A two-stage exacerbated hypoxia nanoengineering strategy induced amplifying activation of tirapazamine for microwave hyperthermia-chemotherapy of breast cancer

Microwave hyperthermia (MH) is an emerging treatment for solid tumors, such as breast cancer, due to its advantages of minimally invasive and deep tissue penetration. However, MH induced tumor hypoxia is still an obstacle to breast tumor treatment failure. Therefore, an original nanoengineering strategy was proposed to exacerbate hypoxia in two stages, thereby amplifying the efficiency of activating tirapazamine (TPZ). And a novel microwave-sensitized nanomaterial (GdEuMOF@TPZ, GEMT) is designed. GdEuMOF (GEM) nanoparticles are certified excellent microwave (MW) sensitization performance, thus improving tumor selectivity to achieve MH. Meanwhile MW can aggravate the generation of thrombus and caused local circulatory disturbance of tumor, resulting in the Stage I exacerbated hypoxia environment passively. Due to tumor heterogeneity and uneven hypoxia, GEMT nanoparticles under microwave could actively deplete residual oxygen through the chemical reaction, exacerbating hypoxia level more evenly, thus forming the Stage II of exacerbated hypoxia environment. Consequently, a two-stage exacerbated hypoxia GEMT nanoparticles realize amplifying activation of TPZ, significantly enhance the efficacy of microwave hyperthermia and chemotherapy, and effectively inhibit breast cancer. This research provides insights into the development of progressive nanoengineering strategies for effective breast tumor therapy.

Three-dimensional printing of the human lung pleural cavity model for PDT malignant mesothelioma

OBJECTIVE

The primary aim was to investigate emerging 3D printing and optical acquisition technologies to refine and enhance photodynamic therapy (PDT) dosimetry in the management of malignant pleural mesothelioma (MPM).

MATERIALS AND METHODS

A rigorous digital reconstruction of the pleural lung cavity was conducted utilizing 3D printing and optical scanning methodologies. These reconstructions were systematically assessed against CT-derived data to ascertain their accuracy in representing critical anatomic features and post-resection topographical variations.

RESULTS

The resulting reconstructions excelled in their anatomical precision, proving instrumental translation for precise dosimetry calculations for PDT. Validation against CT data confirmed the utility of these models not only for enhancing therapeutic planning but also as critical tools for educational and calibration purposes.

CONCLUSION

The research outlined a successful protocol for the precise calculation of light distribution within the complex environment of the pleural cavity, marking a substantive advance in the application of PDT for MPM. This work holds significant promise for individualizing patient care, minimizing collateral radiation exposure, and improving the overall efficiency of MPM treatments.

Parkinson's disease diagnosis using deep learning: A bibliometric analysis and literature review

Parkinson's Disease (PD) is a progressive neurodegenerative illness triggered by decreased dopamine secretion. Deep Learning (DL) has gained substantial attention in PD diagnosis research, with an increase in the number of published papers in this discipline. PD detection using DL has presented more promising outcomes as compared with common machine learning approaches. This article aims to conduct a bibliometric analysis and a literature review focusing on the prominent developments taking place in this area. To achieve the target of the study, we retrieved and analyzed the available research papers in the Scopus database. Following that, we conducted a bibliometric analysis to inspect the structure of keywords, authors, and countries in the surveyed studies by providing visual representations of the bibliometric data using VOSviewer software. The study also provides an in-depth review of the literature focusing on different indicators of PD, deployed approaches, and performance metrics. The outcomes indicate the firm development of PD diagnosis using DL approaches over time and a large diversity of studies worldwide. Additionally, the literature review presented a research gap in DL approaches related to incremental learning, particularly in relation to big data analysis.

Heart and Lung Dose as Predictors of Overall Survival in Patients With Locally Advanced Lung Cancer. A National Multicenter Study

Introduction

It is an ongoing debate how much lung and heart irradiation impact overall survival (OS) after definitive radiotherapy for lung cancer. This study uses a large national cohort of patients with locally advanced NSCLC to investigate the association between OS and irradiation of lung and heart.

Methods

Treatment plans were acquired from six Danish radiotherapy centers, and patient characteristics were obtained from national registries. A hybrid segmentation tool automatically delineated the heart and substructures. Dose-volume histograms for all structures were extracted and analyzed using principal component analyses (PCAs). Parameter selection for a multivariable Cox model for OS prediction was performed using cross-validation based on bootstrapping.

Results

The population consisted of 644 patients with a median survival of 26 months (95% confidence interval [CI]: 24-29). The cross-validation selected two PCA variables to be included in the multivariable model. PCA1 represented irradiation of the heart and affected OS negatively (hazard ratio, 1.14; 95% CI: 1.04-1.26). PCA2 characterized the left-right balance (right atrium and left ventricle) irradiation, showing better survival for tumors near the right side (hazard ratio, 0.92; 95% CI: 0.84-1.00). Besides the two PCA variables, the multivariable model included age, sex, body-mass index, performance status, tumor dose, and tumor volume.

Conclusions

Besides the classic noncardiac risk factors, lung and heart doses had a negative impact on survival, while it is suggested that the left side of the heart is a more radiation dose-sensitive region. The data indicate that overall heart irradiation should be reduced to improve the OS if possible.

Machine learning based on SPECT/CT to differentiate bone metastasis and benign bone lesions in lung malignancy patients

BACKGROUND

Bone metastasis is a common event in lung cancer progression. Early diagnosis of lung malignant tumor with bone metastasis is crucial for selecting effective treatment strategies. However, 14.3% of patients are still difficult to diagnose after SPECT/CT examination.

PURPOSE

Machine learning analysis of [99mTc]-methylene diphosphate (99mTc-MDP) SPECT/CT scans to distinguish bone metastases from benign bone lesions in patients with lung cancer.

METHODS

One hundred forty-one patients (69 with bone metastases and 72 with benign bone lesions) were randomly assigned to the training group or testing group in a 7:3 ratio. Lesions were manually delineated using ITK-SNAP, and 944 radiomics features were extracted from SPECT and CT images. The least absolute shrinkage and selection operator (LASSO) regression was used to select the radiomics features in the training set, and the single/bimodal radiomics models were established based on support vector machine (SVM). To further optimize the model, the best bimodal radiomics features were combined with clinical features to establish an integrated Radiomics-clinical model. The diagnostic performance of models was evaluated using receiver operating characteristic (ROC) curve and confusion matrix, and performance differences between models were evaluated using the Delong test.

RESULTS

The optimal radiomics model comprised of structural modality (CT) and metabolic modality (SPECT), with an area under curve (AUC) of 0.919 and 0.907 for the training and testing set, respectively. The integrated model, which combined SPECT, CT, and two clinical features, exhibited satisfactory differentiation in the training and testing set, with AUC of 0.939 and 0.925, respectively.

CONCLUSIONS

The machine learning can effectively differentiate between bone metastases and benign bone lesions. The Radiomics-clinical integrated model demonstrated the best performance.

Investigating the interpretability of schizophrenia EEG mechanism through a 3DCNN-based hidden layer features aggregation framework

BACKGROUND AND OBJECTIVE

Electroencephalogram (EEG) signals record brain activity, with growing interest in quantifying neural activity through complexity analysis as a potential biological marker for schizophrenia. Presently, EEG complexity analysis primarily relies on manual feature extraction, which is subjective and yields varied findings in studies involving schizophrenia and healthy controls.

METHODS

This study aims to leverage deep learning methods for enhanced EEG complexity exploration, aiding early schizophrenia screening and diagnosis. Our proposed approach utilizes a three-dimensional Convolutional Neural Network (3DCNN) to extract enhanced data features for early schizophrenia identification and subsequent complexity analysis. Leveraging the spatiotemporal capabilities of 3DCNN, we extract advanced latent features and employ knowledge distillation to reintegrate these features into the original channels, creating feature-enhanced data.

RESULTS

We employ a 10-fold cross-validation strategy, achieving the average accuracies of 99.46% and 98.06% in subject-dependent experiments on Dataset 1(14SZ and 14HC) and Dataset 2 (45SZ and 39HC). The average accuracy for subject-independent is 96.04% and 92.67% on both datasets. Feature extraction and classification are conducted on both the re-aggregated data and the original data. Our results demonstrate that re-aggregated data exhibit superior classification performance and a more stable training process after feature extraction. In the complexity analysis of re-aggregated data, we observe lower entropy features in schizophrenic patients compared to healthy controls, with more pronounced differences in the temporal and frontal lobes. Analyzing Katz's Fractal Dimension (KFD) across three sub-bands of lobe channels reveals the lowest α band KFD value in schizophrenia patients.

CONCLUSIONS

This emphasizes the ability of our method to enhance the discrimination and interpretability in schizophrenia detection and analysis. Our approach enhances the potential for EEG-based schizophrenia diagnosis by leveraging deep learning, offering superior discrimination capabilities and richer interpretive insights.

