Search

Objective: Evaluation of left ventricular (LV) function in critical care patients is useful for guidance of therapy and early detection of LV dysfunction, but the tools currently available are too time-consuming. To resolve this issue, we previously proposed a method for the continuous and automatic quantification of global LV function in critical care patients based on the detection and tracking of anatomical landmarks on transesophageal heart ultrasound. In the present study, our aim was to improve the performance of mitral annulus detection in transesophageal echocardiography (TEE)., Methods: We investigated several state-of-the-art networks for both the detection and tracking of the mitral annulus in TEE. We integrated the networks into a pipeline for automatic assessment of LV function through estimation of the mitral annular plane systolic excursion (MAPSE), called autoMAPSE. TEE recordings from a total of 245 patients were collected from St. Olav's University Hospital and used to train and test the respective networks. We evaluated the agreement between autoMAPSE estimates and manual references annotated by expert echocardiographers in 30 Echolab patients and 50 critical care patients. Furthermore, we proposed a prototype of autoMAPSE for clinical integration and tested it in critical care patients in the intensive care unit., Results: Compared with manual references, we achieved a mean difference of 0.8 (95% limits of agreement: -2.9 to 4.7) mm in Echolab patients, with a feasibility of 85.7%. In critical care patients, we reached a mean difference of 0.6 (95% limits of agreement: -2.3 to 3.5) mm and a feasibility of 88.1%. The clinical prototype of autoMAPSE achieved real-time performance., Conclusion: Automatic quantification of LV function had high feasibility in clinical settings. The agreement with manual references was comparable to inter-observer variability of clinical experts., Competing Interests: Conflict of interest The authors declare no competing interests., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

Three-dimensional (3D) images provide a comprehensive view of material microstructures, enabling numerical simulations unachievable with two-dimensional (2D) imaging alone. However, obtaining these 3D images can be costly and constrained by resolution limitations. We introduce a novel method capable of generating large-scale 3D images of material microstructures, such as metal or rock, from a single 2D image. Our approach circumvents the need for 3D image data while offering a cost-effective, high-resolution alternative to existing imaging techniques. Our method combines a denoising diffusion probabilistic model with a generative adversarial network framework. To compensate for the lack of 3D training data, we implement chain sampling, a technique that utilizes the 3D intermediate outputs obtained by reversing the diffusion process. During the training phase, these intermediate outputs are guided by a 2D discriminator. This technique facilitates our method's ability to gradually generate 3D images that accurately capture the geometric properties and statistical characteristics of the original 2D input. This study features a comparative analysis of the 3D images generated by our method, SliceGAN (the current state-of-the-art method), and actual 3D micro-CT images, spanning a diverse set of rock and metal types. The results shown an improvement of up to three times in the Frechet inception distance score, a typical metric for evaluating the performance of image generative models, and enhanced accuracy in derived properties compared to SliceGAN. The potential of our method to produce high-resolution and statistically representative 3D images paves the way for new applications in material characterization and analysis domains., (© 2024. The Author(s).)

Objective: Our goal was to review the available literature on prognostic risk prediction for incident hypertension, synthesize performance, and provide suggestions for future work on the topic., Methods: A systematic search on PUBMED and Web of Science databases was conducted for studies on prognostic risk prediction models for incident hypertension in generally healthy individuals. Study-quality was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST) checklist. Three-level meta-analyses were used to obtain pooled AUC/C-statistic estimates. Heterogeneity was explored using study and cohort characteristics in meta-regressions., Results: From 5090 hits, we found 53 eligible studies, and included 47 in meta-analyses. Only four studies were assessed to have results with low risk of bias. Few models had been externally validated, with only the Framingham risk model validated more than thrice. The pooled AUC/C-statistics were 0.82 (0.77-0.86) for machine learning models and 0.78 (0.76-0.80) for traditional models, with high heterogeneity in both groups (I2 > 99%). Intra-class correlations within studies were 60% and 90%, respectively. Follow-up time (P = 0.0405) was significant for ML models and age (P = 0.0271) for traditional models in explaining heterogeneity. Validations of the Framingham risk model had high heterogeneity (I2 > 99%)., Conclusion: Overall, the quality of included studies was assessed as poor. AUC/C-statistic were mostly acceptable or good, and higher for ML models than traditional models. High heterogeneity implies large variability in the performance of new risk models. Further, large heterogeneity in validations of the Framingham risk model indicate variability in model performance on new populations. To enable researchers to assess hypertension risk models, we encourage adherence to existing guidelines for reporting and developing risk models, specifically reporting appropriate performance measures. Further, we recommend a stronger focus on validation of models by considering reasonable baseline models and performing external validations of existing models. Hence, developed risk models must be made available for external researchers., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Schjerven et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

