Showing papers presented at "Computer Assisted Radiology and Surgery in 2010"
••
15 May 2010
TL;DR: Medical application of rapid prototyping is feasible for specialized surgical planning and prosthetics applications and has significant potential for development of new medical applications.
Abstract: Generation of graspable three-dimensional objects applied for surgical planning, prosthetics and related applications using 3D printing or rapid prototyping is summarized and evaluated. Graspable 3D objects overcome the limitations of 3D visualizations which can only be displayed on flat screens. 3D objects can be produced based on CT or MRI volumetric medical images. Using dedicated post-processing algorithms, a spatial model can be extracted from image data sets and exported to machine-readable data. That spatial model data is utilized by special printers for generating the final rapid prototype model. Patient–clinician interaction, surgical training, medical research and education may require graspable 3D objects. The limitations of rapid prototyping include cost and complexity, as well as the need for specialized equipment and consumables such as photoresist resins. Medical application of rapid prototyping is feasible for specialized surgical planning and prosthetics applications and has significant potential for development of new medical applications.
1,362 citations
••
01 Mar 2010TL;DR: While the components of the MiroSurge system are shown to fulfil the rigid design requirements for robotic telesurgery with force feedback, the system remains versatile, which is supposed to be a key issue for the further development and optimisation.
Abstract: Research on surgical robotics demands systems for evaluating scientific approaches. Such systems can be divided into dedicated and versatile systems. Dedicated systems are designed for a single surgical task or technique, whereas versatile systems are designed to be expandable and useful in multiple surgical applications. Versatile systems are often based on industrial robots, though, and because of this, are hardly suitable for close contact with humans. To achieve a high degree of versatility the Miro robotic surgery platform (MRSP) consists of versatile components, dedicated front–ends towards surgery and configurable interfaces for the surgeon. This paper presents MiroSurge, a configuration of the MRSP that allows for bimanual endoscopic telesurgery with force feedback. While the components of the MiroSurge system are shown to fulfil the rigid design requirements for robotic telesurgery with force feedback, the system remains versatile, which is supposed to be a key issue for the further development and optimisation.
281 citations
••
01 Mar 2010
TL;DR: The presented illustration methods are beneficial for distance assessment in surgical AR and to increase the safety of interventions with the proposed approach, the reduction of inaccuracies in tracking and registration is a subject of the current research.
Abstract: Purpose
Augmented reality (AR) obtains increasing acceptance in the operating room. However, a meaningful augmentation of the surgical view with a 3D visualization of planning data which allows reliable comparisons of distances and spatial relations is still an open request.
130 citations
••
19 May 2010TL;DR: The proposed technique maps diagnosis-relevant criteria inspired by diagnosis procedures based on the advise of an eye expert to quantitative and objective features related to image quality and automatically produces reliable and objective results in determining the image quality of retinal fundus photos.
Abstract: Objective
Automated, objective and fast measurement of the image quality of single retinal fundus photos to allow a stable and reliable medical evaluation.
96 citations
••
01 Jan 2010TL;DR: This study verified the effectiveness of two-stage segmentation with spatial standardization of pancreas in delineating the Pancreas region, patient-specific probabilistic atlas guided segmentation in reducing false negatives, and a classifier ensemble in boosting segmentation performance.
Abstract: Purpose We propose an automated pancreas segmentation algorithm from contrast-enhanced multiphase computed tomography (CT) and verify its effectiveness in segmentation. Methods The algorithm is characterized by three unique ideas. First, a two-stage segmentation strategy with spatial standardization of pancreas was employed to reduce variations in the pancreas shape and location. Second, patientspecific probabilistic atlas guided segmentation was developed to cope with the remaining variability in shape and location. Finally, a classifier ensemble was incorporated to refine the rough segmentation results. Results The effectiveness of the proposed algorithm was validated with 20 unknown CT volumes, as well as three on-site CT volumes distributed in a competition of pancreas segmentation algorithms. The experimental results indicated that the segmentation performance was enhanced by the proposed algorithm, and the Jaccard index between an extracted pancreas and a true one was 57.9%. Conclusions This study verified the effectiveness of twostage segmentation with spatial standardization of pancreas in delineating the pancreas region, patient-specific probabi
79 citations
••
01 May 2010TL;DR: The results indicate that considerable brain shift happens before micro-electrode recordings in DBS but also that brain shift affects the creation of accurate functional atlases, and care must be taken when building and using such atlase of intra-operative data and also when using intra-operatively data to validate anatomical atlased.
