Domain-Specific Processing Stage for Estimating Single-Trail Evoked Potential Improves CNN Performance in Detecting Error Potential.

We present a novel architecture designed to enhance the detection of Error Potential (ErrP) signals during ErrP stimulation tasks. In the context of predicting ErrP presence, conventional Convolutional Neural Networks (CNNs) typically accept a raw EEG signal as input, encompassing both the information associated with the evoked potential and the background activity, which can potentially diminish predictive accuracy. Our approach involves advanced Single-Trial (ST) ErrP enhancement techniques for processing raw EEG signals in the initial stage, followed by CNNs for discerning between ErrP and NonErrP segments in the second stage. We tested different combinations of methods and CNNs. As far as ST ErrP estimation is concerned, we examined various methods encompassing subspace regularization techniques, Continuous Wavelet Transform, and ARX models. For the classification stage, we evaluated the performance of EEGNet, CNN, and a Siamese Neural Network. A comparative analysis against the method of directly applying CNNs to raw EEG signals revealed the advantages of our architecture. Leveraging subspace regularization yielded the best improvement in classification metrics, at up to 14% in balanced accuracy and 13.4% in F1-score.

Relevance of apparent diffusion coefficient features for a radiomics-based prediction of response to induction chemotherapy in sinonasal cancer.

In this paper, several radiomics-based predictive models of response to induction chemotherapy (IC) in sinonasal cancers (SNCs) are built and tested. Models were built as a combination of radiomic features extracted from three types of MRI images: T1-weighted images, T2-weighted images and apparent diffusion coefficient (ADC) maps. Fifty patients (aged 54 ± 12 years, 41 men) were included in this study. Patients were classified according to their response to IC (25 responders and 25 nonresponders). Not all types of images were acquired for all of the patients: 49 had T1-weighted images, 50 had T2-weighted images and 34 had ADC maps. Only in a subset of 33 patients were all three types of image acquired. Eighty-nine radiomic features were extracted from the MRI images. Dimensionality reduction was performed by using principal component analysis (PCA) and by selecting only the three main components. Different algorithms (trees ensemble, K-nearest neighbors, support vector machine, naïve Bayes) were used to classify the patients as either responders or nonresponders. Several radiomic models (either monomodality or multimodality obtained by a combination of T1-weighted, T2-weighted and ADC images) were developed and the performance was assessed through 100 iterations of train and test split. The area under the curve (AUC) of the models ranged from 0.56 to 0.78. Trees ensemble, support vector machine and naïve Bayes performed similarly, but in all cases ADC-based models performed better. Trees ensemble gave the highest AUC (0.78 for the T1-weighted+T2-weighted+ADC model) and was used for further analyses. For trees ensemble, the models based on ADC features performed better than those models that did not use those features (P < 0.02 for one-tail Hanley test, AUC range 0.68-0.78 vs 0.56-0.69) except the T1-weighted+ADC model (AUC 0.71 vs 0.69, nonsignificant differences). The results suggest the relevance of ADC-based radiomics for prediction of response to IC in SNCs.

Identification of Characteristic Points in Multivariate Physiological Signals by Sensor Fusion and Multi-Task Deep Networks.

Identification of characteristic points in physiological signals, such as the peak of the R wave in the electrocardiogram and the peak of the systolic wave of the photopletismogram, is a fundamental step for the quantification of clinical parameters, such as the pulse transit time. In this work, we presented a novel neural architecture, called eMTUnet, to automate point identification in multivariate signals acquired with a chest-worn device. The eMTUnet consists of a single deep network capable of performing three tasks simultaneously: (i) localization in time of characteristic points (labeling task), (ii) evaluation of the quality of signals (classification task); (iii) estimation of the reliability of classification (reliability task). Preliminary results in overnight monitoring showcased the ability to detect characteristic points in the four signals with a recall index of about 1.00, 0.90, 0.90, and 0.80, respectively. The accuracy of the signal quality classification was about 0.90, on average over four different classes. The average confidence of the correctly classified signals, against the misclassifications, was 0.93 vs. 0.52, proving the worthiness of the confidence index, which may better qualify the point identification. From the achieved outcomes, we point out that high-quality segmentation and classification are both ensured, which brings the use of a multi-modal framework, composed of wearable sensors and artificial intelligence, incrementally closer to clinical translation.

