Applications In Medical Diagnosis Research Articles

Iterative non-rigid image registration in Brain MRI images

Non-rigid image registration plays a significant role in medical imaging domain. It involves deformations of moving image pixels according to fixed or reference image anatomy. The accurate image registration is required for accurate medical diagnosis and clinical applications. Non-rigid image registration uses optimization technique to find best possible solution. The solution obtained using single run of non-rigid image registration may be optimal but not much accurate. In order to increase accuracy in non-rigid image registration, multiple runs are required to improve the performance. Here in our research methodology, we used Demon algorithm as non-rigid image registration for brain MRI images of patient with tumor. There is significant improvement i.e., average of 66.61% decrease in error of the results of iterative Demon algorithm as compared to non-iterative Demon algorithm.

N‐soft mappings with application in medical diagnosis

Fatimah et al. suggested different complement operations for N‐soft sets. However, these operations do not comply with De Morgan's laws and double complementation law for N‐soft sets. So we do not restate some classical theorems on topological spaces in the realm of N‐soft sets. Besides, the mappings are a basic mathematical tool which is utilized in numerous areas of mathematics, other sciences, and their applications. But there is not any note on the mappings in the setting of N‐soft set theory. To deal with these problems, firstly, we advance the concept of complement of an N‐soft set and demonstrate that De Morgan's laws and double complementation law are satisfied in N‐soft set theory according to this new definition. Then we present an idea of the N‐soft mappings and investigate some of their properties. Also, we illustrate given properties with examples and counter examples. Finally, using the N‐soft mappings, we describe a mathematical system design for diagnosing purpose of the Covid‐19 disease.

OAM light propagation through tissue

A major challenge in use of the optical spectrum for communication and imaging applications is the scattering of light as it passes through diffuse media. Recent studies indicate that light beams with orbital angular momentum (OAM) can penetrate deeper through diffuse media than simple Gaussian beams. To the best knowledge of the authors, in this paper we describe for the first time an experiment examining transmission of OAM beams through biological tissue with thickness of up to a few centimeters, and for OAM modes reaching up to 20. Our results indicate that OAM beams do indeed show a higher transmittance relative to Gaussian beams, and that the greater the OAM, the higher the transmittance also up to 20, Our results extend measured results to highly multi scattering media and indicate that at 2.6 cm tissue thickness for OAM of order 20, we measure nearly 30% more power in comparison to a Gaussian beam. In addition, we develop a mathematical model describing the improved permeability. This work shows that OAM beams can be a valuable contribution to optical wireless communication (OWC) for medical implants, optical biological imaging, as well as recent innovative applications of medical diagnosis.

APPLICATION OF A SEMI-AUTOMATED TECHNIQUE IN LUNG LESION SEGMENTATION

Segmentation is one of the most important steps in automated medical diagnosis applications, which affects the accuracy of the overall system. In this study, we apply a semi-automated technique that combines an active contour and low-level processing techniques in lung lesion segmentation by extracting lung lesions from thoracic Positron Emission Tomography (PET)/Computed Tomography (CT) images. The lesions were first segmented in Positron Emission Tomography (PET) images which have been converted previously to Standardised Uptake Values (SUVs). The segmented PET images then serve as an initial contour for subsequent active contour segmentation of corresponding CT images. To measure accuracy, the Jaccard Index (JI) was used. Jaccard Index (JI) was calculated by comparing the segmented lesion to alternative segmentations obtained from the QIN lung CT segmentation challenge, which is possible by registering the whole body PET/CT images to the corresponding thoracic CT images. The results showed that the semi-automated technique (combination techniques between an active contour and low-level processing) in lung lesion segmentation has moderate accuracy with an average JI value of 0.76±0.12.

A hybrid decision making method based on q-rung orthopair fuzzy soft information

Soft set (SfS) theory is a basic tool to handle vague information with parameterized study during the process as compared to fuzzy as well as q-rung orthopair fuzzy theory. This research article is devoted to establish some general aggregation operators (AOs), based on Yager’s norm operations, to cumulate the q-rung orthopair fuzzy soft data in decision making environments. In this article, the valuable properties of q-rung orthopair fuzzy soft set (q - ROFSfS) are merged with the Yager operator to propose four new operators, namely, q-rung orthopair fuzzy soft Yager weighted average (q - ROFSfYWA), q-rung orthopair fuzzy soft Yager ordered weighted average (q - ROFSfYOWA), q-rung orthopair fuzzy soft Yager weighted geometric (q - ROFSfYWG) and q-rung orthopair fuzzy soft Yager ordered weighted geometric (q - ROFSfYOWG) operators. The dominant properties of proposed operators are elaborated. To emphasize the importance of proposed operators, a multi-attribute group decision making (MAGDM) strategy is presented along with an application in medical diagnosis. The comparative study shows superiorities of the proposed operators and limitations of the existing operators. The comparison with Pythagorean fuzzy TOPSIS (PF-TOSIS) method shows that PF-TOPSIS method cannot deal with data involving parametric study but developed operators have the ability to deal with decision making problems using parameterized information.

