Sensor Fusion Approach for Multiple Human Motion Detection for Indoor Surveillance Use-Case.

Multi-human detection and tracking in indoor surveillance is a challenging task due to various factors such as occlusions, illumination changes, and complex human-human and human-object interactions. In this study, we address these challenges by exploring the benefits of a low-level sensor fusion approach that combines grayscale and neuromorphic vision sensor (NVS) data. We first generate a custom dataset using an NVS camera in an indoor environment. We then conduct a comprehensive study by experimenting with different image features and deep learning networks, followed by a multi-input fusion strategy to optimize our experiments with respect to overfitting. Our primary goal is to determine the best input feature types for multi-human motion detection using statistical analysis. We find that there is a significant difference between the input features of optimized backbones, with the best strategy depending on the amount of available data. Specifically, under a low-data regime, event-based frames seem to be the preferred input feature type, while higher data availability benefits the combined use of grayscale and optical flow features. Our results demonstrate the potential of sensor fusion and deep learning techniques for multi-human tracking in indoor surveillance, although it is acknowledged that further studies are needed to confirm our findings.

BEAS-Net: a Shape-Prior-Based Deep Convolutional Neural Network for Robust Left Ventricular Segmentation in 2D Echocardiography.

Left ventricle (LV) segmentation of 2D echocardiography images is an essential step in the analysis of cardiac morphology and function and - more generally - diagnosis of cardiovascular diseases. Several deep learning (DL) algorithms have recently been proposed for the automatic segmentation of the LV, showing significant performance improvement over the traditional segmentation algorithms. However, unlike the traditional methods, prior information about the segmentation problem, e.g. anatomical shape information, is not usually incorporated for training the DL algorithms. This can degrade the generalization performance of the DL models on unseen images if their characteristics are somewhat different from those of the training images, e.g. low-quality testing images. In this study, a new shape-constrained deep convolutional neural network (CNN) - called BEAS-Net - is introduced for automatic LV segmentation. The BEAS-Net learns how to associate the image features, encoded by its convolutional layers, with anatomical shape-prior information derived by the B-spline explicit active surface (BEAS) algorithm to generate physiologically meaningful segmentation contours when dealing with artifactual or low-quality images. The performance of the proposed network was evaluated using three different in-vivo datasets and was compared a deep segmentation algorithm based on the U-Net model. Both networks yielded comparable results when tested on images of acceptable quality, but the BEAS-Net outperformed the benchmark DL model on artifactual and low-quality images.

Automatic multi-view pose estimation in focused cardiac ultrasound.

Focused cardiac ultrasound (FoCUS) is a valuable point-of-care method for evaluating cardiovascular structures and function, but its scope is limited by equipment and operator's experience, resulting in primarily qualitative 2D exams. This study presents a novel framework to automatically estimate the 3D spatial relationship between standard FoCUS views. The proposed framework uses a multi-view U-Net-like fully convolutional neural network to regress line-based heatmaps representing the most likely areas of intersection between input images. The lines that best fit the regressed heatmaps are then extracted, and a system of nonlinear equations based on the intersection between view triplets is created and solved to determine the relative 3D pose between all input images. The feasibility and accuracy of the proposed pipeline were validated using a novel realistic in silico FoCUS dataset, demonstrating promising results. Interestingly, as shown in preliminary experiments, the estimation of the 2D images' relative poses enables the application of 3D image analysis methods and paves the way for 3D quantitative assessments in FoCUS examinations.

SurgT challenge: Benchmark of soft-tissue trackers for robotic surgery.

This paper introduces the "SurgT: Surgical Tracking" challenge which was organized in conjunction with the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2022). There were two purposes for the creation of this challenge: (1) the establishment of the first standardized benchmark for the research community to assess soft-tissue trackers; and (2) to encourage the development of unsupervised deep learning methods, given the lack of annotated data in surgery. A dataset of 157 stereo endoscopic videos from 20 clinical cases, along with stereo camera calibration parameters, have been provided. Participants were assigned the task of developing algorithms to track the movement of soft tissues, represented by bounding boxes, in stereo endoscopic videos. At the end of the challenge, the developed methods were assessed on a previously hidden test subset. This assessment uses benchmarking metrics that were purposely developed for this challenge, to verify the efficacy of unsupervised deep learning algorithms in tracking soft-tissue. The metric used for ranking the methods was the Expected Average Overlap (EAO) score, which measures the average overlap between a tracker's and the ground truth bounding boxes. Coming first in the challenge was the deep learning submission by ICVS-2Ai with a superior EAO score of 0.617. This method employs ARFlow to estimate unsupervised dense optical flow from cropped images, using photometric and regularization losses. Second, Jmees with an EAO of 0.583, uses deep learning for surgical tool segmentation on top of a non-deep learning baseline method: CSRT. CSRT by itself scores a similar EAO of 0.563. The results from this challenge show that currently, non-deep learning methods are still competitive. The dataset and benchmarking tool created for this challenge have been made publicly available at https://surgt.grand-challenge.org/. This challenge is expected to contribute to the development of autonomous robotic surgery and other digital surgical technologies.