Abstract: Purpose
In the recent past many groups have tried to build functional atlases of the deep brain using intra-operatively acquired information such as stimulation responses or micro-electrode recordings An underlying assumption in building such atlases is that anatomical structures do not move between pre-operative imaging and intra-operative recording In this study, we present evidences that this assumption is not valid We quantify the effect of brain shift between pre-operative imaging and intra-operative recording on the creation of functional atlases using intra-operative somatotopy recordings and stimulation response data
70 citations
••
01 May 2010
TL;DR: A GPU-based framework to perform organ segmentation in N-dimensional (ND) medical image datasets by computation of weighted distances using the Ford–Bellman algorithm is presented and can be implemented in low cost vendor-independent graphics hardware.
Abstract: We present a GPU-based framework to perform organ segmentation in N-dimensional (ND) medical image datasets by computation of weighted distances using the Ford–Bellman algorithm (FBA). Our GPU implementation of FBA gives an alternative and optimized solution to other graph-based segmentation techniques. Given a number of K labelled-seeds, the segmentation algorithm evolves and segments the ND image in K objects. Each region is guaranteed to be connected to seeds with the same label. The method uses a Cellular Automata (CA) to compute multiple shortest-path-trees based on the FBA. The segmentation result is obtained by K-cuts of the graph in order to separate it in K sets. A quantitative evaluation of the method was performed by measuring renal volumes of 20 patients based on magnetic resonance angiography (MRA) acquisitions. Inter-observer reproducibility, accuracy and validity were calculated and associated computing times were recorded. In a second step, the computational performances were evaluated with different graphics hardware and compared to a CPU implementation of the method using Dijkstra’s algorithm. The ICC for inter-observer reproducibility of renal volume measurements was 0.998 (0.997–0.999) for two radiologists and the absolute mean difference between the two readers was lower than 1.2% of averaged renal volumes. The validity analysis shows an excellent agreement of our method with the results provided by a supervised segmentation method, used as reference. The formulation of the FBA in the form of a CA is simple, efficient and straightforward, and can be implemented in low cost vendor-independent graphics hardware. The method can efficiently be applied to perform organ segmentation and quantitative evaluation in clinical routine.
61 citations
••
01 Mar 2010
TL;DR: The method is suitable for the estimation of pose differences of the human rib cage in binary projection images and able to provide crucial 3D information for registration during the generation of 2D subtraction images.
Abstract: This paper describes an approach for the three-dimensional (3D) shape and pose reconstruction of the human rib cage from few segmented two-dimensional (2D) projection images. Our work is aimed at supporting temporal subtraction techniques of subsequently acquired radiographs by establishing a method for the assessment of pose differences in sequences of chest radiographs of the same patient. The reconstruction method is based on a 3D statistical shape model (SSM) of the rib cage, which is adapted to binary 2D projection images of an individual rib cage. To drive the adaptation we minimize a distance measure that quantifies the dissimilarities between 2D projections of the 3D SSM and the projection images of the individual rib cage. We propose different silhouette-based distance measures and evaluate their suitability for the adaptation of the SSM to the projection images. An evaluation was performed on 29 sets of biplanar binary images (posterior–anterior and lateral). Depending on the chosen distance measure, our experiments on the combined reconstruction of shape and pose of the rib cages yield reconstruction errors from 2.2 to 4.7mm average mean 3D surface distance. Given a geometry of an individual rib cage, the rotational errors for the pose reconstruction range from 0.1° to 0.9°. The results show that our method is suitable for the estimation of pose differences of the human rib cage in binary projection images. Thus, it is able to provide crucial 3D information for registration during the generation of 2D subtraction images.
