Skip to main content

Über dieses Buch

This book constitutes revised selected papers from the 4th International Workshop on Clinical Image-Based Procedures, CLIP 2015, held in conjunction with MICCAI 2015 in Munich, Germany, in October 2015.

The 15 papers presented in this volume were carefully reviewed and selected from 22 submissions. CLIP focuses on translational research; therefore, the goal of the works presented in this workshop is to bring basic research methods closer to the clinical practice. A highlight of this workshop is the subject of strategies for personalized medicine to enhance diagnosis, treatment and interventions.



Accuracy Assessment of CBCT-Based Volumetric Brain Shift Field

The displacement of the brain parenchyma during open brain surgery, known as ‘brain shift’, affects the applicability of pre-operative planning and affects the outcome of the surgery. In this article we investigated the accuracy of a novel method to intra-operatively determine the brain shift displacement field throughout the whole brain volume. The brain shift displacement was determined by acquiring contrast enhanced cone-beam CT before and during the surgery. The respective datasets were pre-processed, landmark enhanced, and elastically registered to find the displacement field. The accuracy of this method was evaluated by artificially creating post-operative data with a known ground truth deformation. The artificial post-operative data was obtained by applying the deformation field from one patient on the pre-operative data of another patient, which was repeated for three patients. The mean error that was found with this method ranged from 1 to 2 mm, while the standard deviation was about 1 mm.

Iris Smit-Ockeloen, Daniel Ruijters, Marcel Breeuwer, Drazenko Babic, Olivier Brina, Vitor Mendes Pereira

CRIMSON: Towards a Software Environment for Patient-Specific Blood Flow Simulation for Diagnosis and Treatment

In this paper, we introduce the new software environment CRIMSON: CardiovasculaR Integrated Modelling and SimulatiON. This software provides a number of tools for medical image data analysis, preprocessing, segmentation and blood flow simulation. In this paper we describe the work flow necessary to perform such tasks as well its implementation in CRIMSON based on multiple well-established open-source libraries, such as MITK and OpenCASCADE. We show that the software is easy to use for both experts and non-experts in the field of hemodynamic modelling. The intuitive and responsive interface of CRIMSON facilitates learning and speeds up the model building process by up to a factor of two compared to the existing tool being used for the same purpose. The overall goal of this work is to produce a feature-rich and intuitive open-source blood flow modelling framework that can be used both by engineers and medical personnel.

Rostislav Khlebnikov, C. Alberto Figueroa

Atlas-Guided Transcranial Doppler Ultrasound Examination with a Neuro-Surgical Navigation System: Case Study

Transcranial Doppler (TCD) sonography is a special ultrasound (US) technique that can image and measure the blood flow within certain cerebral blood vessels through bone windows of the human skull. As a relatively inexpensive and portable medical imaging modality, it has shown great applications in the diagnosis and monitoring of a range of neurovascular conditions. However, due to the challenges in imaging through the skull, interpretation of anatomical structures and quick localization of blood vessels in sonograpy can often be difficult. To make the TCD examination more efficient and intuitive, we propose to employ a population-averaged human head atlas that includes a probabilistic blood vessel map and a standard head MRI template to guide the procedure. Using the system, spatially tracked ultrasound images are augmented with the atlas in a navigation system through landmark-based and automated US-MRI registration. A case study of a healthy subject is presented to demonstrate the performance of the proposed technique, and the system is expected to be applied both in clinics and in training.

Yiming Xiao, Ian J. Gerard, Vladimir Fonov, Dante De Nigris, Catherine Therrien, Bèrengére Aubert-Broche, Simon Drouin, Anna Kochanowska, Donatella Tampieri, D. Louis Collins

Improving Patient Specific Neurosurgical Models with Intraoperative Ultrasound and Augmented Reality Visualizations in a Neuronavigation Environment

We present our work to combine intraoperative ultrasound imaging and augmented reality visualization to improve the use of patient specific models throughout image-guided neurosurgery in the context of tumour resections. Preliminary results in a study of 3 patients demonstrate the successful combination of the two technologies as well as improved accuracy of the patient-specific models throughout the surgery. The augmented reality visualizations enabled the surgeon to accurately visualize the anatomy of interest for an extended period of the intervention. These results demonstrate the potential for these technologies to become useful tools for neurosurgeons to improve patient-specific planning by prolonging the use of reliable neuronavigation.