In this study, we aimed to create an 11-year hypertension risk prediction model using data from the Trøndelag Health (HUNT) Study in Norway, involving 17 852 individuals (20-85 years; 38% male; 24% incidence rate) with blood pressure (BP) below the hypertension threshold at baseline (1995-1997). We assessed 18 clinical, behavioral, and socioeconomic features, employing machine learning models such as eXtreme Gradient Boosting (XGBoost), Elastic regression, K-Nearest Neighbor, Support Vector Machines (SVM) and Random Forest. For comparison, we used logistic regression and a decision rule as reference models and validated six external models, with focus on the Framingham risk model. The top-performing models consistently included XGBoost, Elastic regression and SVM. These models efficiently identified hypertension risk, even among individuals with optimal baseline BP (< 120/80 mmHg), although improvement over reference models was modest. The recalibrated Framingham risk model outperformed the reference models, approaching the best-performing ML models. Important features included age, systolic and diastolic BP, body mass index, height, and family history of hypertension. In conclusion, our study demonstrated that linear effects sufficed for a well-performing model. The best models efficiently predicted hypertension risk, even among those with optimal or normal baseline BP, using few features. The recalibrated Framingham risk model proved effective in our cohort., (© 2024. The Author(s).)

Perioperative monitoring of cardiac function is beneficial for early detection of cardiovascular complications. The standard of care for cardiac monitoring performed by trained cardiologists and anesthesiologists involves a manual and qualitative evaluation of ultrasound imaging, which is a time-demanding and resource-intensive process with intraobserver- and interobserver variability. In practice, such measures can only be performed a limited number of times during the intervention. To overcome these difficulties, this study presents a robust method for automatic and quantitative monitoring of cardiac function based on 3D transesophageal echocardiography (TEE) B-mode ultrasound recordings of the left ventricle (LV). Such an assessment obtains consistent measurements and can produce a near real-time evaluation of ultrasound imagery. Hence, the presented method is time-saving and results in increased accessibility. The mitral annular plane systolic excursion (MAPSE), characterizing global LV function, is estimated by landmark detection and cardiac view classification of two-dimensional images extracted along the long-axis of the ultrasound volume. MAPSE estimation directly from 3D TEE recordings is beneficial since it removes the need for manual acquisition of cardiac views, hence decreasing the need for interference by physicians. Two convolutional neural networks (CNNs) were trained and tested on acquired ultrasound data of 107 patients, and MAPSE estimates were compared to clinically obtained references in a blinded study including 31 patients. The proposed method for automatic MAPSE estimation had low bias and low variability in comparison to clinical reference measures. The method accomplished a mean difference for MAPSE estimates of (-0.16±1.06) mm. Thus, the results did not show significant systematic errors. The obtained bias and variance of the method were comparable to inter-observer variability of clinically obtained MAPSE measures on 2D TTE echocardiography. The novel pipeline proposed in this study has the potential to enhance cardiac monitoring in perioperative- and intensive care settings., Competing Interests: Declaration of competing interest, (Copyright © 2023 The Author(s). Published by Elsevier B.V. All rights reserved.)

Purpose: This study aims to explore training strategies to improve convolutional neural network-based image-to-image deformable registration for abdominal imaging., Methods: Different training strategies, loss functions, and transfer learning schemes were considered. Furthermore, an augmentation layer which generates artificial training image pairs on-the-fly was proposed, in addition to a loss layer that enables dynamic loss weighting., Results: Guiding registration using segmentations in the training step proved beneficial for deep-learning-based image registration. Finetuning the pretrained model from the brain MRI dataset to the abdominal CT dataset further improved performance on the latter application, removing the need for a large dataset to yield satisfactory performance. Dynamic loss weighting also marginally improved performance, all without impacting inference runtime., Conclusion: Using simple concepts, we improved the performance of a commonly used deep image registration architecture, VoxelMorph. In future work, our framework, DDMR, should be validated on different datasets to further assess its value., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 de Frutos et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Deep learning-based methods, in particular, convolutional neural networks and fully convolutional networks are now widely used in the medical image analysis domain. The scope of this review focuses on the analysis using deep learning of focal liver lesions, with a special interest in hepatocellular carcinoma and metastatic cancer; and structures like the parenchyma or the vascular system. Here, we address several neural network architectures used for analyzing the anatomical structures and lesions in the liver from various imaging modalities such as computed tomography, magnetic resonance imaging and ultrasound. Image analysis tasks like segmentation, object detection and classification for the liver, liver vessels and liver lesions are discussed. Based on the qualitative search, 91 papers were filtered out for the survey, including journal publications and conference proceedings. The papers reviewed in this work are grouped into eight categories based on the methodologies used. By comparing the evaluation metrics, hybrid models performed better for both the liver and the lesion segmentation tasks, ensemble classifiers performed better for the vessel segmentation tasks and combined approach performed better for both the lesion classification and detection tasks. The performance was measured based on the Dice score for the segmentation, and accuracy for the classification and detection tasks, which are the most commonly used metrics., (Copyright © 2022 The Authors. Published by Elsevier B.V. All rights reserved.)