Atrial cardiopathy in young adults with embolic stroke of undetermined source: a myocardial deformation imaging analysis.

BACKGROUND: Atrial cardiopathy (AC) has emerged as a potential pathological thrombogenic atrial substract of embolic stroke of undetermined source (ESUS), even in the absence of atrial fibrillation. Left atrium (LA) myocardial deformation analysis may be of value as a subclinical marker of AC and a predictor of ESUS. AIMS: To compare LA mechanical function between ESUS cases and age and sex-matched controls. METHODS: A single-center analytical study with case-control design was performed. Case group was composed by young patients admitted in the Neurology department from January 2017 to June 2021. Control group was composed by age and sex matched controls recruited from the community. All participants performed echocardiogram and a smaller sample underwent cardiac magnetic resonance. RESULTS: We recruited 31 ESUS patients aged between 18 and 65 years and 31 age and sex matched controls. ESUS patients had a significantly higher prevalence of cardiovascular risk factors and patent foramen ovale (PFO). The prevalence of AC was not different between groups. Echocardiogram parameters, including strain analysis, were similar between groups, except for LA appendage (LAA) ostium variation which was significantly lower in ESUS patients (absolute: 6.5vs8.7mm, p<0.001; relative: 44.5%vs53.4%, p=0.002). After exclusion of patients with PFO, all the results were statistically similar. Regarding cardiac magnetic resonance analysis, there were no statistically significant differences between groups. CONCLUSION: This study shows that in our population atria cardiopathy and atrial function was not associated with ESUS.LAA structural and functional abnormalities may play a major role. The role of LAA in ESUS warrants further studies.

Deep Learning Segmentation of the Right Ventricle in Cardiac MRI: The M&Ms Challenge.

In recent years, several deep learning models have been proposed to accurately quantify and diagnose cardiac pathologies. These automated tools heavily rely on the accurate segmentation of cardiac structures in MRI images. However, segmentation of the right ventricle is challenging due to its highly complex shape and ill-defined borders. Hence, there is a need for new methods to handle such structure's geometrical and textural complexities, notably in the presence of pathologies such as Dilated Right Ventricle, Tricuspid Regurgitation, Arrhythmogenesis, Tetralogy of Fallot, and Inter-atrial Communication. The last MICCAI challenge on right ventricle segmentation was held in 2012 and included only 48 cases from a single clinical center. As part of the 12th Workshop on Statistical Atlases and Computational Models of the Heart (STACOM 2021), the M&Ms-2 challenge was organized to promote the interest of the research community around right ventricle segmentation in multi-disease, multi-view, and multi-center cardiac MRI. Three hundred sixty CMR cases, including short-axis and long-axis 4-chamber views, were collected from three Spanish hospitals using nine different scanners from three different vendors, and included a diverse set of right and left ventricle pathologies. The solutions provided by the participants show that nnU-Net achieved the best results overall. However, multi-view approaches were able to capture additional information, highlighting the need to integrate multiple cardiac diseases, views, scanners, and acquisition protocols to produce reliable automatic cardiac segmentation algorithms.

Feasibility and Accuracy of Automated Three-Dimensional Echocardiographic Analysis of Left Atrial Appendage for Transcatheter Closure.