Diffusion-weighted MRI radiomics of spine bone tumors: feature stability and machine learning-based classification performance.

PURPOSE: To evaluate stability and machine learning-based classification performance of radiomic features of spine bone tumors using diffusion- and T2-weighted magnetic resonance imaging (MRI). MATERIAL AND METHODS: This retrospective study included 101 patients with histology-proven spine bone tumor (22 benign; 38 primary malignant; 41 metastatic). All tumor volumes were manually segmented on morphologic T2-weighted sequences. The same region of interest (ROI) was used to perform radiomic analysis on ADC map. A total of 1702 radiomic features was considered. Feature stability was assessed through small geometrical transformations of the ROIs mimicking multiple manual delineations. Intraclass correlation coefficient (ICC) quantified feature stability. Feature selection consisted of stability-based (ICC > 0.75) and significance-based selections (ranking features by decreasing Mann-Whitney p-value). Class balancing was performed to oversample the minority (i.e., benign) class. Selected features were used to train and test a support vector machine (SVM) to discriminate benign from malignant spine tumors using tenfold cross-validation. RESULTS: A total of 76.4% radiomic features were stable. The quality metrics for the SVM were evaluated as a function of the number of selected features. The radiomic model with the best performance and the lowest number of features for classifying tumor types included 8 features. The metrics were 78% sensitivity, 68% specificity, 76% accuracy and AUC 0.78. CONCLUSION: SVM classifiers based on radiomic features extracted from T2- and diffusion-weighted imaging with ADC map are promising for classification of spine bone tumors. Radiomic features of spine bone tumors show good reproducibility rates.

Distributed learning: a reliable privacy-preserving strategy to change multicenter collaborations using AI.

PURPOSE: The present scoping review aims to assess the non-inferiority of distributed learning over centrally and locally trained machine learning (ML) models in medical applications. METHODS: We performed a literature search using the term "distributed learning" OR "federated learning" in the PubMed/MEDLINE and EMBASE databases. No start date limit was used, and the search was extended until July 21, 2020. We excluded articles outside the field of interest; guidelines or expert opinion, review articles and meta-analyses, editorials, letters or commentaries, and conference abstracts; articles not in the English language; and studies not using medical data. Selected studies were classified and analysed according to their aim(s). RESULTS: We included 26 papers aimed at predicting one or more outcomes: namely risk, diagnosis, prognosis, and treatment side effect/adverse drug reaction. Distributed learning was compared to centralized or localized training in 21/26 and 14/26 selected papers, respectively. Regardless of the aim, the type of input, the method, and the classifier, distributed learning performed close to centralized training, but two experiments focused on diagnosis. In all but 2 cases, distributed learning outperformed locally trained models. CONCLUSION: Distributed learning resulted in a reliable strategy for model development; indeed, it performed equally to models trained on centralized datasets. Sensitive data can get preserved since they are not shared for model development. Distributed learning constitutes a promising solution for ML-based research and practice since large, diverse datasets are crucial for success.

Prognostic role of pre-treatment magnetic resonance imaging (MRI)-based radiomic analysis in effectively cured head and neck squamous cell carcinoma (HNSCC) patients.