Purpose: Cancer is among the leading causes of death in the developed world, and lung cancer is the most lethal type. Early detection is crucial for better prognosis, but can be resource intensive to achieve. Automating tasks such as lung tumor localization and segmentation in radiological images can free valuable time for radiologists and other clinical personnel. Convolutional neural networks may be suited for such tasks, but require substantial amounts of labeled data to train. Obtaining labeled data is a challenge, especially in the medical domain., Methods: This paper investigates the use of a teacher-student design to utilize datasets with different types of supervision to train an automatic model performing pulmonary tumor segmentation on computed tomography images. The framework consists of two models: the student that performs end-to-end automatic tumor segmentation and the teacher that supplies the student additional pseudo-annotated data during training., Results: Using only a small proportion of semantically labeled data and a large number of bounding box annotated data, we achieved competitive performance using a teacher-student design. Models trained on larger amounts of semantic annotations did not perform better than those trained on teacher-annotated data. Our model trained on a small number of semantically labeled data achieved a mean dice similarity coefficient of 71.0 on the MSD Lung dataset., Conclusions: Our results demonstrate the potential of utilizing teacher-student designs to reduce the annotation load, as less supervised annotation schemes may be performed, without any real degradation in segmentation accuracy., Competing Interests: The authors have declared that no competing interests exist.

Obtaining an accurate segmentation of images obtained by computed microtomography (micro-CT) techniques is a non-trivial process due to the wide range of noise types and artifacts present in these images. Current methodologies are often time-consuming, sensitive to noise and artifacts, and require skilled people to give accurate results. Motivated by the rapid advancement of deep learning-based segmentation techniques in recent years, we have developed a tool that aims to fully automate the segmentation process in one step, without the need for any extra image processing steps such as noise filtering or artifact removal. To get a general model, we train our network using a dataset made of high-quality three-dimensional micro-CT images from different scanners, rock types, and resolutions. In addition, we use a domain-specific augmented training pipeline with various types of noise, synthetic artifacts, and image transformation/distortion. For validation, we use a synthetic dataset to measure accuracy and analyze noise/artifact sensitivity. The results show a robust and accurate segmentation performance for the most common types of noises present in real micro-CT images. We also compared the segmentation of our method and five expert users, using commercial and open software packages on real rock images. We found that most of the current tools fail to reduce the impact of local and global noises and artifacts. We quantified the variation on human-assisted segmentation results in terms of physical properties and observed a large variation. In comparison, the new method is more robust to local noises and artifacts, outperforming the human segmentation and giving consistent results. Finally, we compared the porosity of our model segmented images with experimental porosity measured in the laboratory for ten different untrained samples, finding very encouraging results., (© 2021. The Author(s).)

3D ultrasound (US) is a convenient tool for guiding the resection of low-grade gliomas, seemingly without deterioration in patients' quality of life. This article offers an update of the intraoperative workflow and the general principles behind the 3D US acquisition of high-quality images.The authors also provide case examples illustrating the technique in two small mesial temporal lobe lesions and in one insular glioma. Due to the ease of acquiring new images for navigation, the operations can be guided by updated image volumes throughout the entire course of surgery. The high accuracy offered by 3D US systems, based on nearly real-time images, allows for precise and safe resections. This is especially useful when an operation is performed through very narrow transcortical corridors.

Purpose: Test the feasibility of the novel Single Landmark image-to-patient registration method for use in the operating room for future clinical trials. The algorithm is implemented in the open-source platform CustusX, a computer-aided intervention research platform dedicated to intraoperative navigation and ultrasound, with an interface for laparoscopic ultrasound probes., Methods: The Single Landmark method is compared to fiducial landmark on an IOUSFAN (Kyoto Kagaku Co., Ltd., Japan) soft tissue abdominal phantom and T2 magnetic resonance scans of it., Results: The experiments show that the accuracy of the Single Landmark registration is good close to the registered point, increasing with the distance from this point (12.4 mm error at 60 mm away from the registered point). In this point, the registration accuracy is mainly dominated by the accuracy of the user when clicking on the ultrasound image. In the presented set-up, the time required to perform the Single Landmark registration is 40% less than for the FLRM., Conclusion: The Single Landmark registration is suitable for being integrated in a laparoscopic workflow. The statistical analysis shows robustness against translational displacements of the patient and improvements in terms of time. The proposed method allows the clinician to accurately register lesions intraoperatively by clicking on these in the ultrasound image provided by the ultrasound transducer. The Single Landmark registration method can be further combined with other more accurate registration approaches improving the registration at relevant points defined by the clinicians.

