Accurate phase extraction from sinusoidal signals is a crucial task in various signal processing applications. While prior research predominantly addresses the case of asynchronous sampling with unknown signal frequency, this study focuses on the more specific situation where synchronous sampling is possible, and the signal's frequency is known. In this framework, a comprehensive analysis of phase estimation accuracy in the presence of both additive and phase noises is presented. A closed-form expression for the asymptotic Probability Density Function (PDF) of the resulting phase is asymptotically efficient, converging rapidly to its Cram & egrave;r-Rao identified based on SNR, sample count (N), and noise level: (i) (SNR), (ii) linear decrease with the square roots of N and SNR at the impact of sample count, additive noise, and phase noise on phase estimation accuracy, this work provides valuable insights for designing systems requiring precise phase extraction, such as phase-based fluorescence assays or system identification.

AbstractPurposeTo evaluate deep learning (DL)‐based deformable image registration (DIR) for dose accumulation during radiotherapy of prostate cancer patients.Methods and MaterialsData including 341 CBCTs (209 daily, 132 weekly) and 23 planning CTs from 23 patients was retrospectively analyzed. Anatomical deformation during treatment was estimated using free‐form deformation (FFD) method from Elastix and DL‐based VoxelMorph approaches. The VoxelMorph method was investigated using anatomical scans (VMorph_Sc) or label images (VMorph_Msk), or the combination of both (VMorph_Sc_Msk). Accumulated doses were compared with the planning dose.ResultsThe DSC ranges, averaged for prostate, rectum and bladder, were 0.60–0.71, 0.67–0.79, 0.93–0.98, and 0.89–0.96 for the FFD, VMorph_Sc, VMorph_Msk, and VMorph_Sc_Msk methods, respectively. When including both anatomical and label images, VoxelMorph estimated more complex deformations resulting in heterogeneous determinant of Jacobian and higher percentage of deformation vector field (DVF) folding (up to a mean value of 1.90% in the prostate). Large differences were observed between DL‐based methods regarding estimation of the accumulated dose, showing systematic overdosage and underdosage of the bladder and rectum, respectively. The difference between planned mean dose and accumulated mean dose with VMorph_Sc_Msk reached a median value of +6.3 Gy for the bladder and −5.1 Gy for the rectum.ConclusionThe estimation of the deformations using DL‐based approach is feasible for male pelvic anatomy but requires the inclusion of anatomical contours to improve organ correspondence. High variability in the estimation of the accumulated dose depending on the deformable strategy suggests further investigation of DL‐based techniques before clinical deployment.

Une récente étude portant sur près de quatre millions de patients atteints de BPCO a révélé que le taux de réadmission toutes causes confondues à 30 jours variait de 9 à 26 % [1]. De nouvelles approches pour prévenir les réadmissions sont nécessaires pour aider à atténuer le risque. L’étude interventionnelle prospective et multicentrique DACRE collecte en vie réelle les signes vitaux de patients BPCO à partir de leur hospitalisation pour exacerbation sévère et jusqu’à 30 jours après leur sortie. L’analyse de ces signes vitaux a pour but d’en comprendre l’évolution afin de prévenir une réadmission. Au total, 21 patients ont été équipés du dispositif médical de télésurveillance Bora Care lors d’une hospitalisation pour une exacerbation sévère de BPCO. Les signes vitaux (fréquence cardiaque, fréquence respiratoire et saturation en oxygène) ainsi que le niveau d’activité des patients sont mesurés en vie réelle durant l’hospitalisation puis pendant 30 jours après le retour à domicile. Au total, 21 patients BPCO (9,5 % stade 1, 19 % stade 2,3 % stade 3,2 % stade 4) âgés de 52 à 86 ans (moyenne 67 ans) ont été télésurveillés sur une durée variant de 21 à 61 jours (moyenne : 37 jours) (Tableau 1). Le sex-ratio est 4 : 3 (12H, 9F). Afin de collecter le taux de saturation en oxygène, la fréquence respiratoire, la fréquence cardiaque et l’activité, les patients ont porté le bracelet connecté Bora Band 87 % du temps (valeur médiane, écart-type 11 %). Durant l’étude, 5 patients (23,8 %) ont été réadmis au bout de 3 à 27 jours (15 jours en moyenne). Un test statistique a été effectué pour évaluer la dépendance des signes vitaux mesurés dans l’étude avec une réadmission à 30 jours. L’intensité de la dépendance a été calculée pour classer les paramètres, de 0 (pas du tout dépendant) à 1 (très dépendant). En synthèse, le taux de variation de la fréquence respiratoire (p-valeur = 0,01 ; coefficient de corrélation = 0,61) est le marqueur prépondérant des patients réadmis. Viennent ensuite le taux de variation de la fréquence cardiaque, puis le taux de variation de la saturation en oxygène. Les données de l’étude permettent d’identifier et de hiérarchiser les signes vitaux des patients BPCO télésurveillés et ayant été réadmis à 30 jours. La poursuite des inclusions devrait permettre d’atteindre une puissance statistique plus importante pour confirmer ces premières observations.