OBJECTIVES: To identify and validate baseline magnetic resonance imaging (b-MRI) radiomic features (RFs) as predictors of disease outcomes in effectively cured head and neck squamous cell carcinoma (HNSCC) patients. MATERIALS AND METHODS: Training set (TS) and validation set (VS) were retrieved from preexisting datasets (HETeCo and BD2Decide trials, respectively). Only patients with both pre- and post-contrast enhancement T1 and T2-weighted b-MRI and at least 2 years of follow-up (FUP) were selected. The combination of the best extracted RFs was used to classify low risk (LR) vs. high risk (HR) of disease recurrence. Sensitivity, specificity, and area under the curve (AUC) of the radiomic model were computed on both TS and VS. Overall survival (OS) and 5-year disease-free survival (DFS) Kaplan-Meier (KM) curves were compared for LR vs. HR. The radiomic-based risk class was used in a multivariate Cox model, including well-established clinical prognostic factors (TNM, sub-site, human papillomavirus [HPV]). RESULTS: In total, 57 patients of TS and 137 of VS were included. Three RFs were selected for the signature. Sensitivity of recurrence risk classifier was 0.82 and 0.77, specificity 0.78 and 0.81, AUC 0.83 and 0.78 for TS and VS, respectively. VS KM curves for LR vs. HR groups significantly differed both for 5-year DFS (p<.0001) and OS (p=.0004). A combined model of RFs plus TNM improved prognostic performance as compared to TNM alone, both for VS 5-year DFS (C-index: 0.76 vs. 0.60) and OS (C-index: 0.74 vs. 0.64). CONCLUSIONS: Radiomics of b-MRI can help to predict recurrence and survival outcomes in HNSCC.

Radiomic analysis of soft tissues sarcomas can distinguish intermediate from high-grade lesions.

PURPOSE: To assess the feasibility of grading soft tissue sarcomas (STSs) using MRI features (radiomics). MATERIALS AND METHODS: MRI (echo planar SE, 1.5T) from 19 patients with STSs and a known histological grading, were retrospectively analyzed. The apparent diffusion coefficient (ADC) maps, obtained by diffusion-weighted imaging acquisitions, were analyzed through 65 radiomic features, intensity-based (first order statistics, FOS) and texture (gray level co-occurrence matrix, GLCM; and gray level run length matrix, GLRLM) features. Feature selection (sequential forward floating search) and classification (k-nearest neighbor classifier) were performed to distinguish intermediate- from high-grade STSs. Classification was performed using the three different sub-groups of features separately as well as all the features together. The entire dataset was divided in three subsets: the training, validation and test set, containing, respectively, 60, 30, and 10% of the data. RESULTS: Intermediate-grade lesions had a higher and less disperse ADC values compared with high-grade ones: most of FOS related to intensity are higher for the intermediate-grade STSs, while FOS related to signal variability were higher in the high grade (e.g., the feature variance is 2.6*105 ± 0.9*105 versus 3.3*105 ± 1.6*105 , P = 0.3). The GLCM features related to entropy and dissimilarity were higher in the high-grade. When performing classification, the best accuracy is obtained with a maximum of three features for each subgroup, FOS features being those leading to the best classification (validation set: FOS accuracy 0.90 ± 0.11, area under the curve [AUC] 0.85 ± 0.16; test set: FOS accuracy 0.88 ± 0.25, AUC 0.87 ± 0.34). CONCLUSION: Good accuracy and AUC could be obtained using only few Radiomic features, belonging to the FOS class. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:829-840.

Big Data in Head and Neck Cancer.

OPINION STATEMENT: Head and neck cancers can be used as a paradigm for exploring "big data" applications in oncology. Computational strategies derived from big data science hold the promise of shedding new light on the molecular mechanisms driving head and neck cancer pathogenesis, identifying new prognostic and predictive factors, and discovering potential therapeutics against this highly complex disease. Big data strategies integrate robust data input, from radiomics, genomics, and clinical-epidemiological data to deeply describe head and neck cancer characteristics. Thus, big data may advance research generating new knowledge and improve head and neck cancer prognosis supporting clinical decision-making and development of treatment recommendations.

Assessment of Stability and Discrimination Capacity of Radiomic Features on Apparent Diffusion Coefficient Images.