Background: Unreliable neuronavigation owing to inaccurate patient-to-image registration and brain shift is a major problem in conventional magnetic resonance imaging-guided neurosurgery. We performed a prospective intraoperative validation of a system for fully automatic correction of this inaccuracy based on intraoperative three-dimensional ultrasound and magnetic resonance imaging-to-ultrasound registration., Methods: The system was tested intraoperatively in 13 tumor resection cases, and performance was evaluated intraoperatively and postoperatively., Results: Intraoperatively, the system was accurate enough for tumor resection guidance in 9 of 13 cases. Manually placed anatomic landmarks showed improvement of alignment from 5.12 mm to 2.72 mm (median) after intraoperative correction. Postoperatively, the limitations of the current system were identified and modified for the system to be sufficiently accurate in all cases., Conclusions: Automatic and accurate correction of spatially unreliable neuronavigation is feasible within the constraints of surgery. The current limitations of the system were also identified and addressed., (Copyright © 2018 Elsevier Inc. All rights reserved.)

Objective: In flexible endoscopy techniques, such as bronchoscopy, there is often a challenge visualizing the path from start to target based on preoperative data and accessing these during the procedure. An example of this is visualizing only the inside of central airways in bronchoscopy. Virtual bronchoscopy (VB) does not meet the pulmonologist's need to detect, define and sample the frequent targets outside the bronchial wall. Our aim was to develop and study a new visualization technique for navigated bronchoscopy., Material and Methods: We extracted the shortest possible path from the top of the trachea to the target along the airway centerline and a corresponding auxiliary route in the opposite lung. A surface structure between the centerlines was developed and displayed. The new technique was tested on non-selective CT data from eight patients using artificial lung targets., Results: The new display technique anchored to centerline curved surface (ACCuSurf) made it easy to detect and interpret anatomical features, targets and neighboring anatomy outside the airways, in all eight patients., Conclusions: ACCuSurf can simplify planning and performing navigated bronchoscopy, meets the challenge of improving orientation and register the direction of the moving endoscope, thus creating an optimal visualization for navigated bronchoscopy.

Ultrasound-guided regional anesthesia can be challenging, especially for inexperienced physicians. The goal of the proposed methods is to create a system that can assist a user in performing ultrasound-guided femoral nerve blocks. The system indicates in which direction the user should move the ultrasound probe to investigate the region of interest and to reach the target site for needle insertion. Additionally, the system provides automatic real-time segmentation of the femoral artery, the femoral nerve and the two layers fascia lata and fascia iliaca. This aids in interpretation of the 2-D ultrasound images and the surrounding anatomy in 3-D. The system was evaluated on 24 ultrasound acquisitions of both legs from six subjects. The estimated target site for needle insertion and the segmentations were compared with those of an expert anesthesiologist. Average target distance was 8.5 mm with a standard deviation of 2.5 mm. The mean absolute differences of the femoral nerve and the fascia segmentations were about 1-3 mm., (Copyright © 2016 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.)

Introduction: We have previously described a method that has the potential to improve surgery of arteriovenous malformations (AVMs). In the present paper, we present our clinical results., Materials and Methods: Of 78 patients referred for AVMs to our University Hospital from our geographical catchment region from 2005 through 2013, 31 patients were operated on with microsurgical technique. 3D MR angiography (MRA) with neuronavigation was used for planning. Navigated 3D ultrasound angiography (USA) was used to identify and clip feeders in the initial phase of the operation. None of our patients was embolized preoperatively as part of the surgical procedure. The niduses were extirpated based on the 3D USA. After extirpation, controls were done with 3D USA to verify that the AVMs were completely removed. The Spetzler three-tier classification of the patients was: A: 21, B: 6, C: 4., Results: Sixty-eight feeders were identified on preoperative MRA and DSA and 67 feeders were identified and clipped by guidance of intraoperative 3D USA. Six feeders identified preoperatively were missed by 3D USA, while five preoperatively unknown feeders were found and clipped. The overall average bleeding was 440 ml. There was a significant reduction in average bleeding in the last 15 operations compared to the first 16 (340 vs. 559 ml, p = 0.019). We had no serious morbidity (GOS 3 or less). New deficits due to surgery were two patients with quadrantanopia (one class B and one class C), the latter (C) also acquired epilepsy. One patient (class A) acquired a hardly noticeable paresis in two fingers. One hundred percent angiographic cure was achieved in all patients, as evaluated by postoperative DSA., Conclusions: Navigated intraoperative 3D USA is a useful tool to identify and clip AVM feeders. Microsurgical extirpation assisted by navigated 3D USA is an effective and safe method for removing AVMs.