Introduction: After hospital discharge following an acute exacerbation of COPD (AECOPD), remote patient monitoring (RPM) can prevent readmissions [1] by alerting healthcare professionals when vital signs exceed some limits. Objectives: Compare the performance of different vital signs alert configurations in early detection of readmission. Methods: Breath rate (BR), heart rate (HR) and SpO2 of COPD patients were monitored by Bora Care RPM solution during hospitalization for AECOPD and 30 days after discharge. Results: 21 COPD patients (GOLD grade: 9.5% I, 19% II, 33% III, 24% IV; mean age 67 years) were monitored for an average session duration of 37 days (SD 11 days), 5 patients (23.8%) were readmitted. The area under the curve (AUC) of the Receiver Operating Characteristic curve (ROC) was computed to rank the performance of several alert rules on 1) fixed thresholds and 2) variable thresholds based on deviation of the last 48-hour median value from a 15-day baseline. The variable threshold applied simultaneously to SpO2, HR and BR is the best performing alert (AUC=0.84), followed by the fixed threshold applied to SpO2, HR and BR (0.82) and the variable threshold applied to HR only (0.76). Conclusion: Early detection of a patient9s risk of readmission is optimized when SpO2, HR and BR all exceed variable thresholds derived from the patient9s 15-day baseline. [1] Brinchault, G., et al. Rev Mal Resp 15.1 (2023): 70

Continuous measurement of heart rate variability (HRV) in the short and ultra-short-term using wearable devices allows monitoring of physiological status and prevention of diseases. This study aims to evaluate the agreement of HRV features between a commercial device (Bora Band, Biosency) measuring photoplethysmography (PPG) and reference electrocardiography (ECG) and to assess the validity of ultra-short-term HRV as a surrogate for short-term HRV features. PPG and ECG recordings were acquired from 5 healthy subjects over 18 nights in total. HRV features include time-domain, frequency-domain, nonlinear, and visibility graph features and are extracted from 5 min 30 s and 1 min 30 s duration PPG recordings. The extracted features are compared with reference features of 5 min 30 s duration ECG recordings using repeated-measures correlation, Bland–Altman plots with 95% limits of agreements, Cliff’s delta, and an equivalence test. Results showed agreement between PPG recordings and ECG reference recordings for 37 out of 48 HRV features in short-term durations. Sixteen of the forty-eight HRV features were valid and retained very strong correlations, negligible to small bias, with statistical equivalence in the ultra-short recordings (1 min 30 s). The current study concludes that the Bora Band provides valid and reliable measurement of HRV features in short and ultra-short duration recordings.

Purpose Segmenting organs in cone-beam CT (CBCT) images would allow to adapt the radiotherapy based on the organ deformations that may occur between treatment fractions. However, this is a difficult task because of the relative lack of contrast in CBCT images, leading to high inter-observer variability. Deformable image registration (DIR) and deep-learning based automatic segmentation approaches have shown interesting results for this task in the past years. However, they are either sensitive to large organ deformations, or require to train a convolutional neural network (CNN) from a database of delineated CBCT images, which is difficult to do without improvement of image quality. In this work, we propose an alternative approach: to train a CNN (using a deep learning-based segmentation tool called nnU-Net) from a database of artificial CBCT images simulated from planning CT, for which it is easier to obtain the organ contours. Methods Pseudo-CBCT (pCBCT) images were simulated from readily available segmented planning CT images, using the GATE Monte Carlo simulation. CT reference delineations were copied onto the pCBCT, resulting in a database of segmented images used to train the neural network. The studied segmentation contours were: bladder, rectum, and prostate contours. We trained multiple nnU-Net models using different training: (1) segmented real CBCT, (2) pCBCT, (3) segmented real CT and tested on pseudo-CT (pCT) generated from CBCT with cycleGAN, and (4) a combination of (2) and (3). The evaluation was performed on different datasets of segmented CBCT or pCT by comparing predicted segmentations with reference ones thanks to Dice similarity score and Hausdorff distance. A qualitative evaluation was also performed to compare DIR-based and nnU-Net-based segmentations. Results Training with pCBCT was found to lead to comparable results to using real CBCT images. When evaluated on CBCT obtained from the same hospital as the CT images used in the simulation of the pCBCT, the model trained with pCBCT scored mean DSCs of 0.92 +/- 0.05, 0.87 +/- 0.02, and 0.85 +/- 0.04 and mean Hausdorff distance 4.67 +/- 3.01, 3.91 +/- 0.98, and 5.00 +/- 1.32 for the bladder, rectum, and prostate contours respectively, while the model trained with real CBCT scored mean DSCs of 0.91 +/- 0.06, 0.83 +/- 0.07, and 0.81 +/- 0.05 and mean Hausdorff distance 5.62 +/- 3.24, 6.43 +/- 5.11, and 6.19 +/- 1.14 for the bladder, rectum, and prostate contours, respectively. It was also found to outperform models using pCT or a combination of both, except for the prostate contour when tested on a dataset from a different hospital. Moreover, the resulting segmentations demonstrated a clinical acceptability, where 78% of bladder segmentations, 98% of rectum segmentations, and 93% of prostate segmentations required minor or no corrections, and for 76% of the patients, all structures of the patient required minor or no corrections. Conclusion We proposed to use simulated CBCT images to train a nnU-Net segmentation model, avoiding the need to gather complex and time-consuming reference delineations on CBCT images.