BACKGROUND: Procedural success of transcatheter left atrial appendage closure (LAAC) is dependent on correct device selection. Three-dimensional (3D) transesophageal echocardiography (TEE) is more accurate than the two-dimensional modality for evaluation of the complex anatomy of the left atrial appendage (LAA). However, 3D transesophageal echocardiographic analysis of the LAA is challenging and highly expertise dependent. The aim of this study was to evaluate the feasibility and accuracy of a novel software tool for automated 3D analysis of the LAA using 3D transesophageal echocardiographic data. METHODS: Intraprocedural 3D transesophageal echocardiographic data from 158 patients who underwent LAAC were retrospectively analyzed using a novel automated LAA analysis software tool. On the basis of the 3D transesophageal echocardiographic data, the software semiautomatically segmented the 3D LAA structure, determined the device landing zone, and generated measurements of the landing zone dimensions and LAA length, allowing manual editing if necessary. The accuracy of LAA preimplantation anatomic measurement reproducibility and time for analysis of the automated software were compared against expert manual 3D analysis. The software feasibility to predict the optimal device size was directly compared with implanted models. RESULTS: Automated 3D analysis of the LAA on 3D TEE was feasible in all patients. There was excellent agreement between automated and manual measurements of landing zone maximal diameter (bias, -0.32; limits of agreement, -3.56 to 2.92), area-derived mean diameter (bias, -0.24; limits of agreement, -3.12 to 2.64), and LAA depth (bias, 0.02; limits of agreement, -3.14 to 3.18). Automated 3D analysis, with manual editing if necessary, accurately identified the implanted device size in 90.5% of patients, outperforming two-dimensional TEE (68.9%; P < .01). The automated software showed results competitive against the manual analysis of 3D TEE, with higher intra- and interobserver reproducibility, and allowed quicker analysis (101.9 ± 9.3 vs 183.5 ± 42.7 sec, P < .001) compared with manual analysis. CONCLUSIONS: Automated LAA analysis on the basis of 3D TEE is feasible and allows accurate, reproducible, and rapid device sizing decision for LAAC.

Automatic Assessment of Pectus Excavatum Severity From CT Images Using Deep Learning.

Pectus excavatum (PE) is the most common abnormality of the thoracic cage, whose severity is evaluated by extracting three indices (Haller, correction and asymmetry) from computed tomography (CT) images. To date, this analysis is performed manually, which is tedious and prone to variability. In this paper, a fully automatic framework for PE severity quantification from CT images is proposed, comprising three steps: (1) identification of the sternum's greatest depression point; (2) detection of 8 anatomical keypoints relevant for severity assessment; and (3) measurements' geometric regularization and extraction. The first two steps rely on heatmap regression networks based on the Unet++ architecture, including a novel variant adapted to predict 1D confidence maps. The framework was evaluated on a database with 269 CTs. For comparative purposes, intra-observer, inter-observer and intra-patient variability of the estimated indices were analyzed in a subset of patients. The developed system showed a good agreement with the manual approach (a mean relative absolute error of 4.41%, 5.22% and 1.86% for the Haller, correction, and asymmetry indices, respectively), with limits of agreement comparable to the inter-observer variability. In the intra-patient analysis, the proposed framework outperformed the expert, showing a higher reproducibility between indices extracted from distinct CTs of the same patient. Overall, these results support the feasibility of the developed framework for the automatic, accurate and reproducible quantification of PE severity in a clinical context.

Power Modulation Echocardiography to Detect and Quantify Myocardial Scar.

BACKGROUND: Myocardial scar correlates with clinical outcomes. Traditionally, late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) is used to detect and quantify scar. In this prospective study using LGE CMR as reference, the authors hypothesized that nonlinear ultrasound imaging, namely, power modulation, can detect and quantify myocardial scar in selected patients with previous myocardial infarction. In addition, given the different histopathology between ischemic and nonischemic scar, a further aim was to test the diagnostic performance of this echocardiographic technique in unselected consecutive individuals with ischemic and nonischemic LGE or no LGE on CMR. METHODS: Seventy-one patients with previous myocardial infarction underwent power modulation echocardiography following CMR imaging (group A). Subsequently, 101 consecutive patients with or without LGE on CMR, including individuals with nonischemic LGE, were scanned using power modulation echocardiography (group B). RESULTS: In group A, echocardiography detected myocardial scar in all 71 patients, with good scar volume agreement with CMR (bias = -1.9 cm3; limits of agreement [LOA], -8.0 to 4.2 cm3). On a per-segment basis, sensitivity was 82%, specificity 97%, and accuracy 92%. Sensitivity was higher in the inferior and posterior segments and lower in the anterior and lateral walls. In group B, on a per-subject basis, the sensitivity of echocardiography was 62% (91% for ischemic and 30% for nonischemic LGE), with specificity and accuracy of 89% and 72%, respectively. The bias for scar volume between modalities was 5.9 cm3, with LOA of 34.6 to 22.9 cm3 (bias = -1.9 cm3 [LOA, -11.4 to 7.6 cm3] for ischemic LGE, and bias = 18.9 cm3 [LOA, -67.4 to 29.7.6 cm3] for nonischemic LGE). CONCLUSIONS: Power modulation echocardiography can detect myocardial scar in both selected and unselected individuals with previous myocardial infarction and has good agreement for scar volume quantification with CMR. In an unselected cohort with nonischemic LGE, sensitivity is low.