Purpose: CustusX is an image-guided therapy (IGT) research platform dedicated to intraoperative navigation and ultrasound imaging. In this paper, we present CustusX as a robust, accurate, and extensible platform with full access to data and algorithms and show examples of application in technological and clinical IGT research., Methods: CustusX has been developed continuously for more than 15 years based on requirements from clinical and technological researchers within the framework of a well-defined software quality process. The platform was designed as a layered architecture with plugins based on the CTK/OSGi framework, a superbuild that manages dependencies and features supporting the IGT workflow. We describe the use of the system in several different clinical settings and characterize major aspects of the system such as accuracy, frame rate, and latency., Results: The validation experiments show a navigation system accuracy of [Formula: see text]1.1 mm, a frame rate of 20 fps, and latency of 285 ms for a typical setup. The current platform is extensible, user-friendly and has a streamlined architecture and quality process. CustusX has successfully been used for IGT research in neurosurgery, laparoscopic surgery, vascular surgery, and bronchoscopy., Conclusions: CustusX is now a mature research platform for intraoperative navigation and ultrasound imaging and is ready for use by the IGT research community. CustusX is open-source and freely available at http://www.custusx.org.

Real-time 3D Echocardiography (RT3DE) has been proven to be an accurate tool for left ventricular (LV) volume assessment. However, identification of the LV endocardium remains a challenging task, mainly because of the low tissue/blood contrast of the images combined with typical artifacts. Several semi and fully automatic algorithms have been proposed for segmenting the endocardium in RT3DE data in order to extract relevant clinical indices, but a systematic and fair comparison between such methods has so far been impossible due to the lack of a publicly available common database. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms developed to segment the LV border in RT3DE. A database consisting of 45 multivendor cardiac ultrasound recordings acquired at different centers with corresponding reference measurements from three experts are made available. The algorithms from nine research groups were quantitatively evaluated and compared using the proposed online platform. The results showed that the best methods produce promising results with respect to the experts' measurements for the extraction of clinical indices, and that they offer good segmentation precision in terms of mean distance error in the context of the experts' variability range. The platform remains open for new submissions.

The goal is to create an assistant for ultrasound- guided femoral nerve block. By segmenting and visualizing the important structures such as the femoral artery, we hope to improve the success of these procedures. This article is the first step towards this goal and presents novel real-time methods for identifying and reconstructing the femoral artery, and registering a model of the surrounding anatomy to the ultrasound images. The femoral artery is modelled as an ellipse. The artery is first detected by a novel algorithm which initializes the artery tracking. This algorithm is completely automatic and requires no user interaction. Artery tracking is achieved with a Kalman filter. The 3D artery is reconstructed in real-time with a novel algorithm and a tracked ultrasound probe. A mesh model of the surrounding anatomy was created from a CT dataset. Registration of this model is achieved by landmark registration using the centerpoints from the artery tracking and the femoral artery centerline of the model. The artery detection method was able to automatically detect the femoral artery and initialize the tracking in all 48 ultrasound sequences. The tracking algorithm achieved an average dice similarity coefficient of 0.91, absolute distance of 0.33 mm, and Hausdorff distance 1.05 mm. The mean registration error was 2.7 mm, while the average maximum error was 12.4 mm. The average runtime was measured to be 38, 8, 46 and 0.2 milliseconds for the artery detection, tracking, reconstruction and registration methods respectively.

Introduction: Our motivation is increased bronchoscopic diagnostic yield and optimized preparation, for navigated bronchoscopy. In navigated bronchoscopy, virtual 3D airway visualization is often used to guide a bronchoscopic tool to peripheral lesions, synchronized with the real time video bronchoscopy. Visualization during navigated bronchoscopy, the segmentation time and methods, differs. Time consumption and logistics are two essential aspects that need to be optimized when integrating such technologies in the interventional room. We compared three different approaches to obtain airway centerlines and surface., Method: CT lung dataset of 17 patients were processed in Mimics (Materialize, Leuven, Belgium), which provides a Basic module and a Pulmonology module (beta version) (MPM), OsiriX (Pixmeo, Geneva, Switzerland) and our Tube Segmentation Framework (TSF) method. Both MPM and TSF were evaluated with reference segmentation. Automatic and manual settings allowed us to segment the airways and obtain 3D models as well as the centrelines in all datasets. We compared the different procedures by user interactions such as number of clicks needed to process the data and quantitative measures concerning the quality of the segmentation and centrelines such as total length of the branches, number of branches, number of generations, and volume of the 3D model., Results: The TSF method was the most automatic, while the Mimics Pulmonology Module (MPM) and the Mimics Basic Module (MBM) resulted in the highest number of branches. MPM is the software which demands the least number of clicks to process the data. We found that the freely available OsiriX was less accurate compared to the other methods regarding segmentation results. However, the TSF method provided results fastest regarding number of clicks. The MPM was able to find the highest number of branches and generations. On the other hand, the TSF is fully automatic and it provides the user with both segmentation of the airways and the centerlines. Reference segmentation comparison averages and standard deviations for MPM and TSF correspond to literature., Conclusion: The TSF is able to segment the airways and extract the centerlines in one single step. The number of branches found is lower for the TSF method than in Mimics. OsiriX demands the highest number of clicks to process the data, the segmentation is often sparse and extracting the centerline requires the use of another software system. Two of the software systems performed satisfactory with respect to be used in preprocessing CT images for navigated bronchoscopy, i.e. the TSF method and the MPM. According to reference segmentation both TSF and MPM are comparable with other segmentation methods. The level of automaticity and the resulting high number of branches plus the fact that both centerline and the surface of the airways were extracted, are requirements we considered particularly important. The in house method has the advantage of being an integrated part of a navigation platform for bronchoscopy, whilst the other methods can be considered preprocessing tools to a navigation system.