An artificial intelligence process of immunoassay for multiple biomarkers based on logic gates.

We present a universal platform to synchronously analyze the possible existing state of two protein biomarkers. This platform is based on the integration of three logic gates: NAND, OR and NOT. These logic gates were constructed by the principle of immune recognition and fluorescence quenching between fluorescein labelled antibodies/antigens and antibody-conjugated graphene oxide (GO). An artificial intelligence (AI) protein analysis process was designed by us and accordingly a small program was written in JAVA. This protein analysis process with its JAVA code may be applied to give logic judgments on the possible existing state of two protein components. We expect that our fundamental research on multiple biomarker analysis can provide potential application in AI-assisted medical diagnosis with the interface for remote medical treatment.

Interpretable Pneumonia Detection by Combining Deep Learning and Explainable Models With Multisource Data

With the rapid development of AI techniques, Computer-aided Diagnosis has attracted much attention and has been successfully deployed in many applications of health care and medical diagnosis. For some specific tasks, the learning-based system can compare with or even outperform human experts' performance. The impressive performance owes to the excellent expressiveness and scalability of the neural networks, although the models' intuition usually cannot be represented explicitly. Interpretability is, however, very important, even the same as the diagnosis precision, for computer-aided diagnosis. To fill this gap, our approach is intuitive to detect pneumonia interpretably. We first build a large dataset of community-acquired pneumonia consisting of 35389 cases (distinguished from nosocomial pneumonia) based on actual medical records. Second, we train a prediction model with the chest X-ray images in our dataset, capable of precisely detecting pneumonia. Third, we propose an intuitive approach to combine neural networks with an explainable model such as the Bayesian Network. The experiment result shows that our proposal further improves the performance by using multi-source data and provides intuitive explanations for the diagnosis results.

Simultaneous quantitative analysis of Listeria monocytogenes and Staphylococcus aureus based on antibiotic-introduced lateral flow immunoassay.

Food poisoning caused by microorganisms has caused widespread concern. Herein, a highly sensitive on-site screening test strip for the detection of different pathogenic microorganisms (Listeria monocytogenes and Staphylococcus aureus) was designed. In this analysis platform, colloidal gold-coupled vancomycin was used as a signal unit to label Gram-positive bacteria, and highly sensitive polyclonal antibodies were used as recognition molecules to capture these specific strains. Compared with the traditional dual-antibody sandwich model, this new type of antibiotic-pathogen-antibody sandwich model is low-cost and can simultaneously detect multiple microorganisms. Under optimal conditions, this strategy showed satisfactory sensitivity and a wide linear range (L. monocy and S. aure could be directly assayed within linear ranges of 5 × 104 to 107 and 5 × 102 to 107 CFU mL-1, and the visual detection limits were 105 and 103 CFU mL-1, respectively). The analytical performance and practicability of this sensor system have been further studied. This developed biosensor was applied to bacteria-contaminated water, milk and broth with satisfactory results. All of these attractive characteristics make the assay possess potential applications in food safety, medical diagnosis and environmental monitoring.

Computational Effective Multimodal Medical Image Fusion in NSCT Domain

Multimodal Medical Image Fusion provides comprehensive data in recent medical image diagnosis applications. This paper presents a novel Multimodal Medical Image fusion framework based on the Angular Consistency (AC) and Sub Band Adaptive Filtering (SAF). In the proposed model, the Non-subsampled Contourlet Transform (NSSCT) decomposes the source image pair into high frequency (HF) and low frequency (LF) sub bands. The LF bands are integrated with Angular consistency rule that can fuse the finer details which are very much helpful in medical image diagnosis. Further the HF bands are processed through sub band adaptive filtering such that the redundant information is filtered out and only significant information is preserved. At last the fused sub bands are processed for Inverse Non-subsampled Contourlet Transform to produce a fused image. Experimental evaluation is accomplished through a real time image data set and the performance is measured through Edge Based Similarity index, Local Quality Index and Computational time. The obtained results show that the proposed system achieves a satisfactory results compared to the conventional methods.

