick and easy way of detecting CES. OTB-decorated LC surfaces have been developed as a sensor, with a detection limit of 18 U/L for CES detection. As-made LCs-based sensor exhibits superior detection sensitivity and specificity towards the detection of CES, as well as the excellent long-term stability. The preliminary results shows success in sensing CES from the urine samples, which also suggests the promising detection performance of LCs sensor in practical situations. In summary, the as-prepared CES sensor, offers several advantages along with its cost-effective and easy fabrication procedure, demonstrates its potential for medically assisted therapy in human samples.

A Framework for Interpretable Full-Body Kinematic Description Using Geometric and Functional Analysis.

Rapid advances in cost-effective and non-invasive depth sensors, and the development of reliable and real-time 3D skeletal data estimation algorithms, have opened up a new application area in computer vision - statistical analysis of human kinematic data for fast, automated assessment of body movements. These assessments can play important roles in sports, medical diagnosis, physical therapy, elderly monitoring and related applications. This paper develops a comprehensive geometric framework for quantification and statistical evaluation of kinematic features. The key idea is to avoid analysis of individual joints, as is the current paradigm, and represent movements as temporal evolutions, or trajectories, on shape space of full body skeletons. This allows metrics with appropriate invariance properties to be imposed on these trajectories and leads to definitions of higher-level features, such as spatial symmetry (sS), temporal symmetry (tS), action's velocity (Vl) and body's balance (Bl), during performance of an action. These features exploit skeletal symmetries in space and time, and capture motion cadence to naturally quantify motions of individual subjects. The study of these features as functional data allows us to formulate certain hypothesis tests in feature space. This, in turn, leads to validation of existing assumptions and discoveries of new relationships between kinematics and demographic factors, such as age, gender, and athletic training. We use the clinically validated K3Da kinect dataset to illustrate these ideas, and hope these tools will lead to discovery of new relationships between full-body kinematic features and demographic, health, and wellness factors that are clinically relevant.

Logarithmic similarity measure of dynamic neutrosophic cubic sets and its application in medical diagnosis

In the medical diagnosis process, the symptoms of patients are always changing with time and relative to dynamical information at different time intervals. However, existing information expression methods usually neglect the temporal correlation of information expression, and hardly depict certain and uncertain information on complex medical diagnosis problems. For the first time, the study presents dynamic neutrosophic cubic set (DNCS) to express the patient's disease symptoms in a time sequence (different time intervals). Then, the logarithmic similarity measure (LSM) of DNCSs is put forward and their properties are verified. After that, a medical diagnosis method is constructed on the basis of the proposed logarithmic similarity measure in DNCS setting, where the disease symptom information collected from different time intervals is given by the form of DNCSs. Lastly, a medical diagnosis example is used to demonstrate its applicability, and then the diagnosis results indicate that the presented method is effective and feasible.

An Efficient Technique to Remove Gaussian Noise and Improve the Quality of Magnetic Resonance Image

Medical Resonance Imaging (MRI) is very useful in different medical applications for diagnosis the diseases in human body. But the main problem arising in MRI images is presence of various noises. These noises are affecting the originality of the MRI images and producing erroneous results. Here Brain MRI images are used for analysis of noise. Brain images are fractal in nature and especially those images are affected by various noises. In this paper we discussed about the Gaussian noise in brain MRI image. The effect of this noise is reduced by wavelet based thresholding techniques. They are namely Visu shrink, SURE shrink and Bayes shrink. These three methods are applied to the brain MRI images and obtained results are compared by PSNR(Peak signal to Noise ratio), MSE(Mean Square Error),Absolute error, Fractal dimension, IEF(Image Enhancement Factor),Normalized cross correlation and structural content.

Risk-Aware Machine Learning Classifier for Skin Lesion Diagnosis.