Ian J. Gerard, Marta Kersten-Oertel, Simon Drouin, Jeffery A. Hall, Kevin Petrecca, Dante De Nigris, Tal Arbel, D. Louis Collins

Patient-Specific Cranial Nerve Identification Using a Discrete Deformable Contour Model for Skull Base Neurosurgery Planning and Simulation

In this paper, we present a minimally supervised method for the identification of the intra-cranial portion of cranial nerves, using a novel, discrete 1-Simplex 3D active contour model. The clinical applications include planning and personalized simulation of skull base neurosurgery. The centerline of a cranial nerve is initialized from two user-supplied end points by computing a Minimal Path. The 1-Simplex is a Newtonian model for vertex motion, where every non-endpoint vertex has 2-connectivity with neighboring vertices, with which it is linked by edges. The segmentation behavior of the model is governed by the equilibrium between internal and external forces. The external forces include an image force that favors a centered path within high-vesselness points. The method is validated quantitatively using synthetic and real MRI datasets.

Sharmin Sultana, Jason E. Blatt, Yueh Lee, Matthew Ewend, Justin S Cetas, Anthony Costa, Michel A. Audette

Prediction of Rib Motion During Free-Breathing from Liver Observations Using 4D MRI

Magnetic resonance guided high intensity focused ultrasound (MRgHIFU) is a new therapy for treating malignant liver tissues. However, the motion of the ribs in the beam path may compromise an effective and safe treatment. Due to poor visibility of bones in MR and US liver images, tracking them in real time is currently not feasible. We propose a method for modeling and registration of the respiratory motion of the ribs. Moreover, we show that it is possible to predict the ribs’ motion based on a few tracked points in the liver. Our registration had a mean error of 1.06 mm for deep inhalations with an average motion of 2.71 mm. We developed subject-specific and population-based modeling methods, which recover 60 % and 40 % of the respiratory motion extracted through registration, respectively. To the best of our knowledge, this is the first time the ribs’ motion due to respiration has been directly studied during free breathing over a relatively long time (100 breathing cycles).

Golnoosh Samei, Gábor Székely, Christine Tanner

Efficient and Extensible Workflow: Reliable Whole Brain Segmentation for Large-Scale, Multi-center Longitudinal Human MRI Analysis Using High Performance/Throughput Computing Resources

Advances in medical image applications have led to mounting expectations in regard to their impact on neuroscience studies. In light of this fact, a comprehensive application is needed to move neuroimaging data into clinical research discoveries in a way that maximizes collected data utilization and minimizes the development costs. We introduce BRAINS AutoWorkup, a Nipype based open source MRI analysis application distributed with BRAINSTools suite ( This work describes the use of efficient and extensible automated brain MRI analysis workflow for large-scale multi-center longitudinal studies. We first explain benefits of our extensible workflow development using Nipype, including fast integration and validation of recently introduced tools with heterogeneous software infrastructures. Based on this workflow development, we also discuss our recent advancements to the workflow for reliable and accurate analysis of multi-center longitudinal data. In addition to Nipype providing a unified workflow, its support for High Performance Computing (HPC) resources leads to a further increased time efficiency of our workflow. We show our success on a few selected large-scale studies, and discuss future direction of this translation research in medical imaging applications.

Regina EY Kim, Peg Nopoulos, Jane Paulsen, Hans Johnson

Navigation Path Retrieval from Videobronchoscopy Using Bronchial Branches

Bronchoscopy biopsy can be used to diagnose lung cancer without risking complications of other interventions like transthoracic needle aspiration. During bronchoscopy, the clinician has to navigate through the bronchial tree to the target lesion. A main drawback is the difficulty to check whether the exploration is following the correct path. The usual guidance using fluoroscopy implies repeated radiation of the clinician, while alternative systems (like electromagnetic navigation) require specific equipment that increases intervention costs. We propose to compute the navigated path using anatomical landmarks extracted from the sole analysis of videobronchoscopy images. Such landmarks allow matching the current exploration to the path previously planned on a CT to indicate clinician whether the planning is being correctly followed or not. We present a feasibility study of our landmark based CT-video matching using bronchoscopic videos simulated on a virtual bronchoscopy interactive interface.

