ResearchIssueSegmentation

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Research in Segmentation

Table of Content

Abstract

Modern medical imaging, particular in three and more dimensions, requires computer-aided segmentation methods in order to assist the physician in identifying boundaries of anatomical and pathological objects within clinically feasible times. CAMP covers the spectrum from mathematical modeling and optimization of semi-automatic segmentation methods based on anatomical shape, appearance, texture and temporal variation in various modalities, including MRI, CT, US, PET and SPECT. Applications range from computer-assisted diagnosis to simulation and prediction of disease progression.

Contact Person and Group Coordination

Stefanie Demirci
Nassir Navab




Research Projects in Segmentation

Shape Guided Segmentation of Cardiac Boundaries

Shape Guided Segmentation of Cardiac Boundaries

Prior shape information has been shown to be invaluable for segmenting cardiac boundaries. We develop new methods of exploiting such prior information to guide the segmentation by using techniques of machine learning or formulating the segmentation problem to fit our requirements in segmentation of 4D cardiac data.
patient-Specific Translational research on Atherosclerosis and Diagnosis (STAnD)

patient-Specific Translational research on Atherosclerosis and Diagnosis (STAnD)

Improvement and Automatic Classification of IVUS-VH (Intravascular Ultrasound – Virtual Histology) Images

Improvement and Automatic Classification of IVUS-VH (Intravascular Ultrasound – Virtual Histology) Images

Heart attack and stroke are the major causes of human death and atherosclerotic plaques are the most common effect of cardiovascular disease. Intravascular ultrasound (IVUS), a diagnostic imaging technique, offers a unique view of the morphology of the arterial plaque and displays the morphological and histological properties of a cross-section of the vessel. Limitations of the grayscale IVUS manual plaque assessment have led to the development of quantitative techniques for analysis of characteristics of plaque components. In vivo plaque characterization with the so called Virtual Histology (VH)-IVUS, which is based on the ultrasound RF signal processing, is widely available for atherosclerosis plaque characterization in IVUS images. However, it suffers from a poor longitudinal resolution due to the ECG-gated acquisition. The focus of this PhD? work is to provide effective methods for image-based vessel plaque characterization via IVUS image analysis to overcome the limitations of current techniques. The proposed algorithms are also applicable to the large amount of the IVUS image sequences obtained from patients in the past, where there is no access to the corresponding radio frequency(RF) data. Since the proposed method is applicable to all IVUS frames of the heart cycle, therefore it outperforms the longitudinal resolution of the so called VH method.
Scene Understanding From a Moving Camera

Scene Understanding From a Moving Camera

Modern vehicles are equipped with multiple cameras which are already used in various practical applications. Advanced driver assistance systems (ADAS) are of particular interest because of the safety and comfort features they offer to the driver. Camera based scene understanding is an important scientific problem that has to be addressed in order to provide the information needed for camera based driver assistance systems. While frontal cameras are widely used, there are applications where cameras observing lateral space can deliver better results. Fish eye cameras mounted in the side mirrors are particularly interesting, because they can observe a big area on the side of the vehicle and can be used for several applications for which the traditional front facing cameras are not suitable.

We present a general method for scene understanding using 3D reconstruction of the environment around the vehicle. It is based on pixel-wise image labeling using a conditional random field (CRF). Our method is able to create a simple 3D model of the scene and also to provide semantic labels of the different objects and areas in the image, like for example cars, sidewalks, and buildings.

We demonstrate how our method can be used for two applications that are of high importance for various driver assistance systems - car detection and free space estimation. We show that our system is able to perform in real time for speeds of up to 63 km/h.
Non Invasive Histology of Atherosclerotic Plaque

Non Invasive Histology of Atherosclerotic Plaque

Stroke is the third leading cause of death in Germany. It is a neurology injury, whereby the oxygen supply to parts of the brain gets cut off. About 80% of these strokes are due to ischemia, i.e. an occlusion of a blood vessel leading to an interrupted blood flow. Stenosis inside the carotid artery imaged using four different MR weightings Special setting in this project is the arteria carotis. Plaque is most likely to develop at the branching of the arteria carotis communis into the arteria carotis interna (leading to the brain) and the arteria carotis externa. This can lead to an abnormal narrowing, called a stenosis. According to the American Heart Association these plaques can be divided into different types, based on their consistency and structure. Until now the decision about a surgery was only based on the degree of the stenosis and not on the type of plaque causing it. This is a faulty approach since there is a plaque type (Type IV) which constitutes a relevant clinical danger, although it does not necessary come along with a stenosis. Unlike most other image modalities MR images do not only give information about the degree of the stenosis, but also about the consistency of the plaque. Using different weighted MR images it is possible to correctly classify plaque into the types defined by the AHA. The main goal of this project is to create a classification tool based on T1, T2, Proton Density and 'Time of flight' weighted images. To achieve this goal the arteria carotis and the plaque have to be segmented from the images. Furthermore various features of the plaque have to be extracted in order to get information needed for the classification.
Assessment of Fluid Tissue Interaction Using Multi-Modal Image Fusion for Characterization and Progression of Coronary Atherosclerosis