Knowing when a machine learning system is not confident about its prediction is crucial in medical domains where safety is critical. Ideally, a machine learning algorithm should make a prediction only when it is highly certain about its competency, and refer the case to physicians otherwise. In this paper, we investigate how Bayesian deep learning can improve the performance of the machine–physician team in the skin lesion classification task. We used the publicly available HAM10000 dataset, which includes samples from seven common skin lesion categories: Melanoma (MEL), Melanocytic Nevi (NV), Basal Cell Carcinoma (BCC), Actinic Keratoses and Intraepithelial Carcinoma (AKIEC), Benign Keratosis (BKL), Dermatofibroma (DF), and Vascular (VASC) lesions. Our experimental results show that Bayesian deep networks can boost the diagnostic performance of the standard DenseNet-169 model from 81.35% to 83.59% without incurring additional parameters or heavy computation. More importantly, a hybrid physician–machine workflow reaches a classification accuracy of while only referring of the cases to physicians. The findings are expected to generalize to other medical diagnosis applications. We believe that the availability of risk-aware machine learning methods will enable a wider adoption of machine learning technology in clinical settings.

New Similarity Measure between Intuitionistic Fuzzy Multisets based on Tangent Function and its Application in Medical Diagnosis

In recent years, Intuitionistic fuzzy set is very useful in decision making problems such as medical diagnosis, pattern recognition, clustering etc., which deals with vagueness and uncertainty. Similarity measure is a tool used to find the closeness of the intuitionistic fuzzy sets by considering the membership, nonmembership and hesitation function. In this paper, we propose an effective similarity measure based on tangent function for intuitionistic fuzzy multi sets in which membership, nonmembership, hesitation function occurs more than once and also we apply this measure in medical diagnosis and pattern recognition.

Gas Identification by a Single Metal-Oxide-Semiconductor Sensor Assisted by Ultrasound.

The gas identification technology has huge potential applications in medical diagnoses, food industries, early warning of poisonous gas leakage, fire prevention, antiterrorism, military, etc. Although electronic noses may be used to identify different gases, it has been a big challenge to identify gases by a single sensor. In this work, we demonstrate a novel gas identification strategy based on a single metal-oxide-semiconductor (MOS) sensor assisted by an ultrasound. The identification is based on different ultrasonic effects on the steady sensing responses of an ultrasonically radiated MOS gas sensor to different target gases. It does not need a complicated feature extraction computation. Our experiments show that the success rate of identification can be up to 100% if strong enough ultrasound is employed. The identification process can also give the concentration of the gas to be identified. The identification result is immune to the interference of impurity gases to some extent. The anti-interference capability may be strengthened by increasing the vibration velocity and choosing proper sensing materials.

High-performance stretchable PZT particles/Cu@Ag branch nanofibers composite piezoelectric nanogenerator for self-powered body motion monitoring

The development of stretchable nanogenerators has attracted intensive attentions for their promising applications in wearable electronics recently. Here, a newly high-performance stretchable PZT particles/Cu@Ag branch nanofibers (BNFs) nanocomposite piezoelectric generator (NCPG) is reported. The uniform mixture of PZT particles and Cu@Ag BNFs is blended into silicone rubber matrix that exhibits remarkably piezoelectric, mechanical and electrical characteristics. Owing to the similar molding method and the identical elastic matrix, the piezoelectric layer and the electrode layers could be completely integrated into stretchable NCPG based on all-in-one structure, which reveals high output performances (Vpeak–peak ≈ 61 V, Ipeak–peak ≈ 1.1 μA, 22.36 μw cm−3). The generated electricity is utilized to directly light five green emitting diodes (LEDs) and to drive a digital thermometer after stored in capacitor under the mechanical tensile strain stimulation. Moreover, the stretchable NCPG could act as a self-powered body motion sensor for distinguishing the bending angles and frequencies of the knee joint. This work provides a novel design idea for stretchable nanogenerators and shows great potential applications in artificial intelligence, medical diagnosis and movement entertainment.