Purpose: Computer systems are becoming increasingly heterogeneous in the sense that they consist of different processors, such as multi-core CPUs and graphic processing units. As the amount of medical image data increases, it is crucial to exploit the computational power of these processors. However, this is currently difficult due to several factors, such as driver errors, processor differences, and the need for low-level memory handling. This paper presents a novel FrAmework for heterogeneouS medical image compuTing and visualization (FAST). The framework aims to make it easier to simultaneously process and visualize medical images efficiently on heterogeneous systems., Methods: FAST uses common image processing programming paradigms and hides the details of memory handling from the user, while enabling the use of all processors and cores on a system. The framework is open-source, cross-platform and available online., Results: Code examples and performance measurements are presented to show the simplicity and efficiency of FAST. The results are compared to the insight toolkit (ITK) and the visualization toolkit (VTK) and show that the presented framework is faster with up to 20 times speedup on several common medical imaging algorithms., Conclusions: FAST enables efficient medical image computing and visualization on heterogeneous systems. Code examples and performance evaluations have demonstrated that the toolkit is both easy to use and performs better than existing frameworks, such as ITK and VTK.

Within the field of ultrasound-guided procedures, there are a number of methods for ultrasound probe calibration. While these methods are usually developed for a specific probe, they are in principle easily adapted to other probes. In practice, however, the adaptation often proves tedious and this is impractical in a research setting, where new probes are tested regularly. Therefore, we developed a method which can be applied to a large variety of probes without adaptation. The method used a robot arm to move a plastic sphere submerged in water through the ultrasound image plane, providing a slow and precise movement. The sphere was then segmented from the recorded ultrasound images using a MATLAB programme and the calibration matrix was computed based on this segmentation in combination with tracking information. The method was tested on three very different probes demonstrating both great versatility and high accuracy.

Purpose: Multi-volume visualization is important for displaying relevant information in multimodal or multitemporal medical imaging studies. The main objective with the current study was to develop an efficient GPU-based multi-volume ray caster (MVRC) and validate the proposed visualization system in the context of image-guided surgical navigation., Methods: Ray casting can produce high-quality 2D images from 3D volume data but the method is computationally demanding, especially when multiple volumes are involved, so a parallel GPU version has been implemented. In the proposed MVRC, imaginary rays are sent through the volumes (one ray for each pixel in the view), and at equal and short intervals along the rays, samples are collected from each volume. Samples from all the volumes are composited using front to back α-blending. Since all the rays can be processed simultaneously, the MVRC was implemented in parallel on the GPU to achieve acceptable interactive frame rates. The method is fully integrated within the visualization toolkit (VTK) pipeline with the ability to apply different operations (e.g., transformations, clipping, and cropping) on each volume separately. The implemented method is cross-platform (Windows, Linux and Mac OSX) and runs on different graphics card (NVidia and AMD). The speed of the MVRC was tested with one to five volumes of varying sizes: 128(3), 256(3), and 512(3). A Tesla C2070 GPU was used, and the output image size was 600 × 600 pixels. The original VTK single-volume ray caster and the MVRC were compared when rendering only one volume., Results: The multi-volume rendering system achieved an interactive frame rate (> 15 fps) when rendering five small volumes (128 (3) voxels), four medium-sized volumes (256(3) voxels), and two large volumes (512(3) voxels). When rendering single volumes, the frame rate of the MVRC was comparable to the original VTK ray caster for small and medium-sized datasets but was approximately 3 frames per second slower for large datasets. The MVRC was successfully integrated in an existing surgical navigation system and was shown to be clinically useful during an ultrasound-guided neurosurgical tumor resection., Conclusions: A GPU-based MVRC for VTK is a useful tool in medical visualization. The proposed multi-volume GPU-based ray caster for VTK provided high-quality images at reasonable frame rates. The MVRC was effective when used in a neurosurgical navigation application.