Carles Sánchez, Marta Diez-Ferrer, Jorge Bernal, F. Javier Sánchez, Antoni Rosell, Debora Gil

Left Atrial Wall Segmentation from CT for Radiofrequency Catheter Ablation Planning

Atrial fibrillation is the most common cardiac arrhythmia and a major cause of ischemic stroke. It is believed that measurements of the thickness of a patient’s left atrial wall can improve understanding of the patient’s disease state, as well as assist in treatment planning for radiofrequency catheter ablation. Left atrial wall thickness can be measured and visualized from segmented contrast-enhanced cardiac CT images, but segmentation itself is challenging. Here we present a pipeline for segmenting the left atrial wall, using a hierarchical constraint structure in order to distinguish between the atrial wall and other muscular structures. Using this approach, the left atrial wall was successfully differentiated from adjacent structures such as the aortic wall. The method was compared to manual segmentation on ten clinical CT images of patients undergoing radiofrequency catheter ablation for atrial fibrillation. Similarity between the methods, by Dice coefficient, was found to be 0.79, and the rMSE of the epicardial segmentation was found to be 0.86 mm. A roadmap to automation for clinical translation is also presented.

Jiro Inoue, John S. H. Baxter, Maria Drangova

Classification of Tumor Epithelium and Stroma in Colorectal Cancer Based on Discrete Tchebichef Moments

Colorectal cancer is a major cause of mortality. As the disease progresses, adenomas and their surrounding tissue are modified. Therefore, a large number of samples from the epithelial cell layer and stroma must be collected and analyzed manually to estimate the potential evolution and stage of the disease. In this study, we propose a novel method for automatic classification of tumor epithelium and stroma in digitized tissue microarrays. To this end, we use discrete Tchebichef moments (DTMs) to characterize tumors based on their textural information. DTMs are able to capture image features in a non-redundant way providing a unique description. A support vector machine was trained to classify a dataset composed of 1376 tissue microarrays from 643 patients with colorectal cancer. The proposal achieved 97.62 % of sensitivity and 95 % of specificity showing the effectiveness of the methodology.

Rodrigo Nava, Germán González, Jan Kybic, Boris Escalante-Ramírez

From Subjective to Objective: Quantitative Computerized Monitoring Tool for MRI-guided Cryoablation

During percutaneous ablations, interventionalists currently rely on subjective assessments of procedural images to determine if the ablation is successful and the extent of injury to the surrounding tissues. In order to provide an objective assessment of these images, we developed a unified software package for monitoring MRI-guided cryoablation in real-time. We assessed its feasibility and functionality within the workflow of renal tumor cryoablation procedures using images from 13 MRI-guided renal tumor cryoablation procedures. This retrospective study demonstrated that the software package met the real-time requirements with 92 % success. We were therefore able to develop a comprehensive, real-time, interventionalist-friendly software package for quantitative monitoring of MRI-guided percutaneous cryoablation procedures, which aides in the assessment of tumor eradication and is compatible with the clinical workflow of these procedure. This tool has the potential to minimize damage to surrounding parenchyma and nearby critical structures, thereby enhancing patient safety and treatment success.

Jonathan Scalera, Xinyang Liu, Gary P. Zientara, Kemal Tuncali

Monopolar Stimulation of the Implanted Cochlea: A Synthetic Population-Based Study

Cochlear implantation is carried out to recover the sense of hearing. However, its functional outcome varies highly between patients. In the current work, we present a study to assess the functional outcomes of cochlear implants considering the inter-variability found among a population of patients. In order to capture the cochlear anatomical details, a statistical shape model is created from high-resolution human $$\mu $$CT data. A population of virtual patients is automatically generated by sampling new anatomical instances from the statistical shape model. For each virtual patient, an implant insertion is simulated and a finite element model is generated to estimate the electrical field created into the cochlea. These simulations are defined according to the monopolar stimulation protocol of a cochlear implant and a prediction of the voltage spread over the population of virtual patients is evaluated.