Compact 3-D Antenna for Medical Diagnosis of the Human Head

A compact 3-D antenna for microwave medical diagnosis is presented. The antenna is matched with an inhomogeneous human head allowing higher signal penetration so as to obtain more meaningful data reflected from inside the brain. Utilizing a folded inverted F-like structure and a slot-loaded ground plane, the antenna is a compact $0.23\,\,\lambda \times 0.23 \,\,\lambda \times 0.04 \,\,\lambda $ in size with respect to the lowest operating frequency. The antenna is backed with a rectangular cavity to minimize sidelobe and backlobe radiation. The cavity and folded antenna configuration achieve a highly directional radiation pattern toward the head with a front-to-back ratio of more than 17 dB. A curved inhomogeneous human head phantom is fabricated to validate the antenna performance for medical diagnosis applications. An operational frequency band from 1 to 1.7 GHz is achieved with the antenna attached to the surface of the phantom. Less than 0.0147 W/kg SAR is achieved throughout the operating frequency range, which is lower than the state of the art for comparable antennas. The salient characteristics of the proposed antenna make it a suitable candidate for microwave diagnosis of the human head.

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

Though deep learning has shown successful performance in classifying the label and severity stage of certain disease, most of them give few evidence on how to make prediction. Here, we propose to exploit the interpretability of deep learning application in medical diagnosis. Inspired by Koch’s Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector. To visualize the symptom and feature encoded in this descriptor, we propose a GAN based method to synthesize pathological retinal image given the descriptor and a binary vessel segmentation. Besides, with this descriptor, we can arbitrarily manipulate the position and quantity of lesions. As verified by a panel of 5 licensed ophthalmologists, our synthesized images carry the symptoms that are directly related to diabetic retinopathy diagnosis. The panel survey also shows that our generated images is both qualitatively and quantitatively superior to existing methods.

Efficient multi-scale non-sub-sampled shearlet fusion system based on modified central force optimization and contrast enhancement

Infrared, visible, and medical image fusion systems are mandatory solutions for obtaining more spatial and more spectral information in a single image for efficient object detection and medical diagnosis applications. In this paper, an optimized fusion system for multi-modality images based on the Non-sub-Sampled Shearlet Transform (NSST) with Modified Central Force Optimization (MCFO), histogram matching, and local contrast enhancement is presented. The proposed multi-modality image fusion system consists of four stages. The first stage is the image registration and then histogram matching of one of the images to the other to allow the same dynamic range for both images to minimize the fusion artifacts. The NSST is used after that to decompose the images to be fused into their coefficients. The NSST provides a better sparse image representation of highly localized coefficients, anisotropic directionality, and reduced pseudo-Gibbs artifacts. After that, the MCFO technique is used to determine the optimum decomposition level and the optimum gain parameters for the best fusion of coefficients based on certain constraints. Finally, an additional contrast enhancement process is applied on the fused image to enhance its visual quality and reinforce details. The proposed fusion system is subjectively and objectively evaluated with different fusion quality metrics including average gradient, local contrast, standard deviation, edge intensity, entropy, Peak Signal-to-Noise Ratio (PSNR), and Qab/f. Real infrared, visible, and medical datasets of different modalities are used to test the proposed system. Experimental results demonstrate that the proposed system achieves a superior performance with higher image quality, higher evaluation metrics values, and much more details in images. These characteristics help for more accuracy in applications such as object detection and medical diagnosis.

A Fuzzy Brain Emotional Learning Classifier Design and Application in Medical Diagnosis

A Fuzzy Brain Emotional Learning Classifier Design and Application in Medical Diagnosis

Artificial intelligence, osteoporosis and fragility fractures.

Artificial intelligence tools have found new applications in medical diagnosis. These tools have the potential to capture underlying trends and patterns, otherwise impossible with previous modeling capabilities. Machine learning and deep learning models have found a role in osteoporosis, both to model the risk of fragility fracture, and to help with the identification and segmentation of images. Here we survey the latest research in the artificial intelligence application to the prediction of osteoporosis that has been published between January 2017 and March 2019. Around half of the articles that are covered here predict (by classification or regression) an indicator of osteoporosis, such as bone mass or fragility fractures; the other half of studies use tools for automatic segmentation of the images of patients with or at risk of osteoporosis. The data for these studies include diverse signal sources: acoustics, MRI, CT, and of course, X-rays. New methods for automatic image segmentation, and prediction of fracture risk show promising clinical value. Though these recent developments have had a successful initial application to osteoporosis research, their development is still under improvement, such as accounting for positive/negative class bias. We urge care when reporting accuracy metrics, and when comparing such metrics between different studies.