Biomechanical Effectivity Evaluation of Single- and Double-Metal-Bar Methods with Rotation and Equilibrium Displacements in Nuss Procedure Simulations

Surgical treatment of the pectus excavatum has led to the introduction of the Nuss procedure, a minimally invasive surgical procedure that involves inserting a metal bar under the sternum through a small lateral thoracic incision. An additional metal bar was inserted in patients with pectus excavatum to improve the retention of the restored chest wall after the Nuss procedure. However, a need still exists to analyze the mechanistic advantages and disadvantages of the double-bar method owing to the increased surgical time and proficiency. The purpose of this study is to compare and evaluate the efficiency of single- and double-bar methods using rotational and equilibrium displacement simulations of the Nuss procedure. A finite-element model was constructed for two types of metal bars inserted into the chest wall. Boundary conditions for the rotation and equilibrium displacements were set for the metal bar. The anterior sternal translation, Haller index and maximum equivalent stress and strain owing to the behavior of the metal bar were estimated and compared with the single-bar method and postoperatively acquired patient data. The simulation results showed that the influences of the intercostal muscle and equilibrium after rotation displacement were significant. The stresses and strains were distributed across the two metal bars, and the upper-metal bar was heavily loaded. The double-bar method was advantageous regarding the load distribution effects of the two metal bars on the chest wall. However, mechanical assessments are also important because an excessive load is typically applied to the upper-metal bar.

FLASH Radiotherapy: What Can FLASH's Ultra High Dose Rate Offer to the Treatment of Patients With Sarcoma?

FLASH is an emerging treatment paradigm in radiotherapy (RT) that utilizes ultra-high dose rates (UHDR; >40 Gy)/s) of radiation delivery. Developing advances in technology support the delivery of UHDR using electron and proton systems, as well as some ion beam units (eg, carbon ions), while methods to achieve UHDR with photons are under investigation. The major advantage of FLASH RT is its ability to increase the therapeutic index for RT by shifting the dose response curve for normal tissue toxicity to higher doses. Numerous preclinical studies have been conducted to date on FLASH RT for murine sarcomas, alongside the investigation of its effects on relevant normal tissues of skin, muscle, and bone. The tumor control achieved by FLASH RT of sarcoma models is indistinguishable from that attained by treatment with standard RT to the same total dose. FLASH's high dose rates are able to mitigate the severity or incidence of RT side effects on normal tissues as evaluated by endpoints ranging from functional sparing to histological damage. Large animal studies and clinical trials of canine patients show evidence of skin sparing by FLASH vs. standard RT, but also caution against delivery of high single doses with FLASH that exceed those safely applied with standard RT. Also, a human clinical trial has shown that FLASH RT can be delivered safely to bone metastasis. Thus, data to date support continued investigations of clinical translation of FLASH RT for the treatment of patients with sarcoma. Toward this purpose, hypofractionated irradiation schemes are being investigated for FLASH effects on sarcoma and relevant normal tissues.

Initial Clinical Experience of a Novel Shapeable Bolus for Radiotherapy in a Patient With a Facial Cutaneous Squamous Cell Carcinoma: A Case Report

Radiation therapy with X-rays for skin cancer uses a bolus to increase the surface dose. Commercial gel sheet boluses adhere poorly to the patient's body because of surface irregularities. This causes an air gap and reduces the surface dose. We have developed a novel shapeable bolus (HM bolus; Hayakawa Rubber Co., Ltd., Hiroshima, Japan), and we describe the first clinical application of this bolus here. The case was an 82-year-old male with a facial cutaneous squamous cell carcinoma. The postoperative radiotherapy plan using the HM bolus provided a more uniform dose to the target compared with a plan without the HM bolus. The HM bolus adhered stably to the patient's skin, and there were no issues with its clinical use.

Non-Invasive Heart Failure Evaluation Using Machine Learning Algorithms

Heart failure is a prevalent cardiovascular condition with significant health implications, necessitating effective diagnostic strategies for timely intervention. This study explores the potential of continuous monitoring of non-invasive signals, specifically integrating photoplethysmogram (PPG) and electrocardiogram (ECG), for enhancing early detection and diagnosis of heart failure. Leveraging a dataset from the MIMIC-III database, encompassing 682 heart failure patients and 954 controls, our approach focuses on continuous, non-invasive monitoring. Key features, including the QRS interval, RR interval, augmentation index, heart rate, systolic pressure, diastolic pressure, and peak-to-peak amplitude, were carefully selected for their clinical relevance and ability to capture cardiovascular dynamics. This feature selection not only highlighted important physiological indicators but also helped reduce computational complexity and the risk of overfitting in machine learning models. The use of these features in training machine learning algorithms led to a model with impressive accuracy (98%), sensitivity (97.60%), specificity (96.90%), and precision (97.20%). Our integrated approach, combining PPG and ECG signals, demonstrates superior performance compared to single-signal strategies, emphasizing its potential in early and precise heart failure diagnosis. The study also highlights the importance of continuous monitoring with wearable technology, suggesting a significant stride forward in non-invasive cardiovascular health assessment. The proposed approach holds promise for implementation in hardware systems to enable continuous monitoring, aiding in early detection and prevention of critical health conditions.

Evaluation of the trend of set-up errors during the treatment period using set-up margin in prostate radiotherapy

Accurate information on set-up error during radiotherapy is essential for determining the optimal number of treatments in hypofractionated radiotherapy for prostate cancer. This necessitates careful control by the radiotherapy staff to assess the patient's condition. This study aimed to develop an evaluation method of the temporal trends in a patient's specific prostate movement during treatment using image matching and margin values. This study included 65 patients who underwent prostate volumetric modulated arc therapy (mean treatment time, 87.2 s). Set-up errors were assessed using bone, inter-, and intra-fraction marker matching across 39 fractions. The set-up margin was determined by dividing the four periods into 39 fractions using Stroom's formula and correlation coefficient. The intra-fraction set-up error was biased in the anterior-superior (AS) direction during treatment. The temporal trend of set-up errors during radiotherapy slightly increased based on bone matching and inter-fraction marker matching, with a 1.6-mm difference in the set-up margin fractions 11 to 20. The correlation coefficient of the mean prostate movement during treatment significantly decreased in the superior-inferior direction, while remaining high in the left-right and anterior-posterior directions. Image matching contributed significantly to the improvement of set-up errors; however, careful attention is needed for prostate movement in the AS direction, particularly during short treatment times. Understanding the trend of set-up errors during the treatment period is essential in numerical information sharing on patient condition and evaluating the margins for tailored hypo-fractionated radiotherapy, considering the facility's image-guided radiation therapy technology.

Characteristics of antenna fabricated using additive manufacturing technology and the potential applications

Antennas play a critical role in modern technology. They are used in various devices and applications, including wireless communication, broadcasting, navigation, military, and space. Overall, the importance of antennas in technology lies in their ability to transmit and receive signals, allowing communication and information transfer across various applications and devices. Three-dimensional printing technology creates antennas using multiple materials, including plastics, metals, and ceramics. Some standard 3D printing techniques used to create antennas include Fused Deposition Modeling (FDM), Stereolithography (SLA), and Selective Laser Sintering (SLS). These antennas can be made in various shapes and sizes. 3D printing can help create complex and customized antenna designs that are difficult or impossible to produce using traditional manufacturing methods. 3D-printing technology has many advantages for building antennas, including customization, ease of fabrication, and cost-effectiveness. This review comprehensively evaluates the usage of 3D-printing technology in antenna fabrication.

A Novel Framework Based on Deep Learning Architecture for Continuous Human Activity Recognition with Inertial Sensors

Frameworks for human activity recognition (HAR) can be applied in the clinical environment for monitoring patients' motor and functional abilities either remotely or within a rehabilitation program. Deep Learning (DL) models can be exploited to perform HAR by means of raw data, thus avoiding time-demanding feature engineering operations. Most works targeting HAR with DL-based architectures have tested the workflow performance on data related to a separate execution of the tasks. Hence, a paucity in the literature has been found with regard to frameworks aimed at recognizing continuously executed motor actions. In this article, the authors present the design, development, and testing of a DL-based workflow targeting continuous human activity recognition (CHAR). The model was trained on the data recorded from ten healthy subjects and tested on eight different subjects. Despite the limited sample size, the authors claim the capability of the proposed framework to accurately classify motor actions within a feasible time, thus making it potentially useful in a clinical scenario.