Quality Assurance of Segmental Strain Values Provided by Commercial 2-D Speckle Tracking Echocardiography Using in Silico Models: A Report from the EACVI-ASE Strain Standardization Task Force.

The aim of this study was to determine the accuracy and reproducibility of vendor-specific regional strain values by echocardiography using in silico data. Synthetic 2-D ultrasound gray-scale images of the left ventricle (LV) were generated with knowledge of the longitudinal segmental strain values from the underlying electromechanical LV model. Four of five models mimicked transmural infarctions with systolic segmental stretching in different vascular areas. Cine loops in the three apical views were synthetically generated at four noise levels. All in silico images were repeatedly analyzed by a single investigator and some by another investigator. The absolute errors varied significantly between vendors from 3.3 ± 3.1% to 11.2 ± 5.9%. The area under the curve for the identification of segmental stretching ranged from 0.80 (confidence interval: 0.77-0.83) to 0.96 (0.95-0.98). The levels of agreement for intra-investigator variability varied between -3.0% to 2.9% and -5.2% to 4.8%, and for inter-investigator variability, between -3.6% to 3.5% and -14.5% to 8.5%. Segmental strain analysis allows the identification of areas with segmental stretching with good accuracy. However, single segmental peak-strain values are not accurate and should be interpreted with caution. Nevertheless, our results indicate the usefulness of semiquantitative strain assessment for the detection of regional dysfunction.

The Impact of Vendor-Specific Ultrasound Beam-Forming and Processing Techniques on the Visualization of In Vitro Experimental "Scar": Implications for Myocardial Scar Imaging Using Two-Dimensional and Three-Dimensional Echocardiography.

BACKGROUND: Myocardial scar appears brighter compared with normal myocardium on echocardiography because of differences in tissue characteristics. The aim of this study was to test how different ultrasound pulse characteristics affect the brightness contrast (i.e., contrast ratio [CR]) between tissues of different acoustic properties, as well as the accuracy of assessing tissue volume. METHODS: An experimental in vitro "scar" model was created using overheated and raw pieces of commercially available bovine muscle. Two-dimensional and three-dimensional ultrasound scanning of the model was performed using combinations of ultrasound pulse characteristics: ultrasound frequency, harmonics, pulse amplitude, steady pulse (SP) emission, power modulation (PM), and pulse inversion modalities. RESULTS: On both two-dimensional and three-dimensional imaging, the CR between the "scar" and its adjacent tissue was higher when PM was used. PM, as well as SP ultrasound imaging, provided good "scar" volume quantification. When tested on 10 "scars" of different size and shape, PM resulted in lower bias (-9.7 vs 54.2 mm3) and narrower limits of agreement (-168.6 to 149.2 mm3 vs -296.0 to 404.4 mm3, P = .03). The interobserver variability for "scar" volume was better with PM (intraclass correlation coefficient = 0.901 vs 0.815). Two-dimensional and three-dimensional echocardiography with PM and SP was performed on 15 individuals with myocardial scar secondary to infarction. The CR was higher on PM imaging. Using cardiac magnetic resonance as a reference, quantification of myocardial scar volume showed better agreement when PM was used (bias, -645 mm3; limits of agreement, -3,158 to 1,868 mm3) as opposed to SP (bias, -1,138 mm3; limits of agreement, -5,510 to 3,233 mm3). CONCLUSIONS: The PM modality increased the CR between tissues with different acoustic properties in an experimental in vitro "scar" model while allowing accurate quantification of "scar" volume. By applying the in vitro findings to humans, PM resulted in higher CR between scarred and healthy myocardium, providing better scar volume quantification than SP compared with cardiac magnetic resonance.

Kidney Segmentation in 3-D Ultrasound Images Using a Fast Phase-Based Approach.