Segmentation of anatomical structures, from modalities like computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound, is a key enabling technology for medical applications such as diagnostics, planning and guidance. More efficient implementations are necessary, as most segmentation methods are computationally expensive, and the amount of medical imaging data is growing. The increased programmability of graphic processing units (GPUs) in recent years have enabled their use in several areas. GPUs can solve large data parallel problems at a higher speed than the traditional CPU, while being more affordable and energy efficient than distributed systems. Furthermore, using a GPU enables concurrent visualization and interactive segmentation, where the user can help the algorithm to achieve a satisfactory result. This review investigates the use of GPUs to accelerate medical image segmentation methods. A set of criteria for efficient use of GPUs are defined and each segmentation method is rated accordingly. In addition, references to relevant GPU implementations and insight into GPU optimization are provided and discussed. The review concludes that most segmentation methods may benefit from GPU processing due to the methods' data parallel structure and high thread count. However, factors such as synchronization, branch divergence and memory usage can limit the speedup., (Copyright © 2014 The Authors. Published by Elsevier B.V. All rights reserved.)

The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases., (Copyright © 2014 Elsevier B.V. All rights reserved.)

Objective: Many studies demonstrate that the accuracy of freehand catheter placement for cerebrospinal fluid drainage is suboptimal. The aim of placement should be a single pass with a free-floating catheter tip in the intended position. The objective of this study was to achieve an accurate and user-friendly system for three-dimensional (3D) ultrasound-navigated catheter placement through a regular burr hole., Methods: A new phased-array ultrasound burr hole probe (4-10 MHz, 8 mm×9 mm footprint) was especially developed and optimized for navigated 3D ultrasound with the SonoWand Invite system. A catheter holder for optical tracking was also developed. Head immobilization was achieved with a vacuum cushion. With the described setup, 4 patients underwent surgery., Results: Ultrasound image quality and visualization of the ventricles was good in all cases. Optimal placement of the catheter was achieved in a single pass in all patients. One of the trajectories was slightly more medial on postoperative computed tomography than anticipated from the neuronavigation system. None of the patients experienced any adverse event related to the procedure., Conclusions: 3D ultrasound with the described setup is a promising technique for accurate, fast, and user-friendly navigated placement of catheters for cerebrospinal fluid diversion., (Copyright © 2014 Elsevier Inc. All rights reserved.)

Purpose: Treatments like radiotherapy and focused ultrasound in the abdomen require accurate motion tracking, in order to optimize dosage delivery to the target and minimize damage to critical structures and healthy tissues around the target. 4D ultrasound is a promising modality for motion tracking during such treatments. In this study, the authors evaluate the accuracy of motion tracking in the liver based on deformable registration of 4D ultrasound images., Methods: The offline analysis was performed using a nonrigid registration algorithm that was specifically designed for motion estimation from dynamic imaging data. The method registers the entire 4D image data sequence in a groupwise optimization fashion, thus avoiding a bias toward a specifically chosen reference time point. Three healthy volunteers were scanned over several breathing cycles (12 s) from three different positions and angles on the abdomen; a total of nine 4D scans for the three volunteers. Well-defined anatomic landmarks were manually annotated in all 96 time frames for assessment of the automatic algorithm. The error of the automatic motion estimation method was compared with interobserver variability. The authors also performed experiments to investigate the influence of parameters defining the deformation field flexibility and evaluated how well the method performed with a lower temporal resolution in order to establish the minimum frame rate required for accurate motion estimation., Results: The registration method estimated liver motion with an error of 1 mm (75% percentile over all datasets), which was lower than the interobserver variability of 1.4 mm. The results were only slightly dependent on the degrees of freedom of the deformation model. The registration error increased to 2.8 mm with an eight times lower temporal resolution., Conclusions: The authors conclude that the methodology was able to accurately track the motion of the liver in the 4D ultrasound data. The authors believe that the method has potential in interventions on moving abdominal organs such as MR or ultrasound guided focused ultrasound therapy and radiotherapy, pending the method is enabled to run in real-time. The data and the annotations used for this study are made publicly available for those who would like to test other methods on 4D liver ultrasound data.

Background: Brain-shift is a major source of error in neuronavigation systems based on pre-operative images. In this paper, we present intra-operative correction of brain-shift using 3D ultrasound., Methods: The method is based on image registration of vessels extracted from pre-operative MRA and intra-operative power Doppler-based ultrasound and is fully integrated in the neuronavigation software., Results: We have performed correction of brain-shift in the operating room during surgery and provided the surgeon with updated information. Here, we present data from seven clinical cases with qualitative and quantitative error measures., Conclusion: The registration algorithm is fast enough to provide the surgeon with updated information within minutes and accounts for large portions of the experienced shift. Correction of brain-shift can make pre-operative data like fMRI and DTI reliable for a longer period of time and increase the usefulness of the MR data as a supplement to intra-operative 3D ultrasound in terms of overview and interpretation.