59 citations
••
01 Mar 2010TL;DR: The automated insertion tool has proven its capability to perform electrode insertions with final insertion depth angles within the target range of a standard cochlear implant surgery.
Abstract: Atraumatic electrode insertion has been identified to be a crucial step for the preservation of residual hearing abilities, which allows hybrid electro-acoustic stimulation (EAS). The authors propose a tool for automation of the insertion process to achieve this. General benefits as well as concept and design of an automated insertion tool are presented. Thirty insertions of Nucleus 24 Contour Advance Practice Electrodes in an artificial scala tympani model as well as 20 insertions in a human cochlea specimen were performed using the tool, implementing the AOS technique. For both studies, the achieved insertion depth angle was evaluated by photographic or X-ray documentation. The mean achieved insertion depth angle was 410° for the lubricated model and 330° for the human cochlea specimen. The automated insertion tool has proven its capability to perform electrode insertions with final insertion depth angles within the target range of a standard cochlear implant surgery. Additionally, to the knowledge of the authors, it represents the only possibility to automatically insert cochlear implant electrodes via minimally invasive approaches.
57 citations
••
27 Apr 2010
TL;DR: The concept is generic and can be adapted to facilitate the safety engineering approach defined in several standards that employ the concept of integrity or assurance levels including ISO 26262, the emerging automotive safety standard.
Abstract: In this paper, we describe a concept for the automatic allocation of general Safety Integrity Levels (SILs) to subsystems and components of complex hierarchical networked architectures that deliver sets of safety critical functions. The concept is generic and can be adapted to facilitate the safety engineering approach defined in several standards that employ the concept of integrity or assurance levels including ISO 26262, the emerging automotive safety standard. SIL allocation is facilitated by HiP-HOPS, an automated safety analysis tool, and can be performed in the context of development using EAST-ADL2, an automotive architecture description language. The process rationalizes complex risk allocation and leads to optimal/economic allocation of SILs.
55 citations
••
01 Mar 2010
TL;DR: A system that integrates an existing virtual endoscopy system originally designed for pre-operative planning of pituitary surgery with a professional intra-operative navigation system is proposed and the visualization of hidden anatomical structures behind the bony walls of the sphenoid sinus during the sellar phase of the surgery has been found most beneficial.
Abstract: Purpose
Virtual endoscopy has already proven its benefit for pre-operative planning of endoscopic pituitary surgery. The translation of such a system into the operating room is a logical consequence, but only a few general intra-operative image guided systems providing virtual endoscopic images have been proposed so far. A discussion of related visualization and interaction problems occurring during sinus and pituitary surgery is still missing.
••
01 Mar 2010TL;DR: The study confirms the functionality and reliability of the automated insertion tool for insertion of preformed CI and improves insertion strategies considering patient-specific anatomy become possible.
Abstract: As a substantial part of our concept of a minimally invasive cochlear implant (CI) surgery, we developed an automated insertion tool. Studies on an artificial scala tympani model were performed in order to evaluate force application when using the insertion tool. Contour electrodes were automatically inserted into a transparent cochlea model in Advance Off-Stylet technique. Occurring forces were measured by the use of a load cell and correlated with observed intracochlear movement of the electrode carriers. Mean insertion forces were measured up to 20 mN comparable to previous studies on temporal bones. The most influencing factor is the implant’s 2D curling behaviour in comparison to the 3D helical shape of the cochlea. The study confirms the functionality and reliability of the automated insertion tool for insertion of preformed CI. Improved insertion strategies considering patient-specific anatomy become possible.
••
01 May 2010TL;DR: The proposed model that incorporates disc appearance, location, and context achieves high accuracy for detection of abnormal discs and shows the extendability of the proposed model to subsequent diagnosis tasks specific to each intervertebral disc abnormality such as desiccation and herniation.