Renal ultrasound (US) imaging is the primary imaging modality for the assessment of the kidney's condition and is essential for diagnosis, treatment and surgical intervention planning, and follow-up. In this regard, kidney delineation in 3-D US images represents a relevant and challenging task in clinical practice. In this article, a novel framework is proposed to accurately segment the kidney in 3-D US images. The proposed framework can be divided into two stages: 1) initialization of the segmentation method and 2) kidney segmentation. Within the initialization stage, a phase-based feature detection method is used to detect edge points at kidney boundaries, from which the segmentation is automatically initialized. In the segmentation stage, the B-spline explicit active surface framework is adapted to obtain the final kidney contour. Here, a novel hybrid energy functional that combines localized region- and edge-based terms is used during segmentation. For the edge term, a fast-signed phase-based detection approach is applied. The proposed framework was validated in two distinct data sets: 1) 15 3-D challenging poor-quality US images used for experimental development, parameters assessment, and evaluation and 2) 42 3-D US images (both healthy and pathologic kidneys) used to unbiasedly assess its accuracy. Overall, the proposed method achieved a Dice overlap around 81% and an average point-to-surface error of ~2.8 mm. These results demonstrate the potential of the proposed method for clinical usage.

Strain maps of the left atrium imaged with a novel high-resolution CINE MRI protocol.

To date, regional atrial strains have not been imaged in vivo, despite their potential to provide useful clinical information. To address this gap, we present a novel CINE MRI protocol capable of imaging the entire left atrium at an isotropic 2-mm resolution in one single breath-hold. As proof of principle, we acquired data in 10 healthy volunteers and 2 cardiovascular patients using this technique. We also demonstrated how regional atrial strains can be estimated from this data following a manual segmentation of the left atrium using automatic image tracking techniques. The estimated principal strains vary smoothly across the left atrium and have a similar magnitude to estimates reported in the literature.

Technical Note: Assessment of electromagnetic tracking systems in a surgical environment using ultrasonography and ureteroscopy instruments for percutaneous renal access.

PURPOSE: Electromagnetic tracking systems (EMTSs) have been proposed to assist the percutaneous renal access (PRA) during minimally invasive interventions to the renal system. However, the influence of other surgical instruments widely used during PRA (like ureteroscopy and ultrasound equipment) in the EMTS performance is not completely known. This work performs this assessment for two EMTSs [Aurora® Planar Field Generator (PFG); Aurora® Tabletop Field Generator (TTFG)]. METHODS: An assessment platform, composed by a scaffold with specific supports to attach the surgical instruments and a plate phantom with multiple levels to precisely translate or rotate the surgical instruments, was developed. The median accuracy and precision in terms of position and orientation were estimated for the PFG and TTFG in a surgical environment using this platform. Then, the influence of different surgical instruments (alone or together), namely analogic flexible ureterorenoscope (AUR), digital flexible ureterorenoscope (DUR), two-dimensional (2D) ultrasound (US) probe, and four-dimensional (4D) mechanical US probe, was assessed for both EMTSs by coupling the instruments to 5-DOF and 6-DOF sensors. RESULTS: Overall, the median positional and orientation accuracies in the surgical environment were 0.85 mm and 0.42° for PFG, and 0.72 mm and 0.39° for TTFG, while precisions were 0.10 mm and 0.03° for PFG, and 0.20 mm and 0.12° for TTFG, respectively. No significant differences were found for accuracy between EMTSs. However, PFG showed a tendency for higher precision than TTFG. AUR, DUR, and 2D US probe did not influence the accuracy and precision of both EMTSs. In opposition, the 4D probe distorted the signal near the attached sensor, making readings unreliable. CONCLUSIONS: Ureteroscopy- and ultrasonography-assisted PRA based on EMTS guidance are feasible with the tested AUR or DUR together with the 2D probe. More studies must be performed to evaluate the probes and ureterorenoscopes' influence before their use in PRA based on EMTS guidance.

Non-invasive myocardial performance mapping using 3D echocardiographic stress-strain loops.