Role of superhydrophobic coatings in biomedical applications

Superhydrophobic coatings repel water and, in some cases, other liquids as well. The non-adhesiveness is actuated by topographically elements at the nano-/micro scale and low surface energy. There are various applications which use superhydrophobic coatings such as biomedical, marine, auto- motive and energy sectors etc. Only a few superhydrophobic coatings are suitable for the biomedical applications because of the synthesis compounds' toxic behaviour. Here, in this review, we start with a discussion of superhydrophobicity and the various aspects that are required for the development of biocompatible superhydrophobic coatings for the application of medical diagnosis, medical equipment, use in covid-19 and hospital hygiene management.

Self-assembled natural biomacromolecular fluorescent hydrogels with tunable red edge effects

At present, fluorescent hydrogels have attracted more and more attention due to their wide applications in medical diagnosis, biological imaging and drug delivery. However, the luminescence of traditional fluorescent hydrogels usually requires specific fluorophores, and most of the fluorophores were rigid planar structures containing benzene rings or heterocyclic structures, making traditional fluorescent hydrogels have higher cytotoxicity and lower water solubility, thus limiting their practical applications. Here, we reported a fluorescent hydrogel, which can generate hydrogen bonds without emitting specific fluorophores, and it was found that the fluorescence intensity could be strengthened with the increase of concentration. At the same time, the fluorescence emission peak has the response of excitation wavelength and is not affected by the pH and concentration. Therefore, this special discovery in present work opens new application prospects for fluorescent hydrogels.

Micro/nanofiber-based noninvasive devices for health monitoring diagnosis and rehabilitation

Recently, in healthcare sectors, specifically for personalized health monitoring, motion sensing, and human–machine interactions, the rising demand for stretchable and soft electronic devices is significant. In particular, stretchable, skin mountable, breathable, wearable, light weight, and highly sensitive sensors are needed for detecting subtle deformation arising from human physiological signals and have potential applications in health diagnosis. In this review, we discuss flexible, noninvasive, and wearable sensors based on micro/nanofibers with unique sensing capabilities for detecting human vital signs such as body motion, temperature, heartbeat, respiration rate, and blood glucose level, which have applications in both fitness-monitoring and medical diagnosis. Here, the latest successful examples of micro/nanofiber based flexible and wearable human vital signs monitoring sensors in the form of film, mat, yarn, fabric, textiles, etc., are outlined and discussed in detail. Discussion includes the fiber fabrication technique, sensing mechanism, device structure, sensor performance, and data processing. Some of the latest fabricated self-powered devices with integrated sensing platforms are also reviewed. Finally, this article reveals the existing challenges that are still to be overcome associated with wearable technologies for applications in health monitoring, diagnosis, and rehabilitation.

Photo-excitation production of medically interesting isomers using intense γ-ray source

Photon-induced nuclear excitation (i.e. photo-excitation) can be used for production of nuclear isomers, which have potential applications in astrophysics, energy storage, medical diagnosis and treatment. This paper presents a feasibility study on photo-excitation production of four nuclear isomers (103mRh, 113m,115mIn and 176mLu) with intense γ-ray source based on laser-electron Compton scattering (LCS). The decay properties of these isomers and their potential applications in medical diagnosis and treatment were reviewed. The cross-section curve, simulated yield and activity of product of each photo-excitation process were calculated. The cutoff energy of LCS γ-ray beam was optimized by adjusting electron beam energy in order to maximize the isomer activity. It is found that the specific activity of the above-mentioned isomers can exceed ~0.2 GBq/g for 6-h target irradiation at an intensity of 1013 γ/s. Our simulation results suggest the prospect of producing medically interesting radionuclides with photo-excitation using the state-of-art LCS γ-ray beam facility.

Breast calcification detection based on multichannel radiofrequency signals via a unified deep learning framework

Breast calcifications in radiographic images suggest a high likelihood of breast lesion malignancy. However, it is difficult to detect calcifications in traditional B-mode ultrasound images due to resolution limits and speckle noise. In this paper, we propose a unified deep learning framework for automatic calcification detection based on multichannel ultrasound radio frequency (RF) signals. First, beamforming is used during preprocessing to merge and blend multichannel signals into one-channel RF signals. Each scan line is converted into a spectrogram by the short-time Fourier transform (STFT) to utilize the frequency domain characteristics. Then, an improved fully convolutional neural network called the RF signal Spectrogram-Calcification-Detection-Net (SCD-Net) is proposed to detect calcifications from spectrograms. This method employs a deep learning architecture based on YOLOv3 and combines features via convolutional long short-term memory (ConvLSTM). Next, a Kalman filter for tracking calcifications between consecutive spectrograms based on SCD-Net detection results is applied since the spatial coherence of calcifications in neighboring frames can be taken into account. Finally, the detected calcification is mapped from the time domain of spectrograms to B-mode images for clinical diagnosis. Experiments were conducted on a database of 337 experienced doctor-marked breast tumors with calcifications. Compared to the state-of-the-art methods for detecting calcifications, the proposed method achieved an average precision (AP) of 88.25%, an accuracy of 84% and an F1 score of 91%. The experimental results demonstrate that the unified framework has great performance for tumor calcification detection. The system can be effectively applied in a portable ultrasound instrument to accurately help radiologists and provide guidance for breast tumor diagnosis. This implies that the proposed approach can be implemented in real practice for analyzing breast RF signals, which have many useful medical applications in clinical breast tumor diagnosis.