Abstract: Purpose Detection of abnormal discs from clinical T2-weighted MR Images. This aids the radiologist as well as subsequent CAD methods in focusing only on abnormal discs for further diagnosis. Furthermore, it gives a degree of confidence about the abnormality of the intervertebral discs that helps the radiologist in making his decision. Materials and methods We propose a probabilistic classifier for the detection of abnormality of intervertebral discs. We usethreefeaturestolabelabnormaldiscsthatincludeappearance, location, and context. We model the abnormal disc appearance with a Gaussian model, the location with a 2D Gaussian model, and the context with a Gaussian model for the distance between abnormal discs. We infer on the middle slice of the T2-weighted MRI volume for each case. These MRI scans are specific for the lumbar area. We obtain our gold standard for the ground truth from our collaborating radiologist group by having the clinical diagnosis report for each case. Results We achieve over 91% abnormality detection accuracy in a cross-validation experiment with 80 clinical cases. The experiment runs ten rounds; in each round, we randomly leave 30 cases out for testing and we use the other 50 cases for training. Conclusion Weachievehighaccuracyfordetectionofabnormal discs using our proposed model that incorporates disc appearance,location,andcontext.Weshowtheextendability
••
21 Jul 2010TL;DR: The visualization of intracranial arteries in static 3D models from intrac Cranial time-of-flight MR angiography (MRA) was improved by the use of an autostereoscopic display.
Abstract: An autostereoscopic display with image quality comparable to ordinary 2D displays has recently been developed. The purpose of our study was to evaluate whether the visualization of static 3D models from intracranial time-of-flight (TOF) MR angiography (MRA) was improved by this display. Maximum Intensity Projection (MIP) and Volume Rendering (VR) 3D models of intracranial arteries were created from ten TOF MRA datasets. Thirty-one clinically relevant intracranial arterial segments were marked in the TOF source images. A total of 217 markings were used. The markings were displayed in the 3D models as overlying red dots. Three neuroradiologists viewed the static 3D models on the autostereoscopic display, with the display operating either in autostereoscopic mode or in 2D mode. The task of the neuroradiologists was to correctly identify the marked artery. A paired comparison was made between arterial identification in autostereoscopic and 2D display mode. In 314 MIP 3D models, 233 arterial markings (74%) were correctly identified with the display operating in autostereoscopic mode versus 179 (57%) in 2D mode. Odds ratio for correct identification with autostereoscopic mode versus 2D mode was 2.17 (95% confidence interval 1.55–3.04, P < 0.001). In 337 VR 3D models, 256 markings (76%) were correctly identified using autostereoscopic mode and 229 (68%) using 2D mode (odds ratio 1.49, 95% confidence interval 1.06–2.09, P = 0.021). The visualization of intracranial arteries in static 3D models from TOF MRA can be improved by the use of an autostereoscopic display.
••
24 Feb 2010TL;DR: A standardized optimum protocol to dissect prostatectomy specimens is needed for the validation of medical imaging modalities by histologic correlation, which can enhance disease management by improving the comparability between different modalities.
Abstract: Purpose
There is a need for methods which enable precise correlation of histologic sections with in vivo prostate images. Such methods would allow direct comparison between imaging features and functional or histopathological heterogeneity of tumors. Correlation would be particularly useful for validating the accuracy of imaging modalities, developing imaging techniques, assessing image-guided therapy, etc. An optimum prostate slicing method for accurate correlation between the histopathological and medical imaging planes in terms of section angle, thickness and level was sought.
••
27 Apr 2010
TL;DR: This paper reports on experience gained with the application of ISO 26262 in a pilot project at a German car manufacturer as well as experience from various consultancy projects, and recommends a transition from a document-centric approach to safety analysis and associated documentation to a model-based approach.
Abstract: Automotive manufacturers and suppliers need to follow the requirements stated in ISO DIS 26262 since it is now published state-of-the-art. In this paper we report on experience gained with the application of ISO 26262 in a pilot project at a German car manufacturer as well as experience from various consultancy projects, and recommend a transition from a document-centric approach to safety analysis and associated documentation to a model-based approach.