Stress reduction through cortical bone thickening improves bone mechanical behavior in adult female Beclin-1+/- mice

Fragility fractures, which are more prevalent in women, may be significantly influenced by autophagy due to altered bone turnover. As an essential mediator of autophagy, Beclin-1 modulates bone homeostasis by regulating osteoclast and chondrocyte differentiation, however, the alteration in the local bone mechanical environment in female Beclin-1+/- mice remains unclear. In this study, our aim is to investigate the biomechanical behavior of femurs from seven-month-old female wild-type (WT) and Beclin-1+/- mice under peak physiological load, using finite element analysis on micro-CT images. Micro-CT imaging analyses revealed femoral cortical thickening in Beclin-1+/- female mice compared to WT. Three-point bending test demonstrated a 63.94% increase in whole-bone strength and a 61.18% increase in stiffness for female Beclin-1+/- murine femurs, indicating improved biomechanical integrity. After conducting finite element analysis, Beclin-1+/- mice exhibited a 26.99% reduction in von Mises stress and a 31.62% reduction in maximum principal strain in the femoral midshaft, as well as a 36.64% decrease of von Mises stress in the distal femurs, compared to WT mice. Subsequently, the strength-safety factor was determined using an empirical formula, revealing that Beclin-1+/- mice exhibited significantly higher minimum safety factors in both the midshaft and distal regions compared to WT mice. In summary, considering the increased response of bone adaptation to mechanical loading in female Beclin-1+/- mice, our findings indicate that increasing cortical bone thickness significantly improves bone biomechanical behavior by effectively reducing stress and strain within the femoral shaft.

Gaussian Aquila optimizer based dual convolutional neural networks for identification and grading of osteoarthritis using knee joint images

Degenerative musculoskeletal disease known as Osteoarthritis (OA) causes serious pain and abnormalities for humans and on detecting at an early stage, timely treatment shall be initiated to the patients at the earliest to overcome this pain. In this research study, X-ray images are captured from the humans and the proposed Gaussian Aquila Optimizer based Dual Convolutional Neural Networks is employed for detecting and classifying the osteoarthritis patients. The new Gaussian Aquila Optimizer (GAO) is devised to include Gaussian mutation at the exploitation stage of Aquila optimizer, which results in attaining the best global optimal value. Novel Dual Convolutional Neural Network (DCNN) is devised to balance the convolutional layers in each convolutional model and the weight and bias parameters of the new DCNN model are optimized using the developed GAO. The novelty of the proposed work lies in evolving a new optimizer, Gaussian Aquila Optimizer for parameter optimization of the devised DCNN model and the new DCNN model is structured to minimize the computational burden incurred in spite of it possessing dual layers but with minimal number of layers. The knee dataset comprises of total 2283 knee images, out of which 1267 are normal knee images and 1016 are the osteoarthritis images with an image of 512 × 512-pixel width and height respectively. The proposed novel GAO-DCNN system attains the classification results of 98.25% of sensitivity, 98.93% of specificity and 98.77% of classification accuracy for abnormal knee case-knee joint images. Experimental simulation results carried out confirms the superiority of the developed hybrid GAO-DCNN over the existing deep learning neural models form previous literature studies.

High-capacity data hiding for medical images based on the mask-RCNN model

This study introduces a novel approach for integrating sensitive patient information within medical images with minimal impact on their diagnostic quality. Utilizing the mask region-based convolutional neural network for identifying regions of minimal medical significance, the method embeds information using discrete cosine transform-based steganography. The focus is on embedding within "insignificant areas", determined by deep learning models, to ensure image quality and confidentiality are maintained. The methodology comprises three main steps: neural network training for area identification, an embedding process for data concealment, and an extraction process for retrieving embedded information. Experimental evaluations on the CHAOS dataset demonstrate the method's effectiveness, with the model achieving an average intersection over union score of 0.9146, indicating accurate segmentation. Imperceptibility metrics, including peak signal-to-noise ratio, were employed to assess the quality of stego images, with results showing high capacity embedding with minimal distortion. Furthermore, the embedding capacity and payload analysis reveal the method's high capacity for data concealment. The proposed method outperforms existing techniques by offering superior image quality, as evidenced by higher peak signal-to-noise ratio values, and efficient concealment capacity, making it a promising solution for secure medical image handling.

Classification of cognitive ability of healthy older individuals using resting-state functional connectivity magnetic resonance imaging and an extreme learning machine

BACKGROUND

Quantitative determination of the correlation between cognitive ability and functional biomarkers in the older brain is essential. To identify biomarkers associated with cognitive performance in the older, this study combined an index model specific for resting-state functional connectivity (FC) with a supervised machine learning method.

METHODS

Performance scores on conventional cognitive test scores and resting-state functional MRI data were obtained for 98 healthy older individuals and 90 healthy youth from two public databases. Based on the test scores, the older cohort was categorized into two groups: excellent and poor. A resting-state FC scores model (rs-FCSM) was constructed for each older individual to determine the relative differences in FC among brain regions compared with that in the youth cohort. Brain areas sensitive to test scores could then be identified using this model. To suggest the effectiveness of constructed model, the scores of these brain areas were used as feature matrix inputs for training an extreme learning machine. classification accuracy (CA) was then tested in separate groups and validated by N-fold cross-validation.

RESULTS

This learning study could effectively classify the cognitive status of healthy older individuals according to the model scores of frontal lobe, temporal lobe, and parietal lobe with a mean accuracy of 86.67%, which is higher than that achieved using conventional correlation analysis.

CONCLUSION

This classification study of the rs-FCSM may facilitate early detection of age-related cognitive decline as well as help reveal the underlying pathological mechanisms.

Arrhythmia classification based on multi-feature multi-path parallel deep convolutional neural networks and improved focal loss

Early diagnosis of abnormal electrocardiogram (ECG) signals can provide useful information for the prevention and detection of arrhythmia diseases. Due to the similarities in Normal beat (N) and Supraventricular Premature Beat (S) categories and imbalance of ECG categories, arrhythmia classification cannot achieve satisfactory classification results under the inter-patient assessment paradigm. In this paper, a multi-path parallel deep convolutional neural network was proposed for arrhythmia classification. Furthermore, a global average RR interval was introduced to address the issue of similarities between N vs. S categories, and a weighted loss function was developed to solve the imbalance problem using the dynamically adjusted weights based on the proportion of each class in the input batch. The MIT-BIH arrhythmia dataset was used to validate the classification performances of the proposed method. Experimental results under the intra-patient evaluation paradigm and inter-patient evaluation paradigm showed that the proposed method could achieve better classification results than other methods. Among them, the accuracy, average sensitivity, average precision, and average specificity under the intra-patient paradigm were 98.73%, 94.89%, 89.38%, and 98.24%, respectively. The accuracy, average sensitivity, average precision, and average specificity under the inter-patient paradigm were 91.22%, 89.91%, 68.23%, and 95.23%, respectively.

Unsupervised local center of mass based scoliosis spinal segmentation and Cobb angle measurement

Scoliosis is a medical condition in which a person's spine has an abnormal curvature and Cobb angle is a measurement used to evaluate the severity of a spinal curvature. Presently, automatic Existing Cobb angle measurement techniques require huge dataset, time-consuming, and needs significant effort. So, it is important to develop an unsupervised method for the measurement of Cobb angle with good accuracy. In this work, an unsupervised local center of mass (LCM) technique is proposed to segment the spine region and further novel Cobb angle measurement method is proposed for accurate measurement. Validation of the proposed method was carried out on 2D X-ray images from the Saudi Arabian population. Segmentation results were compared with GMM-Based Hidden Markov Random Field (GMM-HMRF) segmentation method based on sensitivity, specificity, and dice score. Based on the findings, it can be observed that our proposed segmentation method provides an overall accuracy of 97.3% whereas GMM-HMRF has an accuracy of 89.19%. Also, the proposed method has a higher dice score of 0.54 compared to GMM-HMRF. To further evaluate the effectiveness of the approach in the Cobb angle measurement, the results were compared with Senior Scoliosis Surgeon at Multispecialty Hospital in Saudi Arabia. The findings indicated that the segmentation of the scoliotic spine was nearly flawless, and the Cobb angle measurements obtained through manual examination by the expert and the algorithm were nearly identical, with a discrepancy of only ± 3 degrees. Our proposed method can pave the way for accurate spinal segmentation and Cobb angle measurement among scoliosis patients by reducing observers' variability.

MR compatible detectors assessment for a 0.35 T MR-linac commissioning

PURPOSE

To assess a large panel of MR compatible detectors on the full range of measurements required for a 0.35 T MR-linac commissioning by using a specific statistical method represented as a continuum of comparison with the Monte Carlo (MC) TPS calculations. This study also describes the commissioning tests and the secondary MC dose calculation validation.

MATERIAL AND METHODS

Plans were created on the Viewray TPS to generate MC reference data. Absolute dose points, PDD, profiles and output factors were extracted and compared to measurements performed with ten different detectors: PTW 31010, 31021, 31022, Markus 34045 and Exradin A28 MR ionization chambers, SN Edge shielded diode, PTW 60019 microdiamond, PTW 60023 unshielded diode, EBT3 radiochromic films and LiF µcubes. Three commissioning steps consisted in comparison between calculated and measured dose: the beam model validation, the output calibration verification in four different phantoms and the commissioning tests recommended by the IAEA-TECDOC-1583.