Regional contribution to left ventricular (LV) ejection is of much clinical importance but its assessment is notably challenging. While deformation imaging is often used, this does not take into account loading conditions. Recently, a method for intraventricular pressure estimation was proposed, thus allowing for loading conditions to be taken into account in a non-invasive way. In this work, a method for 3D automatic myocardial performance mapping in echocardiography is proposed by performing 3D myocardial segmentation and tracking, thus giving access to local geometry and strain. This is then used to assess local LV stress-strain relationships which can be seen as a measure of local myocardial work. The proposed method was validated against 18F-fluorodeoxyglucose positron emission tomography, the reference method to clinically assess local metabolism. Averaged over all patients, the mean correlation between FDG-PET and the proposed method was [Formula: see text]. In conclusion, stress-strain loops were, for the first time, estimated from 3D echocardiography and correlated to the clinical gold standard for local metabolism, showing the future potential of real-time 3D echocardiography (RT3DE) for the assessment of local metabolic activity of the heart.

Assessment of aortic valve tract dynamics using automatic tracking of 3D transesophageal echocardiographic images.

The assessment of aortic valve (AV) morphology is paramount for planning transcatheter AV implantation (TAVI). Nowadays, pre-TAVI sizing is routinely performed at one cardiac phase only, usually at mid-systole. Nonetheless, the AV is a dynamic structure that undergoes changes in size and shape throughout the cardiac cycle, which may be relevant for prosthesis selection. Thus, the aim of this study was to present and evaluate a novel software tool enabling the automatic sizing of the AV dynamically in three-dimensional (3D) transesophageal echocardiography (TEE) images. Forty-two patients who underwent preoperative 3D-TEE images were retrospectively analyzed using the software. Dynamic measurements were automatically extracted at four levels, including the aortic annulus. These measures were used to assess the software's ability to accurately and reproducibly quantify the conformational changes of the aortic root and were validated against automated sizing measurements independently extracted at distinct time points. The software extracted physiological dynamic measurements in less than 2 min, that were shown to be accurate (error 2.2 ± 26.3 mm2 and 0.0 ± 2.53 mm for annular area and perimeter, respectively) and highly reproducible (0.85 ± 6.18 and 0.65 ± 7.90 mm2 of intra- and interobserver variability, respectively, in annular area). Using the maximum or minimum measured values rather than mid-systolic ones for device sizing resulted in a potential change of recommended size in 7% and 60% of the cases, respectively. The presented software tool allows a fast, automatic and reproducible dynamic assessment of the AV morphology from 3D-TEE images, with the extracted measures influencing the device selection depending on the cardiac moment used to perform its sizing. This novel tool may thus ease and potentially increase the observer's confidence during prosthesis' size selection at the preoperative TAVI planning.

Semiautomatic Estimation of Device Size for Left Atrial Appendage Occlusion in 3-D TEE Images.

Left atrial appendage (LAA) occlusion is used to reduce the risk of thromboembolism in patients with nonvalvular atrial fibrillation by obstructing the LAA through a percutaneously delivered device. Nonetheless, correct device sizing is complex, requiring the manual estimation of different measurements in preprocedural/periprocedural images, which is tedious and time-consuming and with high interobserver and intraobserver variability. In this paper, a semiautomatic solution to estimate the required relevant clinical measurements is described. This solution starts with the 3-D segmentation of the LAA in 3-D transesophageal echocardiographic images, using a constant blind-ended model initialized through a manually defined spline. Then, the segmented LAA surface is aligned with a set of templates, i.e., 3-D surfaces plus relevant measurement planes (manually defined by one observer), transferring the latter to the unknown situation. Specifically, the alignment is performed in three consecutive steps, namely: 1) rigid alignment using the LAA clipping plane position; 2) orientation compensation using the circumflex artery location; and 3) anatomical refinement through a weighted iterative closest point algorithm. The novel solution was evaluated in a clinical database with 20 volumetric TEE images. Two experiments were set up to assess: 1) the sensitivity of the model's parameters and 2) the accuracy of the proposed solution for the estimation of the clinical measurements. Measurement levels manually identified by two observers were used as ground truth. The proposed solution obtained results comparable to the interobserver variability, presenting narrower limits of agreement for all measurements. Moreover, this solution proved to be fast, taking nearly 40 s (manual analysis took 3 min) to estimate the relevant measurements while being robust to the variation of the model's parameters. Overall, the proposed solution showed its potential for fast and robust estimation of the clinical measurements for occluding device selection, proving its added value for clinical practice.

Surface-based registration between CT and US for image-guided percutaneous renal access - A feasibility study.