The growing availability of large neuroimaging databases offers exceptional opportunities to train more and more efficient machine learning algorithms. Nevertheless, these databases may be prone to several sources of variability (age, gender, acquisition parameters,...). These nuisance variables can hamper the performance of a classification method and can even lead to misinterpret its behavior. We focus in this paper on how to account for data coming from different databases. First, we present experiments on simulated data that illustrate how interactions with other confounds such as age can be problematic for the adjustment of data from multiple databases. Then, we compare three standard strategies to adjust data and evaluate them in the scenario of a ComputerAided Diagnosis system that discriminates healthy from Alzheimer's Disease subjects based on volumetric characteristics derived from MRI. We highlight that classifiers with apparently similar performance do not all rely on relevant information depending on the correction strategy.

This paper compares several linear and non-linear multivariate models for the detection of abnormal patterns in neuroimaging data, when comparing a single subject to a normal control group. The proposed methods learn the manifold spanned by the normal controls using non-linear dimension reduction techniques. The image of a subject is projected on the control group manifold either via a standard projection or through an embedding/reconstruction scheme. A comparison of the reconstruction with the subject's original neuroimaging data allows for the detection of abnormal patterns by way of statistical tests on the residuals. The different abnormality detection methods are assessed on synthetic data and real (MRI) neuroimaging data. The importance of non-linear modeling of the manifold in the reduced-dimension subspace is highlighted, as well as robustness to large abnormalities.

In this paper, we analyze how to accurately track superpixels over extended time periods for computer vision applications. A two-step video processing pipeline dedicated to long-term superpixel tracking is proposed based on unsupervised learning and temporal integration. First, unsupervised learning-based matching provides superpixel correspondences between consecutive and distant frames using context-rich features extended from greyscale to multi-channel. Resulting elementary matches are then combined along multi-step paths running through the whole sequence with various inter-frame distances. This produces a large set of candidate long-term superpixel pairings upon which majority voting is performed. Video object tracking experiments demonstrate the efficiency of this pipeline against state-of-the-art methods.

This paper presents an innovative way to reach accurate semi-dense registration between images based on robust matching of structural entities. The proposed approach relies on a decomposition of images into visual primitives called supervoxels generated by aggregating adjacent voxels sharing similar characteristics. Two new categories of features are estimated at the supervoxel extent: mid-level spectral features relying on a spectral method applied on supervoxel graphs to capture the non-linear modes of intensity displacements, and mid-level context-rich features describing the broadened spatial context on the resulting spectral representations. Accurate supervoxel pairings are established by nearest neighbor search on these newly designed features. The effectiveness of the approach is demonstrated against state-of-the-art methods for semi-dense longitudinal registration of abdominal CT images, relying on liver label propagation and consistency assessment.

This paper addresses the estimation of pairwise supervoxel correspondences toward automatic semi-dense medical image registration. Supervoxel matching is performed through random forests (RF) with supervoxel indexes as label entities to predict matching areas in another target image. Ensuring accurate supervoxel boundary adherence requires a fine supervoxel decomposition which highly increases learning complexity. To alleviate this issue, we extend RF based supervoxel matching from single to multi-scale using a recursive hierarchical supervoxel representation. Output RF matching probabilities obtained for the last scale are gathered with ancestor matching probabilities which acts as a coarse-to-fine matching guidance. The effectiveness of our method is high-lighted for semi-dense abdominal image registration relying on liver label propagation and consistency assessment.