MAIN RESULTS

The symmetry for the high resolution detectors was higher than the TPS data of about 1%. The angular responses of the PTW 60023 and the SN Edge were - 6.6 and - 11.9% compared to the PTW 31010 at 60°. The X/Y-left and the Y-right penumbras measured by the high resolution detectors were in good agreement with the TPS values except for the PTW 60023 for large field sizes. For the 0.84 × 0.83 cm2 field size, the mean deviation to the TPS of the uncorrected OF was - 1.7 ± 1.6% against - 4.0 ± 0.6% for the corrected OF whereas we found - 4.8 ± 0.8% for passive dosimeters. The mean absolute dose deviations to the TPS in different phantoms were 0 ± 0.4%, - 1.2 ± 0.6% and 0.5 ± 1.1% for the PTW 31010, PTW 31021 and Exradin A28 MR respectively.

CONCLUSIONS

The magnetic field effects on the measurements are considerably reduced at low magnetic field. The PTW 31010 ionization chamber can be used with confidence in different phantoms for commissioning and QA tests requiring absolute dose verifications. For relative measurements, the PTW 60019 presented the best agreement for the full range of field size. For the profile assessment, shielded diodes had a behaviour similar to the PTW 60019 and 60023 while the ionization chambers were the most suitable detectors for the symmetry. The output correction factors published by the IAEA TRS 483 seem to be applicable at low magnetic field pending the publication of new MR specific values.

ADHD-AID: Aiding Tool for Detecting Children's Attention Deficit Hyperactivity Disorder via EEG-Based Multi-Resolution Analysis and Feature Selection

The severe effects of attention deficit hyperactivity disorder (ADHD) among adolescents can be prevented by timely identification and prompt therapeutic intervention. Traditional diagnostic techniques are complicated and time-consuming because they are subjective-based assessments. Machine learning (ML) techniques can automate this process and prevent the limitations of manual evaluation. However, most of the ML-based models extract few features from a single domain. Furthermore, most ML-based studies have not examined the most effective electrode placement on the skull, which affects the identification process, while others have not employed feature selection approaches to reduce the feature space dimension and consequently the complexity of the training models. This study presents an ML-based tool for automatically identifying ADHD entitled "ADHD-AID". The present study uses several multi-resolution analysis techniques including variational mode decomposition, discrete wavelet transform, and empirical wavelet decomposition. ADHD-AID extracts thirty features from the time and time-frequency domains to identify ADHD, including nonlinear features, band-power features, entropy-based features, and statistical features. The present study also looks at the best EEG electrode placement for detecting ADHD. Additionally, it looks into the location combinations that have the most significant impact on identification accuracy. Additionally, it uses a variety of feature selection methods to choose those features that have the greatest influence on the diagnosis of ADHD, reducing the classification's complexity and training time. The results show that ADHD-AID has provided scores for accuracy, sensitivity, specificity, F1-score, and Mathew correlation coefficients of 0.991, 0.989, 0.992, 0.989, and 0.982, respectively, in identifying ADHD with 10-fold cross-validation. Also, the area under the curve has reached 0.9958. ADHD-AID's results are significantly higher than those of all earlier studies for the detection of ADHD in adolescents. These notable and trustworthy findings support the use of such an automated tool as a means of assistance for doctors in the prompt identification of ADHD in youngsters.

Remote photoplethysmography based on reflected light angle estimation

Objective. In previous studies, the factors affecting the accuracy of imaging photoplethysmography (iPPG) heart rate (HR) measurement have been focused on the light intensity, facial reflection angle, and motion artifacts. However, the factor of specularly reflected light has not been studied in detail. We explored the effect of specularly reflected light on the accuracy of HR estimation and proposed an estimation method for the direction of specularly radiated light.Approach. To study the HR measurement accuracy influenced by specularly reflected light, we control the component of specularly reflected light by controlling its angle. A total of 100 videos from four different reflected light angles were collected, and 25 subjects participated in the dataset collection. We extracted angles and illuminations for 71 facial regions, fitting sample points through interpolation, and selecting the angle corresponding to the maximum weight in the fitted curve as the estimated reflected angle.Main results. The experimental results show that higher specularly reflected light compromises HR estimation accuracy under the same value of light intensity. Notably, at a 60° angle, the HR accuracy (ACC) increased by 0.7%, while the signal-to-noise ratio and Pearson correlation coefficient increased by 0.8 dB and 0.035, respectively, compared to 0°. The overall root mean squared error, standard deviation, and mean error of our proposed reflected light angle estimation method on the illumination multi-angle incidence (IMAI) dataset are 1.173°, 0.978°, and 0.773°. The average Pearson value is 0.8 in the PURE rotation dataset. In addition, the average ACC of HR measurements in the PURE dataset is improved by 1.73% in our method compared to the state-of-the-art traditional methods.Significance. Our method has great potential for clinical applications, especially in bright light environments such as during surgery, to improve accuracy and monitor blood volume changes in blood vessels.

Multileaf collimator characterization and modeling for a 1.5 T MR-linac using static synchronous and asynchronous sweeping gaps

Objective.The Elekta unity MR-linac delivers step-and-shoot intensity modulated radiotherapy plans using a multileaf collimator (MLC) based on the Agility MLC used on conventional Elekta linacs. Currently, details of the physical Unity MLC and the computational model within its treatment planning system (TPS)Monacoare lacking in published literature. Recently, a novel approach to characterize the physical properties of MLCs was introduced using dynamic synchronous and asynchronous sweeping gap (aSG) tests. Our objective was to develop a step-and-shoot version of the dynamic aSG test to characterize the Unity MLC and the computational MLC models in theMonacoandRayStationTPSs.Approach.Dynamic aSG were discretized into a step-and-shoot aSG by investigating the number of segments/sweep and the minimal number of monitor units (MU) per segment. The step-and-shoot aSG tests were compared to the dynamic aSG tests on a conventional linac at a source-to-detector distance of 143.5 cm, mimicking the Unity configuration. the step-and-shoot aSG tests were used to characterize the Unity MLC through measurements and dose calculations in both TPSs.Main results.The step-and-shoot aSGs tests with 100 segments and 5 MU/segment gave results very similar to the dynamic aSG experiments. The effective tongue-and-groove width of the Unity gradually increased up to 1.4 cm from the leaf tip end. The MLC models inRayStationandMonacoagreed with experimental data within 2.0% and 10%, respectively. The largest discrepancies inMonacowere found for aSG tests with >10 mm leaf interdigitation, which are non-typical for clinical plans.Significance.The step-and-shoot aSG tests accurately characterize the MLC in step-and-shoot delivery mode. The MLC model inRayStation2023B accurately describes the tongue-and-groove and leaf tip effects whereasMonacooverestimates the tongue-and-groove shadowing further away from the leaf tip end.

MENet: A Mitscherlich function based ensemble of CNN models to classify lung cancer using CT scans

Lung cancer is one of the leading causes of cancer-related deaths worldwide. To reduce the mortality rate, early detection and proper treatment should be ensured. Computer-aided diagnosis methods analyze different modalities of medical images to increase diagnostic precision. In this paper, we propose an ensemble model, called the Mitscherlich function-based Ensemble Network (MENet), which combines the prediction probabilities obtained from three deep learning models, namely Xception, InceptionResNetV2, and MobileNetV2, to improve the accuracy of a lung cancer prediction model. The ensemble approach is based on the Mitscherlich function, which produces a fuzzy rank to combine the outputs of the said base classifiers. The proposed method is trained and tested on the two publicly available lung cancer datasets, namely Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases (IQ-OTH/NCCD) and LIDC-IDRI, both of these are computed tomography (CT) scan datasets. The obtained results in terms of some standard metrics show that the proposed method performs better than state-of-the-art methods. The codes for the proposed work are available at https://github.com/SuryaMajumder/MENet.

Generalizable disease detection using model ensemble on chest X-ray images

In the realm of healthcare, the demand for swift and precise diagnostic tools has been steadily increasing. This study delves into a comprehensive performance analysis of three pre-trained convolutional neural network (CNN) architectures: ResNet50, DenseNet121, and Inception-ResNet-v2. To ensure the broad applicability of our approach, we curated a large-scale dataset comprising a diverse collection of chest X-ray images, that included both positive and negative cases of COVID-19. The models' performance was evaluated using separate datasets for internal validation (from the same source as the training images) and external validation (from different sources). Our examination uncovered a significant drop in network efficacy, registering a 10.66% reduction for ResNet50, a 36.33% decline for DenseNet121, and a 19.55% decrease for Inception-ResNet-v2 in terms of accuracy. Best results were obtained with DenseNet121 achieving the highest accuracy at 96.71% in internal validation and Inception-ResNet-v2 attaining 76.70% accuracy in external validation. Furthermore, we introduced a model ensemble approach aimed at improving network performance when making inferences on images from diverse sources beyond their training data. The proposed method uses uncertainty-based weighting by calculating the entropy in order to assign appropriate weights to the outputs of each network. Our results showcase the effectiveness of the ensemble method in enhancing accuracy up to 97.38% for internal validation and 81.18% for external validation, while maintaining a balanced ability to detect both positive and negative cases.