••
01 May 2010
TL;DR: The employed WFD approach was successful to discriminate and numbering of the teeth in the presence of missing teeth, independent of anatomical information such as knowing the sequence of teeth and the location of each tooth in the jaw.
Abstract: Teeth arrangement is essential in face ergonomics and healthiness. In addition, they play key roles in forensic medicine. Various computer-assisted procedures for medical application in quantitative dentistry require automatic classification and numbering of teeth in dental images. In this paper, we propose a multi-stage technique to classify teeth in multi-slice CT (MSCT) images. The proposed algorithm consists of the following three stages: segmentation, feature extraction and classification. We segment the teeth by employing several techniques including Otsu thresholding, morphological operations, panoramic re-sampling and variational level set. In the feature extraction stage, we follow a multi-resolution approach utilizing wavelet-Fourier descriptor (WFD) together with a centroid distance signature. We compute the feature vector of each tooth by employing the slice associated with largest tooth tissues. The feature vectors are employed for classification in the third stage. We perform teeth classification by a conventional supervised classifier. We employ a feed- forward neural network classifier to discriminate different teeth from each other. The performance of the proposed method was evaluated in the presence of 30 different MSCT data sets including 804 teeth. We compare classification results of the WFD technique with Fourier descriptor (FD) and wavelet descriptor (WD) techniques. We also investigate the invariance properties of the WFD technique. Experimental results reveal the effectiveness of the proposed method. We provided an integrated solution for teeth classification in multi-slice CT datasets. In this regard, suggested segmentation technique was successful to separate teeth from each other. The employed WFD approach was successful to discriminate and numbering of the teeth in the presence of missing teeth. The solution is independent of anatomical information such as knowing the sequence of teeth and the location of each tooth in the jaw.
••
03 Aug 2010TL;DR: A new method of computing patient-specific abduction and anteversion angles from a CT study of the anterior pelvic plane and the left and right acetabular rim planes was reliable and accurate and it was found that the acetABular rim plane can be reliably and accurately computed from identified points on the rim.
Abstract: Purpose
Understanding acetabular orientation is important in many orthopaedic procedures. Acetabular orientation, usually described by anteversion and abduction angles, has uncertain measurement variability in adult patients. The goals of this study are threefold: (1) to describe a new method for computing patient-specific abduction/anteversion angles from a single CT study based on the identification of anatomical landmarks and acetabular rim points; (2) to quantify the inaccuracies associated with landmark selection in computing the acetabular angles; and (3) to quantify the variability and symmetry of acetabular orientation.
••
16 Mar 2010
TL;DR: A fast adaptive B-spline snake algorithm that resolves the computational concerns of conventional active contours and avoids computationally expensive optimizations was developed for automatic segmentation of the left ventricular endocardial boundary in echocardiographic images.
Abstract: Purpose
A fast and robust algorithm was developed for automatic segmentation of the left ventricular endocardial boundary in echocardiographic images. The method was applied to calculate left ventricular volume and ejection fraction estimation.
••
01 Mar 2010TL;DR: To model laser bone ablation in microsurgery the volume and shape of each laser pulse should be known and considered in the process of ablation planning and simulation.
Abstract: Laser ablation of hard tissue is not completely understood until now and not modeled for computer-assisted microsurgery. A precise planning and simulation is an essential step toward the usage of microsurgical laser bone ablation in the operating room. Planning the volume for laser bone ablation is based on geometrical definitions. Shape and volume of the removed bone by single laser pulses were measured with a confocal microscope for modeling the microsurgical ablation. To remove the planned volume and to achieve smooth surfaces, a simulation of the laser pulse distribution is developed. The confocal measurements show a clear dependency from laser energy and resulting depth. Two-dimensional Gaussian functions are fitting in these craters. Exemplarily three ablation layers were planned, simulated, executed and verified. To model laser bone ablation in microsurgery the volume and shape of each laser pulse should be known and considered in the process of ablation planning and simulation.