The objectives of the study are to develop a new way to assess stability and discrimination capacity of radiomic features without the need of test-retest or multiple delineations and to use information obtained to perform a preliminary feature selection. Apparent diffusion coefficient (ADC) maps were computed from diffusion-weighted magnetic resonance images (DW-MRI) of two groups of patients: 18 with soft tissue sarcomas (STS) and 18 with oropharyngeal cancers (OPC). Sixty-nine radiomic features were computed, using three different histogram discretizations (16, 32, and 64 bins). Geometrical transformations (translations) of increasing entity were applied to the regions of interest (ROIs), and the intra-class correlation coefficient (ICC) was used to compare the features computed on the original and modified ROIs. The distribution of ICC values for minimal and maximal entity translations (ICC10 and ICC100, respectively) was used to adjust thresholds of ICC (ICCmin and ICCmax) used to discriminate between good, unstable (ICC10 < ICCmin), and non-discriminative features (ICC100 > ICCmax). Fifty-four and 59 radiomic features passed the stability-based selection for all the three histogram discretizations for the OPC and STS datasets, respectively. The excluded features were similar across the different histogram discretizations (Jaccard's index 0.77 ± 0.13 and 0.9 ± 0.1 for OPC and STS, respectively) but different between datasets (Jaccard's index 0.19 ± 0.02). The results suggest that the observed radiomic features are mainly stable and discriminative, but the stability depends on the region of the body under observation. The method provides a way to assess stability without the need of test-retest or multiple delineations.

Contrast mechanisms associated with neuromelanin-MRI.

PURPOSE: To investigate the physical mechanisms associated with the contrast observed in neuromelanin MRI. METHODS: Phantoms having different concentrations of synthetic melanins with different degrees of iron loading were examined on a 3 Tesla scanner using relaxometry and quantitative magnetization transfer (MT). RESULTS: Concentration-dependent T1 and T2 shortening was most pronounced for the melanin pigment when combined with iron. Metal-free melanin had a negligible effect on the magnetization transfer spectra. On the contrary, the presence of iron-laden melanins resulted in a decreased magnetization transfer ratio. The presence of melanin or iron (or both) did not have a significant effect on the macromolecular content, represented by the pool size ratio. CONCLUSION: The primary mechanism underlying contrast in neuromelanin-MRI appears to be the T1 reduction associated with melanin-iron complexes. The macromolecular content is not significantly influenced by the presence of melanin with or without iron, and thus the MT is not directly affected. However, as T1 plays a role in determining the MT-weighted signal, the magnetization transfer ratio is reduced in the presence of melanin-iron complexes. Magn Reson Med 78:1790-1800, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Pool size ratio of the substantia nigra in Parkinson's disease derived from two different quantitative magnetization transfer approaches.

PURPOSE: We sought to measure quantitative magnetization transfer (qMT) properties of the substantia nigra pars compacta (SNc) in patients with Parkinson's disease (PD) and healthy controls (HCs) using a full qMT analysis and determine whether a rapid single-point measurement yields equivalent results for pool size ratio (PSR). METHODS: Sixteen different MT-prepared MRI scans were obtained at 3 T from 16 PD patients and eight HCs, along with B1, B0, and relaxation time maps. Maps of PSR, free and macromolecular pool transverse relaxation times ([Formula: see text], [Formula: see text]) and rate of MT exchange between pools (k mf ) were generated using a full qMT model. PSR maps were also generated using a single-point qMT model requiring just two MT-prepared images. qMT parameter values of the SNc, red nucleus, cerebral crus, and gray matter were compared between groups and methods. RESULTS: PSR of the SNc was the only qMT parameter to differ significantly between groups (p < 0.05). PSR measured via single-point analysis was less variable than with the full MT model, provided slightly better differentiation of PD patients from HCs (area under curve 0.77 vs. 0.75) with sensitivity of 0.75 and specificity of 0.87, and was better than transverse relaxation time in distinguishing PD patients from HCs (area under curve 0.71, sensitivity 0.87, and specificity 0.50). CONCLUSION: The increased PSR observed in the SNc of PD patients may provide a novel biomarker of PD, possibly associated with an increased macromolecular content. Single-point PSR mapping with reduced variability and shorter scan times relative to the full qMT model appears clinically feasible.

Rate-control drugs affect variability and irregularity measures of RR intervals in patients with permanent atrial fibrillation.