Quantum Machine-Based Decision Support System for the Detection of Schizophrenia from EEG Records

Schizophrenia is a serious chronic mental disorder that significantly affects daily life. Electroencephalography (EEG), a method used to measure mental activities in the brain, is among the techniques employed in the diagnosis of schizophrenia. The symptoms of the disease typically begin in childhood and become more pronounced as one grows older. However, it can be managed with specific treatments. Computer-aided methods can be used to achieve an early diagnosis of this illness. In this study, various machine learning algorithms and the emerging technology of quantum-based machine learning algorithm were used to detect schizophrenia using EEG signals. The principal component analysis (PCA) method was applied to process the obtained data in quantum systems. The data, which were reduced in dimensionality, were transformed into qubit form using various feature maps and provided as input to the Quantum Support Vector Machine (QSVM) algorithm. Thus, the QSVM algorithm was applied using different qubit numbers and different circuits in addition to classical machine learning algorithms. All analyses were conducted in the simulator environment of the IBM Quantum Platform. In the classification of this EEG dataset, it is evident that the QSVM algorithm demonstrated superior performance with a 100% success rate when using Pauli X and Pauli Z feature maps. This study serves as proof that quantum machine learning algorithms can be effectively utilized in the field of healthcare.

Novel radiotherapeutic strategies in the management of brain metastases: Challenging the dogma

The role of radiation therapy in the management of brain metastasis is evolving. Advancements in machine learning techniques have improved our ability to both detect brain metastasis and our ability to contour substructures of the brain as critical organs at risk. Advanced imaging with PET tracers and magnetic resonance imaging-based artificial intelligence models can now predict tumor control and differentiate tumor progression from radiation necrosis. These advancements will help to optimize dose and fractionation for each patient's lesion based on tumor size, histology, systemic therapy, medical comorbidities/patient genetics, and tumor molecular features. This review will discuss the current state of brain directed radiation for brain metastasis. We will also discuss future directions to improve the precision of stereotactic radiosurgery and optimize whole brain radiation techniques to improve local tumor control and prevent cognitive decline without forming necrosis.

Deep learning approach to improve the recognition of hand gesture with multi force variation using electromyography signal from amputees

Variations in muscular contraction are known to significantly impact the quality of the generated EMG signal and the output decision of a proposed classifier. This is an issue when the classifier is further implemented in prosthetic hand design. Therefore, this study aims to develop a deep learning classifier to improve the classification of hand motion gestures and investigate the effect of force variations on their accuracy on amputees. The contribution of this study showed that the resulting deep learning architecture based on DNN (deep neural network) could recognize the six gestures and robust against different force levels (18 combinations). Additionally, this study recommended several channels that most contribute to the classifier's accuracy. Also, the selected time domain features were used for a classifier to recognize 18 combinations of EMG signal patterns (6 gestures and three forces). The average accuracy of the proposed method (DNN) was also observed at 92.0 ± 6.1 %. Moreover, several other classifiers were used as comparisons, such as support vector machine (SVM), decision tree (DT), K-nearest neighbors, and Linear Discriminant Analysis (LDA). The increase in the mean accuracy of the proposed method compared to other conventional classifiers (SVM, DT, KNN, and LDA), was 17.86 %. Also, the study's implication stated that the proposed method should be applied to developing prosthetic hands for amputees that recognize multi-force gestures.

ACPSEM position paper: pre-treatment patient specific plan checks and quality assurance in radiation oncology

The Australasian College of Physical Scientists and Engineers in Medicine (ACPSEM) has not previously made recommendations outlining the requirements for physics plan checks in Australia and New Zealand. A recent workforce modelling exercise, undertaken by the ACPSEM, revealed that the workload of a clinical radiation oncology medical physicist can comprise of up to 50% patient specific quality assurance activities. Therefore, in 2022 the ACPSEM Radiation Oncology Specialty Group (ROSG) set up a working group to address this issue. This position paper authored by ROSG endorses the recommendations of the American Association of Physicists in Medicine (AAPM) Task Group 218, 219 and 275 reports with some contextualisation for the Australia and New Zealand settings. A few recommendations from other sources are also endorsed to complete the position.

Efficient quality assurance for isocentric stability in stereotactic body radiation therapy using machine learning

This study aims to predict isocentric stability for stereotactic body radiation therapy (SBRT) treatments using machine learning (ML), covers the challenges of manual assessment and computational time for quality assurance (QA), and supports medical physicists to enhance accuracy. The isocentric parameters for collimator (C), gantry (G), and table (T) tests were conducted with the RUBY phantom during QA using TrueBeam linac for SBRT. This analysis combined statistical features from the IsoCheck EPID software. Five ML models, including logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB), and support vector machines (SVM), were used to predict the outcome of the QA procedure. 247 Winston-Lutz (WL) tests were collected from 2020 to 2022. In our study, both DT and RF achieved the highest score on test accuracy (Acc. test) ranging from 93.5% to 99.4%, and area under curve (AUC) values from 90 to 100% on three modes (C, G, and T). The precision, recall, and F1 scores indicate the DT model consistently outperforms other ML models in predicting isocenter stability deviation in QA. The QA assessment using ML models can assist error prediction early to avoid potential harm during SBRT and ensure safe and effective patient treatments.

CODENET: A deep learning model for COVID-19 detection

Conventional COVID-19 testing methods have some flaws: they are expensive and time-consuming. Chest X-ray (CXR) diagnostic approaches can alleviate these flaws to some extent. However, there is no accurate and practical automatic diagnostic framework with good interpretability. The application of artificial intelligence (AI) technology to medical radiography can help to accurately detect the disease, reduce the burden on healthcare organizations, and provide good interpretability. Therefore, this study proposes a new deep neural network (CNN) based on CXR for COVID-19 diagnosis - CodeNet. This method uses contrastive learning to make full use of latent image data to enhance the model's ability to extract features and generalize across different data domains. On the evaluation dataset, the proposed method achieves an accuracy as high as 94.20%, outperforming several other existing methods used for comparison. Ablation studies validate the efficacy of the proposed method, while interpretability analysis shows that the method can effectively guide clinical professionals. This work demonstrates the superior detection performance of a CNN using contrastive learning techniques on CXR images, paving the way for computer vision and artificial intelligence technologies to leverage massive medical data for disease diagnosis.

Usefulness of Ag Additional Filter on Image Quality and Radiation Dose for Low-Dose Chest Computed Tomography

OBJECTIVE

This study aimed to evaluate the effect of a silver (Ag) additional filter on dose characteristics and image quality in low-dose chest computed tomography (CT).

METHODS

A dose evaluation phantom, physical evaluation phantom, and chest phantom were scanned with and without an Ag additional filter. The doses were adjusted so that the displayed the volume CT dose indexes (CTDI vol ) were from 0.3 to 1.6 mGy. For dose characteristics, the spectrum of photon energies and the measured CTDI vol were calculated for each scanning condition. For task-based image quality analysis, task transfer function, noise power spectrum, and system performance were evaluated. Streak artifacts, image noise, and contrast-to-noise ratio were quantified using a chest phantom.

RESULTS

With the Ag additional filter, mean energy was 22% higher and the CTDI vol was approximately 30% lower than those without the Ag additional filter. The task transfer function and noise power spectrum with the Ag additional filter were lower than those without the Ag additional filter. The system performance with the Ag additional filter was similar to that without the Ag additional filter. The Ag additional filter reduced streak artifact near the lung apex and image noise in the lung fields. The contrast-to-noise ratio was slightly higher with the Ag additional filter than that without the Ag additional filter.

CONCLUSIONS

The output dose and spatial resolution with the Ag additional filter were lower than those without the Ag additional filter. However, this filter helped reduce the radiation dose, image noise, and streak artifacts, particularly when scanning at ultralow doses.

A hypoxia biomarker does not predict benefit from giving chemotherapy with radiotherapy in the BC2001 randomised controlled trial

BACKGROUND

BC2001 showed combining chemotherapy (5-FU + mitomycin-C) with radiotherapy improves loco-regional disease-free survival in patients with muscle-invasive bladder cancer (MIBC). We previously showed a 24-gene hypoxia-associated signature predicted benefit from hypoxia-modifying radiosensitisation in BCON and hypothesised that only patients with low hypoxia scores (HSs) would benefit from chemotherapy in BC2001. BC2001 allowed conventional (64Gy/32 fractions) or hypofractionated (55Gy/20 fractions) radiotherapy. An exploratory analysis tested an additional hypothesis that hypofractionation reduces reoxygenation and would be detrimental for patients with hypoxic tumours.