••
27 Apr 2010TL;DR: The different steps of a method for expressing non functional requirements and ensuring their validation and their traceability over a design flow for automotive system design are presented based on the conjoint use of EAST-ADL2 and MARTE languages and supported in an Eclipse platform.
Abstract: Safety engineering analysis is a mandatory stage in the design of critical embedded automotive systems. The derivation of safety requirements and their verification require establishing traceability links between requirements and the different artifacts involved in the design flow. This paper presents the different steps of a method for expressing non functional requirements (safety, timing, hardware, performance) and ensuring their validation and their traceability over a design flow for automotive system design based on the conjoint use of EAST-ADL2 and MARTE languages and supported in an Eclipse platform. A specific meta-model for requirements modeling and traceability is used. The methodology is illustrated on an industrial knock-control system characterized by strict safety and temporal constraints
••
18 May 2010TL;DR: This self-propelled robotic endoscope has potential as an alternative to current fibre optic colonoscopy examination methods, especially with the addition of new sensors under development.
Abstract: Purpose
Fibre optic colonoscopy is usually performed with manual introduction and advancement of the endoscope, but there is potential for a robot capable of locomoting autonomously from the rectum to the caecum. A prototype robot was designed and tested.
••
09 Apr 2010
TL;DR: Eight distinctive strategies for PACS strategic situational planning are defined that allow decision-makers in hospitals to decide which approach best suits their hospitals’ current situation and future ambition and what in principle is needed to evolve through the different maturity levels.
Abstract: Purpose
While many hospitals are re-evaluating their current Picture Archiving and Communication System (PACS), few have a mature strategy for PACS deployment. Furthermore, strategies for implementation, strategic and situational planning methods for the evolution of PACS maturity are scarce in the scientific literature. Consequently, in this paper we propose a strategic planning method for PACS deployment. This method builds upon a PACS maturity model (PMM), based on the elaboration of the strategic alignment concept and the maturity growth path concept previously developed in the PACS domain.
••
01 May 2010TL;DR: The method used to estimate the GT is important: the differences highlighted that STAPLE and TESD, notwithstanding a few weaknesses, appear to be equally viable as a GT estimator, while the increased availability of computing power is decreasing the appeal afforded to TPMs.
Abstract: Knowledge of the exact shape of a lesion, or ground truth (GT), is necessary for the development of diagnostic tools by means of algorithm validation, measurement metric analysis, accurate size estimation. Four methods that estimate GTs from multiple readers’ documentations by considering the spatial location of voxels were compared: thresholded Probability-Map at 0.50 (TPM0.50) and at 0.75 (TPM0.75), simultaneous truth and performance level estimation (STAPLE) and truth estimate from self distances (TESD). A subset of the publicly available Lung Image Database Consortium archive was used, selecting pulmonary nodules documented by all four radiologists. The pair-wise similarities between the estimated GTs were analyzed by computing the respective Jaccard coefficients. Then, with respect to the readers’ marking volumes, the estimated volumes were ranked and the sign test of the differences between them was performed. (a) the rank variations among the four methods and the volume differences between STAPLE and TESD are not statistically significant, (b) TPM0.50 estimates are statistically larger (c) TPM0.75 estimates are statistically smaller (d) there is some spatial disagreement in the estimates as the one-sided 90% confidence intervals between TPM0.75 and TPM0.50, TPM0.75 and STAPLE, TPM0.75 and TESD, TPM0.50 and STAPLE, TPM0.50 and TESD, STAPLE and TESD, respectively, show: [0.67, 1.00], [0.67, 1.00], [0.77, 1.00], [0.93, 1.00], [0.85, 1.00], [0.85, 1.00]. The method used to estimate the GT is important: the differences highlighted that STAPLE and TESD, notwithstanding a few weaknesses, appear to be equally viable as a GT estimator, while the increased availability of computing power is decreasing the appeal afforded to TPMs. Ultimately, the choice of which GT estimation method, between the two, should be preferred depends on the specific characteristics of the marked data that is used with respect to the two elements that differentiate the method approaches: relative reliabilities of the readers and the reliability of the region boundaries.