Purpose: To create a fast and generic method with sufficient quality for extracting tubular structures such as blood vessels and airways from different modalities (CT, MR and US) and organs (brain, lungs and liver) by utilizing the computational power of graphic processing units (GPUs)., Methods: A cropping algorithm is used to remove unnecessary data from the datasets on the GPU. A model-based tube detection filter combined with a new parallel centerline extraction algorithm and a parallelized region growing segmentation algorithm is used to extract the tubular structures completely on the GPU. Accuracy of the proposed GPU method and centerline algorithm is compared with the ridge traversal and skeletonization/thinning methods using synthetic vascular datasets., Results: The implementation is tested on several datasets from three different modalities: airways from CT, blood vessels from MR, and 3D Doppler Ultrasound. The results show that the method is able to extract airways and vessels in 3-5 s on a modern GPU and is less sensitive to noise than other centerline extraction methods., Conclusions: Tubular structures such as blood vessels and airways can be extracted from various organs imaged by different modalities in a matter of seconds, even for large datasets.

Background: Navigated bronchoscopy uses virtual 3-dimensional lung model visualizations created from preoperative computed tomography images often in synchronization with the video bronchoscope to guide a tool to peripheral lesions. Navigated bronchoscopy has developed fast since the introduction of virtual bronchoscopy with integrated electromagnetic sensors in the late 1990s. The purposes of the review are to give an overview and update of the technological components of navigated bronchoscopy, an assessment of its clinical usefulness, and a brief assessment of the commercial platforms for navigated bronchoscopy., Methods: We performed a literature search with relevant keywords to navigation and bronchoscopy and iterated on the reference lists of relevant papers, with emphasis on the last 5 years., Results: The paper presents an overview of the components necessary for performing navigated bronchoscopy, assessment of the diagnostic accuracy of different approaches, and an analysis of the commercial systems. We were able to identify 4 commercial platforms and 9 research and development groups with considerable activity in the field. Finally, on the basis of our findings and our own experience, we provide a discussion on navigated bronchoscopy with focus on the next steps of development., Conclusions: The literature review showed that the peripheral diagnostic accuracy has improved using navigated bronchoscopy compared with traditional bronchoscopy. We believe that there is room for improvement in the diagnostic success rate by further refinement of methods, approaches, and tools used in navigated bronchoscopy.

In neurosurgery, information of blood flow is important to identify and avoid damage to important vessels. Three-dimensional intraoperative ultrasound color-Doppler imaging has proven useful in this respect. However, due to Doppler angle-dependencies and the complexity of the vascular architecture, clinical valuable 3-D information of flow direction and velocity is currently not available. In this work, we aim to correct for angle-dependencies in 3-D flow images based on a geometric model of the neurovascular tree generated on-the-fly from free-hand 2-D imaging and an accurate position sensor system. The 3-D vessel model acts as a priori information of vessel orientation used to angle-correct the Doppler measurements, as well as provide an estimate of the average flow direction. Based on the flow direction we were also able to do aliasing correction to approximately double the measurable velocity range. In vitro experiments revealed a high accuracy and robustness for estimating the mean direction of flow. Accurate angle-correction of axial velocities were possible given a sufficient beam-to-flow angle for at least parts of a vessel segment . In vitro experiments showed an absolute relative bias of 9.5% for a challenging low-flow scenario. The method also showed promising results in vivo, improving the depiction of flow in the distal branches of intracranial aneurysms and the feeding arteries of an arteriovenous malformation. Careful inspection by an experienced surgeon confirmed the correct flow direction for all in vivo examples.

Background: Intraoperative ultrasound imaging is used in brain tumor surgery to identify tumor remnants. The ultrasound images may in some cases be more difficult to interpret in the later stages of the operation than in the beginning of the operation. The aim of this paper is to explain the causes of surgically induced ultrasound artefacts and how they can be recognized and reduced., Methods: The theoretical reasons for artefacts are addressed and the impact of surgery is discussed. Different setups for ultrasound acquisition and different acoustic coupling fluids to fill up the resection cavity are evaluated with respect to improved image quality., Results: The enhancement artefact caused by differences in attenuation of the resection cavity fluid and the surrounding brain is the most dominating surgically induced ultrasound artefact. The influence of the artefact may be reduced by inserting ultrasound probes with small footprint into the resection cavity for a close-up view of the areas with suspected tumor remnants. A novel acoustic coupling fluid developed for use during ultrasound imaging in brain tumor surgery has the potential to reduce surgically induced ultrasound artefacts to a minimum., Conclusions: Surgeons should be aware of artefacts in ultrasound images that may occur during brain tumor surgery. Techniques to identify and reduce image artefacts are useful and should be known to users of ultrasound in brain tumor surgery.