Similarity Measures between Temporal Complex Intuitionistic Fuzzy Sets and Application in Pattern Recognition and Medical Diagnosis

This work addresses the issue of similarity measures between two temporal complex Atanassov’s intuitionistic fuzzy sets, many measures of similarity between complex Atanassov’s intuitionistic fuzzy sets. What was proposed before did not consider the abstention group influence, which may lead to counterintuitive results in some cases. A new structure of temporal complex Atanassov’s intuitionistic fuzzy sets is obtained. This set is formally generalized from a conventional Atanassov’s intuitionistic complex fuzzy sets. Here we analyze the limitations of the existing similarity measures. Then, a new similarity measure of temporal complex Atanassov’s intuitionistic fuzzy sets is proposed and several numeric examples are given to demonstrate the validity of the proposed measure. Finally, the proposed similarity measure is applied to pattern recognition and medical diagnosis.

Deep convolutional neural network for classification of sleep stages from single-channel EEG signals

Using a smart method for automatic diagnosis in medical applications, such as sleep stage classification is considered as one of the important challenges of the last few years which can replace the time-consuming process of visual inspection done by specialists. One of the problems regarding the automatic diagnosis of sleep patterns is extraction and selection of discriminative features generally demanding high computational burden. This paper provides a new single-channel approach to automatic classification of sleep stages from EEG signal. The main idea is to directly apply the raw EEG signal to deep convolutional neural network, without involving feature extraction/selection, which is a challenging process in the previous literature. The proposed network architecture includes 9 convolutional layers followed by 2 fully connected layers. In order to make the samples of different classes balanced, we used a preprocessing method called data augmentation. The simulation results of the proposed method for classification of 2 to 6 classes of sleep stages show the accuracy of 98.10%, 96.86%, 93.11%, 92.95%, 93.55% and Cohen’s Kappa coefficient of 0.98%, 0.94%, 0.90%, 0.86% and 0.89%, respectively. Furthermore, comparing the obtained results with the state-of-the-art methods reveals the performance improvement of the proposed sleep stage classification in terms of accuracy and Cohen’s Kappa coefficient.

Simultaneous learning of reduced prototypes and local metric for image set classification

Classification based on image set is recently a competitive technique, where each set contains multiple images of a person or an object. As a widely used model, affine hull has shown its power in modeling image set. However, due to the existence of noise and outliers, the over-large affine hull usually matches fails when two hulls overlapped. Aiming at alleviating this handicap, this paper proposes a novel method for image set classification, namely Learning of Reduced Prototypes and Local Metric (LRPLM). Specifically, for each gallery image set, a reduced set of prototypes and an optimal local feature-wise metric are simultaneously learned, which jointly minimize the loss function involved the estimation of classification error probability. In doing so, LRPLM inherits the merits of affine hull with better representation to account for the unseen appearances and makes use of the powerful discriminative ability improved by the local metric. It looks like that LRPLM pulls similar image sets with the same class label “closer” to each other, while pushing dissimilar ones “far away”. Extensive experiments illustrate the considerable effectiveness of LRPLM on three widely used datasets. As we know, classification is a research hotspot in expert and intelligent systems. Different from the previous classification methods, LRPLM focuses on image set-based classification technology, while most of them are single-shot classification technology. Thus, the proposed method can be considered as an expert system technology for medical diagnosis, security monitoring, object categorization, and biometrics recognition applications.

Some Similarity Measures of Neutrosophic Sets Based on the Euclidean Distance and Their Application in Medical Diagnosis

Some Similarity Measures of Neutrosophic Sets Based on the Euclidean Distance and Their Application in Medical Diagnosis

New Similarity Measures of Single-Valued Neutrosophic Multisets Based on the Decomposition Theorem and Its Application in Medical Diagnosis

New Similarity Measures of Single-Valued Neutrosophic Multisets Based on the Decomposition Theorem and Its Application in Medical Diagnosis

A New Hybrid Distance-Based Similarity Measure for Refined Neutrosophic Sets and its Application in Medical Diagnosis

A New Hybrid Distance-Based Similarity Measure for Refined Neutrosophic Sets and its Application in Medical Diagnosis