••
27 Apr 2010TL;DR: This paper sketches out the recent work on conditional safety certificates, which facilitate dynamic safety evaluation in the wake of current computing trends like Car2Car and suggests promising research directions for the future.
Abstract: In the wake of current computing trends like Ubiquitous Computing, Ambient Intelligence and Cyber Physical Systems, new application domains like Car2Car emerged. One key characteristic of these new application domains is their openness with respect to dynamic integration of devices and components. It is obvious that traditional safety assurance techniques, both state of the practice and state of the art, are not sufficient in this context. A possible solution approach would be to shift portions of the safety assurance process into run time. This can be reached by the integration of appropriate run time safety models and corresponding dynamic evaluation mechanisms. In this paper we sketch out our recent work on conditional safety certificates, which facilitate such dynamic safety evaluation. We conclude with a brief discussion and state promising research directions for the future.
••
01 May 2010TL;DR: Newly developed software that can provide fast coronary artery segmentation and accurate centerline extraction for later lesion visualization and quantitative measurement while minimizing user interaction is presented.
Abstract: Purpose
To present newly developed software that can provide fast coronary artery segmentation and accurate centerline extraction for later lesion visualization and quantitative measurement while minimizing user interaction.
••
27 Apr 2010
TL;DR: SINERGIA laparoscopic virtual reality simulator is able to discriminate subjects according to their level of experience in Laparoscopic surgery; therefore, it can be used within a training program as an assessment tool.
Abstract: Purpose
Laparoscopic techniques have nowadays become a gold standard in many surgical procedures, but they imply a more difficult learning skills process. Simulators have a fundamental role in the formative stage of new surgeons. This paper presents the construct and face validity of SINERGIA laparoscopic virtual reality simulator in order to decide whether it can be considered as an assessment tool.
••
17 May 2010TL;DR: A spatially adaptive active contour technique by introducing local snake bending, to improve traditional snakes performance for segmenting tumors, which outperforms the other two methods, and consistently follows an expert’s annotations.
Abstract: Purpose
Tumor segmentation constitutes a crucial step in simulating cancer growth and response to therapy. Incorporation of imaging data individualizes the simulation and assists clinical correlation with the predicted outcome. We adapted snakes to improve tumor segmentation including difficult cases with inherently inhomogeneous structure and poorly defined margins.
••
09 Apr 2010TL;DR: The proposed workflow management system offers the possibility to embed CBIR conveniently into PACS environments and takes into account the tight and solid organization of scheduled and performed tasks in clinical settings.
Abstract: Purpose
Content-based image retrieval (CBIR) bears great potential for computer-aided diagnosis (CAD). However, current CBIR systems are not able to integrate with clinical workflow and PACS generally. One essential factor in this setting is scheduling. Applied and proved with modalities and the acquisition of images for a long time, we now establish scheduling with CBIR.
••
01 Jan 2010
TL;DR: A tool for classification, analysis, and 3D reconstruction of the hepatic and portal systems, providing a correct and detailed reconstruction even where pathologies have caused morphological and geometrical variations in the vessels.
Abstract: The detection and classification of hepatic vessels in diagnostic images are essential for hepatic pre-surgery planning. Our team has developed a tool for classification, analysis, and 3D reconstruction of the hepatic and portal systems. Our software first extracts a graphic representation of a set of connected voxels, representing both systems. It then calculates two binary volumes representing the main part of the two venous systems. Finally, it combines these results to obtain the correct vessel classification. Segmentation steps are semi-automatic and require about 40 min to complete. Schematization and classification steps are automatic and require about 17 min for results. The software provides a correct and detailed reconstruction even where pathologies have caused morphological and geometrical variations in the vessels. The time required for the entire procedure is compatible with clinical requirements, providing an efficient tool for diagnosis and surgical planning.