INTRODUCTION: Irregularity measures have been suggested as risk indicators in patients with atrial fibrillation (AF); however, it is not known to what extent they are affected by commonly used rate-control drugs. We aimed at evaluating the effect of metoprolol, carvedilol, diltiazem, and verapamil on the variability and irregularity of the ventricular response in patients with permanent AF. METHODS AND RESULTS: Sixty patients with permanent AF were part of an investigator-blind cross-over study, comparing 4 rate-control drugs (diltiazem, verapamil, metoprolol, and carvedilol). We analyzed five 20-minute segments per patient: baseline and the 4 drug regimens. On every segment, heart rate (HR) variability and irregularity of RR series were computed. The variability was assessed as standard deviation, pNN20, pNN50, pNN80, and rMSSD. The irregularity was assessed by regularity index, approximate (ApEn), and sample entropy. A significantly lower HR was obtained with all drugs, the HR was lowest using the calcium channel blockers. All drugs increased the variability of ventricular response in respect to baseline (as an example, rMSSD: baseline 171 ± 47 milliseconds, carvedilol 229 ± 58 milliseconds; P < 0.05 vs. baseline, metoprolol 226 ± 66 milliseconds; P < 0.05 vs. baseline, verapamil 228 ± 84; P < 0.05 vs. baseline, diltiazem 256 ± 87 milliseconds; P < 0.05 vs. baseline and all other drugs). Only ß-blockers significantly increased the irregularity of the RR series (as an example, ApEn: baseline 1.86 ± 0.13, carvedilol 1.92 ± 0.09; P < 0.05 vs. baseline, metoprolol 1.93 ± 0.08; P < 0.05 vs. baseline, verapamil 1.86 ± 0.22 ns, diltiazem 1.88 ± 0.16 ns). CONCLUSION: Modification of AV node conduction by rate-control drugs increase RR variability, while only ß-blockers affect irregularity.

Noninvasive Assessment of Atrioventricular Nodal Function: Effect of Rate-Control Drugs during Atrial Fibrillation.

BACKGROUND: During atrial fibrillation (AF), conventional electrophysiological techniques for assessment of refractory period or conduction velocity of the atrioventricular (AV) node cannot be used. We aimed at evaluating changes in AV nodal properties during administration of tecadenoson and esmolol using a novel ECG-based method. METHODS: Fourteen patients (age 58 ± 8 years, 10 men) with AF were randomly assigned to either 75 or 300 µg intravenous tecadenoson. After tecadenoson wash-out, patients received esmolol continuously (100 µg/kg per min for 10 mins, then 50 µg/kg per min for 50 mins). Atrial fibrillatory rate (AFR) and heart rate (HR) were assessed in 15-min segments. Using the novel method, we assessed the absolute refractory periods of the slow and fast pathways (aRPs and aRPf) of the AV node to produce an estimate of the functional refractory period. RESULTS: During esmolol infusion, AFR and HR were significantly decreased and the absolute refractory period was significantly prolonged in both pathways (aRPs: 387 ± 73 vs 409 ± 62 ms, P < 0.05; aRPf: 490 ± 80 vs 529 ± 58 ms, P < 0.05). During both tecadenoson doses, HR decreased significantly and AFR was unchanged. Both aRPs and aRPf were prolonged for a 75 µg dose (aRPs: 322 ± 97 vs 476 ± 75 ms, P < 0.05; aRPf: 456 ± 102 vs 512 ± 55 ms, P < 0.05) whereas a trend toward prolongation was observed for a 300 µg dose. CONCLUSIONS: The estimated parameters reflect expected changes in AV nodal properties, i.e., slower conduction through the AV node for tecadenoson and prolongation of the AV node refractory period for esmolol. Thus, the proposed approach may be used to assess drug effects on the AV node in AF patients.

Noninvasive characterization of atrioventricular conduction in patients with atrial fibrillation.

The atrioventricular (AV) node plays a fundamental role in patients with atrial fibrillation (AF), acting as a filter to the numerous irregular atrial impulses which bombard the node. A phenomenological approach to better understand AV nodal electrophysiology is to analyze the ventricular response with respect to irregularity. In different cohorts of AF patients, such analysis has been performed with the aim to evaluate the association between ventricular response characteristics and long-term clinical outcome and to determine whether irregularity is affected by rate-control drugs. Another approach to studying AV nodal characteristics is to employ a mathematical model which accounts for the refractory periods of the two AV nodal pathways. With atrial fibrillatory rate and RR intervals as input, the model has been considered for analyzing data during (i) rest and head-up tilt test, (ii) tecadenoson and esmolol, and (iii) rate-control drugs. The present paper provides an overview of our recent work on the characterization and assessment of AV nodal conduction using these two approaches.