METHODS

RNA was extracted from pre-treatment biopsies (298 BC2001 patients), transcriptomic data generated (Affymetrix Clariom-S arrays), HSs calculated (median expression of 24-signature genes) and patients stratified as hypoxia-high or -low (cut-off: cohort median).

PRIMARY ENDPOINT

invasive loco-regional control (ILRC); secondary overall survival.

FINDINGS

Hypoxia affected overall survival (HR = 1.30; 95% CI 0.99-1.70; p = 0.062): more uncertainty for ILRC (HR = 1.29; 95% CI 0.82-2.03; p = 0.264). Benefit from chemotherapy was similar for patients with high or low HSs, with no interaction between HS and treatment arm. High HS associated with poor ILRC following hypofractionated (n = 90, HR 1.69; 95% CI 0.99-2.89 p = 0.057) but not conventional (n = 207, HR 0.70; 95% CI 0.28-1.80, p = 0.461) radiotherapy. The finding was confirmed in an independent cohort (BCON) where hypoxia associated with a poor prognosis for patients receiving hypofractionated (n = 51; HR 14.2; 95% CI 1.7-119; p = 0.015) but not conventional (n = 24, HR 1.04; 95% CI 0.07-15.5, p = 0.978) radiotherapy.

INTERPRETATION

Tumour hypoxia status does not affect benefit from BC2001 chemotherapy. Hypoxia appears to affect fractionation sensitivity. Use of HSs to personalise treatment needs testing in a biomarker-stratified trial.

FUNDING

Cancer Research UK, NIHR, MRC.

NIMEQ-SACNet: A novel self-attention precision medicine model for vision-threatening diabetic retinopathy using image data

In the realm of precision medicine, the potential of deep learning is progressively harnessed to facilitate intricate clinical decision-making, especially when navigating multifaceted datasets encompassing Omics, Clinical, image, device, social, and environmental dimensions. This study accentuates the criticality of image data, given its instrumental role in detecting and classifying vision-threatening diabetic retinopathy (VTDR) - a predominant global contributor to vision impairment. The timely identification of VTDR is a linchpin for efficacious interventions and the mitigation of vision loss. Addressing this, This study introduces "NIMEQ-SACNet," a novel hybrid model by the prowess of the Enhanced Quantum-Inspired Binary Grey Wolf Optimizer (EQI-BGWO) with a self-attention capsule network. The proposed approach is characterized by two pivotal advancements: firstly, the augmentation of the Binary Grey Wolf Optimization through Quantum Computing methodologies, and secondly, the deployment of the enhanced EQI-BGWO to adeptly calibrate the SACNet's parameters, culminating in a notable uplift in VTDR classification accuracy. The proposed model's ability to handle binary, 5-stage, and 7-stage VTDR classifications adroitly is noteworthy. Rigorous assessments on the fundus image dataset, underscored by metrics such as Accuracy, Sensitivity, Specificity, Precision, F1-Score, and MCC, bear testament to NIMEQ-SACNet's pre-eminence over prevailing algorithms and classification frameworks.

Development and validation of a gel wax phantom to evaluate geometric accuracy and measurement of a hyperechoic target diameter in diagnostic ultrasound imaging

Diagnostic ultrasound (US) scanners are generally evaluated using proprietary quality assurance (QA) phantoms, but their prohibitively high cost may prevent organizations to perform the necessary tests. This study aimed to develop a low-cost gel wax phantom with targets to determine the lateral and axial resolution and diameter of a hyperechoic target in an US scanner. The acoustic property (AP) of gel wax, which includes the speed of sound (cus), acoustic impedance (Z), and attenuation coefficient (µ), were determined for multiple transducers operating at 2.25, 5, 10, 15, and 30 MHz. These results were compared to the AP of soft tissue. Two polytetrafluoroethylene (PTFE) rectangular frames with holes separated by 5, 10, and 20 mm were constructed. Nylon filaments and stainless-steel disc (SS disc) (diameter = 16.8 mm) were threaded through the frames and suitably placed in gel wax to obtain orthogonal targets in the phantom. The target dimensions obtained from computerized tomography (CT) and US images of the phantom were compared for phantom validation. The average cus=1431.4 m/s, mass density ρ = 0.87 g/cm3, Z = 1.24 MRayls, and µ ranged from 0.7 to 0.98 dB/cm/MHz for gel wax at 22 °C. The US image measurement exhibited a maximum error in determining the diameter of the SS disc, resulting in a value of 18 mm instead of its actual value of 16.8 mm. The phantom volume decreased by 1.8% in 62 weeks. The present phantom is affordable, stable, customizable, and can be used to evaluate diagnostic US scanners across multiple centers.

MRI-Based Radiomics Methods for Predicting Ki-67 Expression in Breast Cancer: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

The purpose of this systematic review and meta-analysis was to assess the quality and diagnostic accuracy of MRI-based radiomics for predicting Ki-67 expression in breast cancer.

MATERIALS AND METHODS

A systematic literature search was performed to find relevant studies published in different databases, including PubMed, Web of Science, and Embase up until March 10, 2023. All papers were independently evaluated for eligibility by two reviewers. Studies that matched research questions and provided sufficient data for quantitative synthesis were included in the systematic review and meta-analysis, respectively. The quality of the articles was assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) and Radiomics Quality Score (RQS) tools. The predictive value of MRI-based radiomics for Ki-67 antigen in patients with breast cancer was assessed using pooled sensitivity (SEN), specificity, and area under the curve (AUC). Meta-regression was performed to explore the cause of heterogeneity. Different covariates were used for subgroup analysis.

RESULTS

31 studies were included in the systematic review; among them, 21 reported sufficient data for meta-analysis. 20 training cohorts and five validation cohorts were pooled separately. The pooled sensitivity, specificity, and AUC of MRI-based radiomics for predicting Ki-67 expression in training cohorts were 0.80 [95% CI, 0.73-0.86], 0.82 [95% CI, 0.78-0.86], and 0.88 [95%CI, 0.85-0.91], respectively. The corresponding values for validation cohorts were 0.81 [95% CI, 0.72-0.87], 0.73 [95% CI, 0.62-0.82], and 0.84 [95%CI, 0.80-0.87], respectively. Based on QUADAS-2, some risks of bias were detected for reference standard and flow and timing domains. However, the quality of the included article was acceptable. The mean RQS score of the included articles was close to 6, corresponding to 16.6% of the maximum possible score. Significant heterogeneity was observed in pooled sensitivity and specificity of training cohorts (I2 > 75%). We found that using deep learning radiomic methods, magnetic field strength (3 T vs. 1.5 T), scanner manufacturer, region of interest structure (2D vs. 3D), route of tissue sampling, Ki-67 cut-off, logistic regression for model construction, and LASSO for feature reduction as well as PyRadiomics software for feature extraction had a great impact on heterogeneity according to our joint model analysis. Diagnostic performance in studies that used deep learning-based radiomics and multiple MRI sequences (e.g., DWI+DCE) was slightly higher. In addition, radiomic features derived from DWI sequences performed better than contrast-enhanced sequences in terms of specificity and sensitivity. No publication bias was found based on Deeks' funnel plot. Sensitivity analysis showed that eliminating every study one by one does not impact overall results.

CONCLUSION

This meta-analysis showed that MRI-based radiomics has a good diagnostic accuracy in differentiating breast cancer patients with high Ki-67 expression from low-expressing groups. However, the sensitivity and specificity of these methods still do not surpass 90%, restricting them from being used as a supplement to current pathological assessments (e.g., biopsy or surgery) to predict Ki-67 expression accurately.

Wavelet transform and deep learning-based obstructive sleep apnea detection from single-lead ECG signals

Sleep apnea is a common sleep disorder. Traditional testing and diagnosis heavily rely on the expertise of physicians, as well as analysis and statistical interpretation of extensive sleep testing data, resulting in time-consuming and labor-intensive processes. To address the problems of complex feature extraction, data imbalance, and low model capacity, we proposed an automatic sleep apnea classification model (CA-EfficientNet) based on the wavelet transform, a lightweight neural network, and a coordinated attention mechanism. The signal is converted into a time-frequency image by wavelet transform and put into the proposed model for classification. The effects of input time window, wavelet transform type and data balancing on the classification performance are considered, and a cost-sensitive algorithm is introduced to more accurately distinguish between normal and abnormal breathing events. PhysioNet apnea ECG database was used for training and evaluation. The 3-min Frequency B-Spline wavelets transform of ECG signal was carried out, and Dice Loss was used to train the classification model of sleep breathing. The classification accuracy was 93.44%, sensitivity was 88.9%, specificity was 96.2% and most indexes were better than other related work.