NIR Luminescence Enhancement of YVO4:Nd Phosphor for Biological Application.

This work reports two systematic studies related to yttrium vanadate (YVO4) phosphors. The first evaluates how the annealing temperature and V5+/Y3+ molar ratio determine the emergence of a single YVO4 tetragonal phase, whereas the second concerns the optimal Nd3+ concentration to improve the infrared emission properties for bio-labelling applications. The YVO4:Nd phosphors were synthesized by adapting the non-hydrolytic sol-gel route. For the first study, samples containing different V5+/Y3+ molar ratios (1.02, 1.48, 1.71, or 3.13) were obtained. For the second study, YVO4:Nd phosphors containing different Nd3+ concentrations (1.0, 3.0, 5.0, or 10.0% in mol) were prepared. X-ray diffractometry and RAMAN spectroscopy results revealed that, regardless of the heat-treatment temperature, the V5+/Y3+ molar ratio of 1.48 was the best composition to avoid undesired phases like Y2O3 and V2O5. Photoluminescence results indicated that the sample containing 3.0% in mol of Nd3+ and annealed at 1000°C presented the best infrared emission properties. This sample displayed an intense broad band in the ultraviolet region, which was ascribed to the VO43- charge transfer band, as well as several bands in the visible and infrared regions, which were attributed to the Nd3+ intraconfigurational f-f transitions. Regardless of the excitation wavelength (ultraviolet, visible, or near-infrared), the mean radiative lifetime was about 12.00 µs. The prepared phosphors presented absorption and emission bands in the biological window (BW) regions, which are located between 750 and 900nm and between 1000 and 1300nm, so they are candidates for applications in medical imaging and diagnoses.

Influence of fast neutron irradiation on the phase composition and optical properties of homogeneous SiOx and composite Si–SiOx thin films

Layers and devices utilizing semiconductor nanocrystals have been the subjects of intensive research due to applications in opto- and microelectronic devices, solar cells, detectors, memories and in many more fields. We have shown previously that those nanocrystals in dielectric matrices undergo a substantial reformation during electron irradiation. The research of the interaction between semiconductor nanoclusters and irradiation is important for both the intentional modification of the structures and for understanding the stability of those devices under harsh, radiative conditions (e.g. space, nuclear, medical diagnosis, or similar applications). In the present research, we investigated the influence of neutron irradiation on substoichiometric silicon oxide. We investigated both homogeneous case and inhomogeneous case of matrices with silicon nanoclusters. We found that a fast neutron flux of 5.5 × 1013 neutrons/cm2 s and a fluence of 3.96 × 1017 neutrons/cm2 induce phase separation in the homogeneous films, whereas it decreases the volume fraction of the amorphous silicon phase caused by the reducing size of amorphous nanoclusters in the inhomogeneous films.

Controlled Synthesis of Au Chiral Propellers from Seeded Growth of Au Nanoplates for Chiral Differentiation of Biomolecules

Chiral plasmonic nanocrystals are promising materials for applications in enantioselective catalysis, DNA detection, and medical diagnosis. Herein, we demonstrate a simple and versatile strategy th...

A Review of Disorder Voice Processing Toward to Applications

Disorder voice processing has great potential to provide convenient, efficient and lowcost applications in medical diagnosis and treatment. For the purpose of a systematic summary of the research progress, this paper introduces it in three terms of research objects, acoustic parameters and features selection, and acoustic model and classification algorithms. It concludes that the appropriate feature selection, feature hybrid and feature offset, integrate with the deep learning frames are the future directions in disorder voice processing.

Calculus of new intuitionistic fuzzy generator: In generated intuitionistic fuzzy sets and its applications in medical diagnosis

Calculus of new intuitionistic fuzzy generator: In generated intuitionistic fuzzy sets and its applications in medical diagnosis

English

English