Non-invasive assessment of the effect of beta blockers and calcium channel blockers on the AV node during permanent atrial fibrillation.

AIM: We aimed at assessing changes in AV nodal properties during administration of the beta blockers metoprolol and carvedilol, and the calcium channel blockers diltiazem and verapamil from electrocardiographic data. METHODS: Parameters accounting for the functional refractory periods of the slow and fast pathways (aRPs and aRPf) were estimated using atrial fibrillatory rate (AFR) and ventricular response assessed from 15-min ECG segments recorded at baseline and on drug treatment from sixty patients with permanent AF. RESULTS: The results showed that AFR and HR were significantly reduced for all drugs, and that aRPs and aRPf were significantly prolonged in both pathways. The prolongation in aRP was significantly larger for the calcium channel blockers than for the beta blockers. CONCLUSIONS: The changes observed in the AV node parameters are in line with the results of previous electrophysiological studies performed in patients during sinus rhythm, therefore supporting the clinical value of the method.

Electrophysiological Investigations of Shape and Reproducibility of Oropharyngeal Swallowing: Interaction with Bolus Volume and Age.

Electrophysiological assessment provides valuable information on physiological and pathophysiological characteristics of human swallowing. Here, new electrophysiological measures for the evaluation of oropharyngeal swallowing were assessed: (1) the activation pattern of the submental/suprahyoid EMG activity (SHEMG); (2) the reproducibility of the oral and pharyngeal phases of swallowing, by calculating the similarity index (SI) of the SHEMG (SI-SHEMG) and of the laryngeal-pharyngeal mechanogram (SI-LPM) during repeated swallows; and (3) kinesiological measures related to the LPM. An electrophysiological-mechanical method for measuring the activation pattern of the SHEMG, the SI-SHEMG, and the SI-LPM, and maximal LPM velocity and acceleration during swallowing was applied in 65 healthy subjects divided into three age groups (18-39, 40-59, 60 years or over). All the measures were assessed during three trials of eight consecutive swallows of different liquid bolus volumes (3, 12, and 20 ml). A high overall reproducibility of oropharyngeal swallowing in healthy humans was recorded. However, while values of SI-SHEMG were similar in all the age groups, the SI-LPM was found to fall significantly in the older age group. Both the SI-SHEMG and the SI-LPM were found to fall with increasing bolus volumes. The activation pattern of the SHEMG and the LPM kinesiological measures were differently modified by bolus volume and age in the older subjects with respect to the others. We describe a new approach to the electrophysiological study of swallowing based on computed semi-automatic analyses. Our findings provide insight into some previously uninvestigated aspects of oropharyngeal swallowing physiology, considered in relation to bolus volume and age. The new electrophysiological measures here described could prove useful in the clinical setting, as it is likely that they could be differently affected in patients with different kinds of dysphagia.

Beta-blockade and A1-adenosine receptor agonist effects on atrial fibrillatory rate and atrioventricular conduction in patients with atrial fibrillation.

AIMS: Reduced irregularity of RR intervals in permanent atrial fibrillation (AF) has been associated with poor outcome. It is not fully understood, however, whether modification of atrioventricular (AV) conduction using rate-control drugs affects RR variability and irregularity measures. We aimed at assessing whether atrial fibrillatory rate (AFR) and variability and irregularity of the ventricular rate are modified by a selective A1-adenosine receptor agonist tecadenoson, beta-blocker esmolol, and their combination. METHODS AND RESULTS: Twenty-one patients (age 58 ± 7 years, 13 men) with AF were randomly assigned to either 75, 150, or 300 µg intravenous tecadenoson. Tecadenoson was administered alone (Dose Period 1) and in combination (Dose Period 2) with esmolol (100 µg/kg/min for 10 min then 50 µg/kg/min for 50 min). Heart rate (HR) and AFR were estimated for every 10 min long recording segment. Similarly, for every 10 min segment, the variability of RR intervals was assessed, as standard deviation, pNN20, pNN50, pNN80, and the root of the mean squared differences of successive RR intervals, and irregularity was assessed by non-linear measures such as regularity index (R) and approximate entropy. A marked decrease in HR was observed after both tecadenoson injections, whereas almost no changes could be seen in the AFR. The variability parameters were increased after the first tecadenoson bolus injection. In contrast, the irregularity parameters did not change after tecadenoson. When esmolol was infused, all the variability parameters further increased. CONCLUSION: Modification of AV node conduction can increase RR variability but does not affect regularity of RR intervals or AFR.