Quality improvement of images with metal artifact reduction using a noise recovery technique in computed tomography

In metal artifact reduction (MAR) in computed tomography (CT) based on projection data inpainting, X-ray photon noise has not been considered in the inpainting process. This study aims to assess the effectiveness of a MAR technique incorporating noise recovery in such projection data regions, compared with existing MAR techniques based on projection data normalization (NMAR), including one with frequency splitting (FSNMAR). Phantoms simulating hip prostheses and dental fillings were scanned using a 64-row multi slice CT scanner. The projection data was processed by NMAR and NMAR with noise recovery (NRNMAR); the processed data was sent back to the CT system for reconstruction. For the phantoms and clinical cases with hip prostheses and dental fillings, images were reconstructed without MAR, and with NMAR, NRNMAR, and FSNMAR (incorporated in the CT system). To validate the efficacy of noise recovery, noise power spectra (NPSs) were measured from the images of the hip prosthesis phantom with and without metals. The artifact index (AI) was compared between NRNMAR and FSNMAR. The resultant NPSs of NRNMAR were very similar to those of phantom images with no metals, endorsing the efficacy of noise recovery. The NMAR images had unnatural noise textures and FSNMAR caused additional streaks. NRNMAR exhibited some significant improvements in these respects: It reduced the AI by as much as 66.2-88.6% compared to FSNMAR, except for the case of a unilateral prosthesis. In conclusion, NRNMAR, which simply adds white noise to the projection data, would be effective in improving the quality of CT images with metal artifacts reduction.

UBES: Unified scatter correction using ultrafast Boltzmann equation solver for conebeam CT

A semi-analytical solution to the unified Boltzmann equation is constructed to exactly describe the scatter distribution on a flat-panel detector for high-quality conebeam CT (CBCT) imaging. The solver consists of three parts, including the phase space distribution estimator, the effective source constructor and the detector signal extractor. Instead of the tedious Monte Carlo solution, the derived Boltzmann equation solver achieves ultrafast computational capability for scatter signal estimation by combining direct analytical derivation and time-efficient one-dimensional numerical integration over the trajectory along each momentum of the photon phase space distribution. The execution of scatter estimation using the proposed ultrafast Boltzmann equation solver (UBES) for a single projection is finalized in around 0.4 seconds. We compare the performance of the proposed method with the state-of-the-art schemes, including a time-expensive Monte Carlo (MC) method and a conventional kernel-based algorithm using the same dataset, which is acquired from the CBCT scans of a head phantom and an abdominal patient. The evaluation results demonstrate that the proposed UBES method achieves comparable correction accuracy compared with the MC method, while exhibits significant improvements in image quality over learning and kernel-based methods. With the advantages of MC equivalent quality and superfast computational efficiency, the UBES method has the potential to become a standard solution to scatter correction in high-quality CBCT reconstruction.

A Nonlinear Functional Link Multilayer Perceptron Using Volterra Series as an Adaptive Noise Canceler for the Extraction of Fetal Electrocardiogram

Uninterrupted monitoring of fetal cardiac health is essential for the timely diagnosis of congenital diseases. The maternal Electrocardiogram (mECG), which has the most significant impact, always tampers with the signals collected from the pregnant woman's abdomen. So, an efficient nonlinear filtering network based on artificial neural network (ANN) is required to eliminate the maternal part from the abdominal Electrocardiogram (aECG) that is traveled from the thoracic of the mother to the abdomen following nonlinear dynamics. In this work, we have presented an adaptive noise canceler (ANC) using 3-layer perceptron architecture where the inputs are expanded by the functional link expansion using the second-order Volterra series, and the weights are updated using backpropagation. The adaptive filter approximates the nonlinear mapping between the thoracic Electrocardiogram (tECG) and the maternal component present in the aECG. Here the thoracic signal is the reference signal, and the abdominal signal is the desired signal to the adaptive filter. The proposed methodology uses the advantages of both multilayer perceptron (MLP) as well as functional link neural network (FLNN) in mapping the nonlinearity and effectively determining the fetal Electrocardiogram (fECG) from the aECG. For the detailed analysis, we have used the real Daisy database, the Non-invasive Fetal ECG database, and the fetal ECG synthetic database from Physionet. The results show that the nonlinear functional link MLP using the Volterra series gives a high-level performance compared to other classical adaptive filtering techniques, as all the evaluation metrics are above 90%.

A feature engineering-based machine learning technique to detect and classify lung and colon cancer from histopathological images

Globally, lung and colon cancers are among the most prevalent and lethal tumors. Early cancer identification is essential to increase the likelihood of survival. Histopathological images are considered an appropriate tool for diagnosing cancer, which is tedious and error-prone if done manually. Recently, machine learning methods based on feature engineering have gained prominence in automatic histopathological image classification. Furthermore, these methods are more interpretable than deep learning, which operates in a "black box" manner. In the medical profession, the interpretability of a technique is critical to gaining the trust of end users to adopt it. In view of the above, this work aims to create an accurate and interpretable machine-learning technique for the automated classification of lung and colon cancers from histopathology images. In the proposed approach, following the preprocessing steps, texture and color features are retrieved by utilizing the Haralick and Color histogram feature extraction algorithms, respectively. The obtained features are concatenated to form a single feature set. The three feature sets (texture, color, and combined features) are passed into the Light Gradient Boosting Machine (LightGBM) classifier for classification. And their performance is evaluated on the LC25000 dataset using hold-out and stratified 10-fold cross-validation (Stratified 10-FCV) techniques. With a test/hold-out set, the LightGBM with texture, color, and combined features classifies the lung and colon cancer images with 97.72%, 99.92%, and 100% accuracy respectively. In addition, a stratified 10-fold cross-validation method also revealed that LightGBM's combined or color features performed well, with an excellent mean auc_mu score and a low mean multi_logloss value. Thus, this proposed technique can help histologists detect and classify lung and colon histopathology images more efficiently, effectively, and economically, resulting in more productivity.

Artificial intelligence for automatic classification of needle EMG signals: A scoping review

OBJECTIVE

This scoping review provides an overview of artificial intelligence (AI), including machine and deep learning techniques, in the interpretation of clinical needle electromyography (nEMG) signals.

METHODS

A comprehensive search of Medline, Embase and Web of Science was conducted to find peer-reviewed journal articles. All papers published after 2010 were included. The methodological quality of the included studies was assessed with CLAIM (checklist for artificial intelligence in medical imaging).

RESULTS

51 studies were identified that fulfilled the inclusion criteria. 61% used open-source EMGlab data set to develop models to classify nEMG signal in healthy, amyotrophic lateral sclerosis (ALS) and myopathy (25 subjects). Only two articles developed models to classify signals recorded at rest. Most articles reported high performance accuracies, but many were subject to bias and overtraining.

CONCLUSIONS

Current AI-models of nEMG signals are not sufficient for clinical implementation. Suggestions for future research include emphasizing the need for an optimal training and validation approach using large datasets of clinical nEMG data from a diverse patient population.

SIGNIFICANCE

The outcomes of this study and the suggestions made aim to contribute to developing AI-models that can effectively handle signal quality variability and are suitable for daily clinical practice in interpreting nEMG signals.

Multicentric characterisation of lateral beam profiles generated by 6FFF beam of three 0.35 T MR-linac systems

BACKGROUND

The physical characterisation of FFF-beam profiles in the presence of a magnetic field requires a new standardization procedure and formulation.

PURPOSE

The aim of this multicentric experience is to propose new normalisation factors to allow for the calculation of standard parameters typical of flattened beams, such as dosimetric field size and penumbra, for a 6 MV FFF beam from an MR-linac.

METHODS

The measurements were carried out on three ViewRay-MRIdiansystems. An equal set of measurements was acquired using the same equipment. Transverse beam profiles were acquired at seven different depthsand for six beam dimensions.The inflection point was estimated as the position of the maximum of a Gaussian fit obtained from the first derivative of the profiles. The position of the minimum and maximum points of the second derivative of the above Gaussian described the fall-off region, and the external peaks of the third derivative were considered as the in-field and out-field points. The profile normalisation was determined by imposing a 55% dose level at the inflection point and the renormalisation factors were calculated.

RESULTS

The position of the inflection point, and the second and third derivatives peaks were analysed,and the renormalisation factors as a function of field size and depth were determined. The values of the unflatness and the slope have been calculated for different depths and field sizes.

CONCLUSION

This study represents the first multi-centric evaluation of the profiles on different low-field MR-Linac systems and theset of renormalisation parameters to analyse the FFF-beam on that system was effectively proposed.