Nerea Mangado, Mario Ceresa, Hector Dejea, Hans Martin Kjer, Sergio Vera, Rasmus R. Paulsen, Jens Fagertun, Pavel Mistrik, Gemma Piella, Miguel Angel Gonzalez Ballester

Partitioned Shape Modeling with On-the-Fly Sparse Appearance Learning for Anterior Visual Pathway Segmentation

MRI quantification of cranial nerves such as anterior visual pathway (AVP) in MRI is challenging due to their thin small size, structural variation along its path, and adjacent anatomic structures. Segmentation of pathologically abnormal optic nerve (e.g. optic nerve glioma) poses additional challenges due to changes in its shape at unpredictable locations. In this work, we propose a partitioned joint statistical shape model approach with sparse appearance learning for the segmentation of healthy and pathological AVP. Our main contributions are: (1) optimally partitioned statistical shape models for the AVP based on regional shape variations for greater local flexibility of statistical shape model; (2) refinement model to accommodate pathological regions as well as areas of subtle variation by training the model on-the-fly using the initial segmentation obtained in (1); (3) hierarchical deformable framework to incorporate scale information in partitioned shape and appearance models. Our method, entitled PAScAL (PArtitioned Shape and Appearance Learning), was evaluated on 21 MRI scans (15 healthy + 6 glioma cases) from pediatric patients (ages 2–17). The experimental results show that the proposed localized shape and sparse appearance-based learning approach significantly outperforms segmentation approaches in the analysis of pathological data.

Awais Mansoor, Juan J. Cerrolaza, Robert A. Avery, Marius G. Linguraru

Statistical Shape Modeling from Gaussian Distributed Incomplete Data for Image Segmentation

Statistical shape models are widely used in medical image segmentation. However, getting sufficient high quality manually generated ground truth data to generate such models is often not possible due to time constraints of clinical experts. In this work, a method for automatically constructing statistical shape models from incomplete data is proposed. The incomplete data is assumed to be the result of any segmentation algorithm or may originate from other sources, e.g. non expert manual delineations. The proposed work flow consists of (1) identifying areas of high probability in the segmentation output of being a boundary, (2) interpolating between the boundary areas, (3) reconstructing the missing high frequency data in the interpolated areas by an iterative back-projection from other data sets of the same population. For evaluation, statistical shape models where constructed from 63 clinical CT data sets using ground truth data, artificial incomplete data, and incomplete data resulting from an existing segmentation algorithm. The results show that a statistical shape model from incomplete data can be built with an added average error of 6 mm compared to a model built from ground truth data.

Ma Jingting, Katharina Lentzen, Jonas Honsdorf, Lin Feng, Marius Erdt

Open-Source Platform for Prostate Motion Tracking During in-Bore Targeted MRI-Guided Biopsy

Accurate sampling of cancer suspicious locations is critical in targeted prostate biopsy, but can be complicated by the motion of the prostate. We present an open-source software for intra-procedural tracking of the prostate and biopsy targets using deformable image registration. The software is implemented in 3D Slicer and is intended for clinical users. We evaluated accuracy, computation time and sensitivity to initialization, and compared implementations that use different versions of the Insight Segmentation Toolkit (ITK). Our retrospective evaluation used data from 25 in-bore MRI-guided prostate biopsy cases (343 registrations total). Prostate Dice similarity coefficient improved on average by 0.17 (p < 0.0001, range 0.02–0.48). Registration was not sensitive to operator variability. Computation time decreased significantly for the implementation using the latest version of ITK. In conclusion, we presented a fully functional open-source tool that is ready for prospective evaluation during clinical MRI-guided prostate biopsy interventions.

Peter A. Behringer, Christian Herz, Tobias Penzkofer, Kemal Tuncali, Clare M. Tempany, Andriy Fedorov


Weitere Informationen

Premium Partner

Neuer Inhalt

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!