Non-invasive evaluation of the effect of metoprolol on the atrioventricular node during permanent atrial fibrillation.

AIMS: During atrial fibrillation (AF), conventional electrophysiological techniques for assessment of refractory period or conduction velocity of the atrioventricular (AV) node cannot be used. We aimed at evaluating changes in AV nodal properties during administration of metoprolol from electrocardiogram data, and to support our findings with simulated data based on results from an electrophysiological study. METHODS AND RESULTS: Sixty patients (age 71 ± 9 years, 42 men) with permanent AF were included in the RATe control in Atrial Fibrillation (RATAF) study. Two 15 min segments, during baseline and metoprolol administration, starting at 2 pm were analysed in this study. Atrial fibrillatory rate (AFR), heart rate (HR), and AV nodal parameters were assessed. The AV nodal parameters account for the probability of an impulse not taking the fast pathway, the absolute refractory periods of the slow and fast pathways (aRPs and aRPf), representing the functional refractory period, and their respective prolongation in refractory period. In addition, simulated RR series were generated that mimic metoprolol administration through prolonged AV conduction interval and AV node effective refractory period. During metoprolol administration, AFR and HR were significantly decreased and aRP was significantly prolonged in both pathways (aRPs: 337 ± 60 vs. 398 ± 79 ms, P < 0.01; aRPf: 430 ± 91 vs. 517 ± 100 ms, P < 0.01). Similar results were found for the simulated RR series, both aRPs and aRPf being prolonged with metoprolol (aRPs: 413 ± 33 vs. 437 ± 43 ms, P = 0.01; aRPf: 465 ± 40 vs. 502 ± 69 ms, P = 0.02). CONCLUSION: The AV nodal parameters reflect expected changes after metoprolol administration, i.e. a prolongation in functional refractory period. The simulations confirmed that aRPs and aRPf may serve as an estimate of the functional refractory period.

Feasibility of proton dosimetry overriding planning CT with daily CBCT elaborated through generative artificial intelligence tools.

Radiotherapy commonly utilizes cone beam computed tomography (CBCT) for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into Hounsfield Units (HU) values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow field of view (FOV) systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent generative adversarial networks (cGAN) processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm's ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT (pCT) and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2 mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.

Comparative Assessment of Physiological Responses to Emotional Elicitation by Auditory and Visual Stimuli.

The study of emotions through the analysis of the induced physiological responses gained increasing interest in the past decades. Emotion-related studies usually employ films or video clips, but these stimuli do not give the possibility to properly separate and assess the emotional content provided by sight or hearing in terms of physiological responses. In this study we have devised an experimental protocol to elicit emotions by using, separately and jointly, pictures and sounds from the widely used International Affective Pictures System and International Affective Digital Sounds databases. We processed galvanic skin response, electrocardiogram, blood volume pulse, pupillary signal and electroencephalogram from 21 subjects to extract both autonomic and central nervous system indices to assess physiological responses in relation to three types of stimulation: auditory, visual, and auditory/visual. Results show a higher galvanic skin response to sounds compared to images. Electrocardiogram and blood volume pulse show different trends between auditory and visual stimuli. The electroencephalographic signal reveals a greater attention paid by the subjects when listening to sounds compared to watching images. In conclusion, these results suggest that emotional responses increase during auditory stimulation at both central and peripheral levels, demonstrating the importance of sounds for emotion recognition experiments and also opening the possibility toward the extension of auditory stimuli in other fields of psychophysiology. Clinical and Translational Impact Statement- These findings corroborate auditory stimuli's importance in eliciting emotions, supporting their use in studying affective responses, e.g., mood disorder diagnosis, human-machine interaction, and emotional perception in pathology.