Identification of OSAHS patients based on ReliefF-mRMR feature selection

Obstructive Sleep Apnea Hypopnea Syndrome (OSAHS) is a serious chronic sleep disorder. Snoring is a common and easily observable symptom of OSAHS patients. The purpose of this work is to identify OSAHS patients by analyzing the acoustic characteristics of snoring sounds throughout the entire night. Ten types of acoustic features, such as Mel-frequency cepstral coefficients (MFCC), linear prediction coefficients (LPC) and spectral entropy among others, were extracted from the snoring sounds. A fused feature selection algorithm based on ReliefF and Max-Relevance and Min-Redundancy (mRMR) was proposed for optimal feature set selection. Four types of machine learning models were then applied to validate the effectiveness of OSAHS patient identification. The results show that the proposed feature selection algorithm can effectively select features with high contribution, including MFCC and LPC. Based on the selected top-20 features and using a support vector machine model, the accuracies in identifying OSAHS patients under the thresholds of AHI = 5,15, and 30, were 100%, 100%, and 98.94%, respectively. This indicates that the proposed model can effectively identify OSAHS patients.

Advancements in non-invasive microwave brain stimulation: A comprehensive survey

This survey provides a comprehensive insight into the world of non-invasive brain stimulation and focuses on the evolving landscape of deep brain stimulation through microwave research. Non-invasive brain stimulation techniques provide new prospects for comprehending and treating neurological disorders. We investigate the methods shaping the future of deep brain stimulation, emphasizing the role of microwave technology in this transformative journey. Specifically, we explore antenna structures and optimization strategies to enhance the efficiency of high-frequency microwave stimulation. These advancements can potentially revolutionize the field by providing a safer and more precise means of modulating neural activity. Furthermore, we address the challenges that researchers currently face in the realm of microwave brain stimulation. From safety concerns to methodological intricacies, this survey outlines the barriers that must be overcome to fully unlock the potential of this technology. This survey serves as a roadmap for advancing research in microwave brain stimulation, pointing out potential directions and innovations that promise to reshape the field.

A simple method to shorten the apparent dead time in the dosimetry of Lu-177 for targeted radionuclide therapy using a gamma camera

BACKGROUND

The dead-time loss reportedly degrades the accuracy of dosimetry using a gamma camera for targeted radionuclide therapy with Lu-177; therefore, the dead-time loss needs to be corrected. However, the correction is challenging. In this study, we propose a novel and simple method to shorten the apparent dead time rather than correcting it through experiments and Monte Carlo simulations.

METHODS

An energy window of 208 keV ± 10 % is generally used for the imaging of Lu-177. Lower-energy gamma photons and X-rays of Lu-177 do not contribute to image formation but lead to dead-time losses. In our proposed method, a thin lead sheet was used to shield gamma photons and X-rays with energies lower than 208 keV, while detecting 208 keV gamma photons that penetrated the thin sheet. We measured and simulated the energy spectra and count rate characteristics of a clinical gamma camera system using a cylindrical phantom filled with a Lu-177 solution. Lead sheets of 1.0- and 0.5-mm thicknesses were used as thin shields, and the dead-time losses in tumour imaging with consumed Lu-177 were simulated.

RESULTS

The apparent dead times with lead sheets of 1.0- and 0.5-mm thicknesses and without a lead sheet were 1.7, 1.9, and 5.8 µs for an energy window of 208 keV ± 10 %, respectively. The dead-time losses could be reduced from 10 % to 1.3 % using the 1.0-mm thick lead sheet in the simulated imaging of tumour.

CONCLUSION

Our method is promising in clinical situations and studies on Lu-177 dosimetry for tumours.

Application of Artificial Intelligence in Oncologic Molecular PET-Imaging: A Narrative Review on Beyond [18F]F-FDG Tracers Part II. [18F]F-FLT, [18F]F-FET, [11C]C-MET and Other Less-Commonly Used Radiotracers

Following the previous part of the narrative review on artificial intelligence (AI) applications in positron emission tomography (PET) using tracers rather than 18F-fluorodeoxyglucose ([18F]F-FDG), in this part we review the impact of PET-derived radiomics data on the diagnostic performance of other PET radiotracers, 18F-O-(2-fluoroethyl)-L-tyrosine ([18F]F-FET), 18F-Fluorothymidine ([18F]F-FLT) and 11C-Methionine ([11C]C-MET). [18F]F-FET-PET, using an artificial amino acid taken up into upregulated tumoral cells, showed potential in lesion detection and tumor characterization, especially with its ability to reflect glioma heterogeneity. [18F]F-FET-PET-derived textural features appeared to have the potential to reveal considerable information for accurate delineation for guiding biopsy and treatment, differentiate between low-grade and high-grade glioma and related wild-type genotypes, and distinguish pseudoprogression from true progression. In addition, models built using clinical parameters and [18F]F-FET-PET-derived radiomics features showed acceptable results for survival stratification of glioblastoma patients. [18F]F-FLT-PET-based characteristics also showed potential in evaluating glioma patients, correlating with Ki-67 and patient prognosis. AI-based PET-volumetry using this radiotracer as a proliferation marker also revealed promising preliminary results in terms of guide-targeting bone marrow-preserving adaptive radiation therapy. Similar to [18F]F-FET, the other amino acid tracer which reflects cellular proliferation, [11C]C-MET, has also shown acceptable performance in predicting tumor grade, distinguishing brain tumor recurrence from radiation necrosis, and treatment monitoring by PET-derived radiomics models. In addition, PET-derived radiomics features of various radiotracers such as [18F]F-DOPA, [18F]F-FACBC, [18F]F-NaF, [68Ga]Ga-CXCR-4 and [18F]F-FMISO may also provide useful information for tumor characterization and predict of disease outcome. In conclusion, AI using tracers beyond [18F]F-FDG could improve the diagnostic performance of PET-imaging for specific indications and help clinicians in their daily routine by providing features that are often not detectable by the naked eye.

Full-length radiograph based automatic musculoskeletal modeling using convolutional neural network

Full-length radiographs contain information from which many anatomical parameters of the pelvis, femur, and tibia may be derived, but only a few anatomical parameters are used for musculoskeletal modeling. This study aimed to develop a fully automatic algorithm to extract anatomical parameters from full-length radiograph to generate a musculoskeletal model that is more accurate than linear scaled one. A U-Net convolutional neural network was trained to segment the pelvis, femur, and tibia from the full-length radiograph. Eight anatomic parameters (six for length and width, two for angles) were automatically extracted from the bone segmentation masks and used to generate the musculoskeletal model. Sørensen-Dice coefficient was used to quantify the consistency of automatic bone segmentation masks with manually segmented labels. Maximum distance error, root mean square (RMS) distance error and Jaccard index (JI) were used to evaluate the geometric accuracy of the automatically generated pelvis, femur and tibia models versus CT bone models. Mean Sørensen-Dice coefficients for the pelvis, femur and tibia 2D segmentation masks were 0.9898, 0.9822 and 0.9786, respectively. The algorithm-driven bone models were closer to the 3D CT bone models than the scaled generic models in geometry, with significantly lower maximum distance error (28.3 % average decrease from 24.35 mm) and RMS distance error (28.9 % average decrease from 9.55 mm) and higher JI (17.2 % average increase from 0.46) (P < 0.001). The algorithm-driven musculoskeletal modeling (107.15 ± 10.24 s) was faster than the manual process (870.07 ± 44.79 s) for the same full-length radiograph. This algorithm provides a fully automatic way to generate a musculoskeletal model from full-length radiograph that achieves an approximately 30 % reduction in distance errors, which could enable personalized musculoskeletal simulation based on full-length radiograph for large scale OA populations.

The assessment of the clinical impact of using a single set of radiotherapy planning data for two kilovoltage therapy units

Kilovoltage therapy units are used for superficial radiotherapy treatment delivery. Peer reviewed studies for MV linear accelerators describe tolerances to dosimetrically match multiple linear accelerators enabling patient treatment on any matched machine. There is an absence of literature on using a single planning data set for multiple kilovoltage units which have limited ability for beam adjustment. This study reviewed kilovoltage dosimetry and treatment planning scenarios to evaluate the feasibility of using ACPSEM annual QA tolerances to determine whether two units (of the same make and model) were dosimetrically matched. The dosimetric characteristics, such as measured half value layer (HVL), percentage depth dose (PDD), applicator factor and output variation with stand-off distance for each kV unit were compared to assess the agreement. Independent planning data based on the measured HVL for each beam energy from each kV unit was prepared. Monitor unit (MU) calculations were performed using both sets of planning data for approximately 200 clinical scenarios and compared with an overall agreement between units of < 2%. Additionally, a dosimetry measurement comparison was completed at each site for a subset of nine scenarios. All machine characterisation measurements were within the ACPSEM Annual QA tolerances, and dosimetric testing was within 2.5%. This work demonstrates that using a single set of planning data for two kilovoltage units is feasible, resulting in a clinical impact within published uncertainty.