PURPOSE: As a crucial step in accessing the kidney in several minimally invasive interventions, percutaneous renal access (PRA) practicality and safety may be improved through the fusion of computed tomography (CT) and ultrasound (US) data. This work aims to assess the potential of a surface-based registration technique and establish an optimal US acquisition protocol to fuse two-dimensional (2D) US and CT data for image-guided PRA. METHODS: Ten porcine kidney phantoms with fiducial markers were imaged using CT and three-dimensional (3D) US. Both images were manually segmented and aligned. In a virtual environment, 2D contours were extracted by slicing the 3D US kidney surfaces and using usual PRA US-guided views, while the 3D CT kidney surfaces were transformed to simulate positional variability. Surface-based registration was performed using two methods of the iterative closest point algorithm (point-to-point, ICP1; and point-to-plane, ICP2), while four acquisition variants were studied: (a) use of single-plane (transverse, SPT ; or longitudinal, SPL ) vs bi-plane views (BP); (b) use of different kidney's coverage ranges acquired by a probe's sweep; (c) influence of sweep movements; and (d) influence of the spacing between consecutive slices acquired for a specific coverage range. RESULTS: BP view showed the best performance (TRE = 2.26 mm) when ICP2 method, a wide kidney coverage range (20°, with slices spaced by 5°), and a large sweep along the central longitudinal view were used, showing a statistically similar performance (P = 0.097) to a full 3D US surface registration (TRE = 2.28 mm). CONCLUSIONS: An optimal 2D US acquisition protocol was evaluated. Surface-based registration, using multiple slices and specific sweep movements and views, is here suggested as a valid strategy for intraoperative image fusion using CT and US data, having the potential to be applied to other image modalities and/or interventions.

Kidney segmentation in ultrasound, magnetic resonance and computed tomography images: A systematic review.

BACKGROUND AND OBJECTIVE: Segmentation is an essential step in computer-aided diagnosis and treatment planning of kidney diseases. In recent years, several researchers proposed multiple techniques to segment the kidney in medical images from distinct imaging acquisition systems, namely ultrasound, magnetic resonance, and computed tomography. This article aims to present a systematic review of the different methodologies developed for kidney segmentation. METHODS: With this work, it is intended to analyze and categorize the different kidney segmentation algorithms, establishing a comparison between them and discussing the most appropriate methods for each modality. For that, articles published between 2010 and 2016 were analyzed. The search was performed in Scopus and Web of Science using the expressions "kidney segmentation" and "renal segmentation". RESULTS: A total of 1528 articles were retrieved from the databases, and 95 articles were selected for this review. After analysis of the selected articles, the reviewed segmentation techniques were categorized according to their theoretical approach. CONCLUSIONS: Based on the performed analysis, it was possible to identify segmentation approaches based on distinct image processing classes that can be used to accurately segment the kidney in images of different imaging modalities. Nevertheless, further research on kidney segmentation must be conducted to overcome the current drawbacks of the state-of-the-art methods. Moreover, a standardization of the evaluation database and metrics is needed to allow a direct comparison between methods.

A novel multi-atlas strategy with dense deformation field reconstruction for abdominal and thoracic multi-organ segmentation from computed tomography.

Anatomical evaluation of multiple abdominal and thoracic organs is generally performed with computed tomography images. Owing to the large field-of-view of these images, automatic segmentation strategies are typically required, facilitating the clinical evaluation. Multi-atlas segmentation (MAS) strategies have been widely used with this process, requiring multiple alignments between the target image and the set of known datasets, and subsequently fusing the alignment results to obtain the final segmentation. Nonetheless, current MAS strategies apply a global alignment of a deformable object, per organ, subdividing the segmentation process into multiple ones and losing the spatial information among nearby organs. This paper presents a novel MAS approach. First, a coarse-to-fine method with multiple global alignments (one per organ) is used. To make the method spatially coherent, these individual organs' global transformations are then fused in one using a dense deformation field reconstruction strategy. Second, from the candidate segmentations obtained, the final segmentation is estimated through an organ-based label fusion approach. The proposed method is evaluated and compared against a conventional MAS strategy through the segmentation of twelve abdominal and thoracic organs from the VISCERAL Anatomy benchmark. Average Dice coefficients for the liver, spleen, lungs and kidneys are all higher than 90%, are around 85% for the aorta, trachea and sternum and 70% for the pancreas, urinary bladder and gallbladder. The novel MAS strategy, with dense deformation field reconstruction, shows competitive results against other state-of-the-art methods, proving its added value for the segmentation of abdominal and thoracic organs, mainly for highly variable organs.