Assessment of Fluid Tissue Interaction Using Multi-Modal Image Fusion for Characterization and Progression of Coronary Atherosclerosis

Coronary artery diseases such as atherosclerosis are the leading cause of death in the industrialized world. In this project, we develop computational tools for segmentation and registration problems on intravascular images including IVUS (Intravascular Ultrasound) and OCT (Optical Coherence Tomography). One sample component of this project is Automatic Stent Implant Follow-up from Intravascular OCT Pullbacks. The stents are automatically detected and their distribution is analyzed for monitoring of the stents: their malpositioning and/or tissue growth over stent struts.
Catheter Extraction in Abdominal Fluoroscopic Image Sequences

Catheter Extraction in Abdominal Fluoroscopic Image Sequences

This work's focus lies in catheter and guide wire extraction from abdominal fluoroscopic sequences. Due to the fact that fluoroscopic X-ray images are of low quality and suffer from a lot of background clutter in the abdominal area the task we are working on is very difficult and not yet solved by the community. The detection process is very important since a properly detected catheter or guide wire is required by many applications that have been proposed in the last few years. One of the major goals is the enhancement of the navigation during abdominal cathterizations in order to reduce the time of interventions and thus the radiation exposure for the patient and especially the physician.
Semi-Automatic Patellar Cartilage Segmentation

Semi-Automatic Patellar Cartilage Segmentation

Development and refinement of a software system for semi-automatic segmentation of the patellar cartilage is the main goal of this project. By providing tools for sub-pixel accurate edge tracing, automatic contour completion, and adequate visualization, a remarkable speed-up of the physicians segmentation process can be achieved. Also, improved exactness can be reached for cartilage segmentation if expertise and automation are merged in a meaningful way.
Assessment of Knee Cartilage

Assessment of Knee Cartilage

Degeneration of knee joint cartilage is an important and early indicator of osteoarthritis (OA) which is one of the major socio-economic burdens nowadays. Accurate quantification of the articular cartilage degeneration in an early stage using MR images is a promising approach in diagnosis and therapy for this disease. Particularly, volume and thickness measurement of cartilage tissue has been shown to deliver significant parameters in assessment of pathologies. Here, accurate computer-aided diagnosis tools could improve the clinical routine where image segmentation plays a crucial role. In order to overcome the time-consuming and tedious work of manual segmentation, one tries to automate the segmentation as much as possible. We focus on novel atlas-based segmentation methods for knee cartilage as well as improve today’s clinical routine of manual segmentation methods. In addition, we try to evaluate different methods for the assessment of parameters such as volume and thickness which could allow computer-aided diagnosis of knee cartilage pathologies in an early stage.
Automatic thrombus segmentation in in vivo micoscopic video sequences under low contrast and highly dynamic conditions

Automatic thrombus segmentation in in vivo micoscopic video sequences under low contrast and highly dynamic conditions

The Bloodomics EU project aims are to identify the genetic risks factors of coronary heart diseases.
One of the most common methods is to study the thrombus formation in the dorsal aorta of mutant Zebrafish larvae. The developing thrombus is imaged in vivo through a microscope/camera setup. The derived time to attachment, growth speed, and time to occlusion permits the characterization of the thrombus formation.
However, this step presently remains manual. Our objective is to provide the geneticists in the Wellcome Trust Sanger Institute with an image processing tool to automatically detect and segment the growing thrombus. This will significantly speed up and improve the precision of this current analysis.
Coupled Curves Segmentation

Coupled Curves Segmentation

The term of coupled curves refers to two or more boundaries bounded biomechanically or anatomically. Some examples are luminal and outer borders of the vessel in intravascular ultrasound images, the myocardial borders of heart in different cardiac modalities like Echocardiography and MRI, retinal layers in optical coherent tomography of eye etc. Coupling these boundaries and taking into account their interdependency efficiently assists segmentation of weaker boundaries by the guide of stronger ones. This project is an extension to our recently developed segmentation approaches by modifying the formulation to segment coupled curves. The primary deliverable is segmentation of double boundaries and can be followed to the secondary deliverable, i.e. segmentation of multiple boundaries depending on the performance of the researcher. Platform of the project is visual programing with mevislab. Preferred coding language is C++ Nevertheless matlab coding can be used for development. There are plenty of applications to the segmentation of coupled curves in medical image processing and the project has significant contribution with high impact to the community.
Prediction of Rupture Risk for Abdominal Aortic Aneurysms

Prediction of Rupture Risk for Abdominal Aortic Aneurysms

An abdominal aortic aneurysm (AAA) describes an enlarged aortic diameter in the abdominal part of the body. Due to weakening rupture of the inner aortic wall layer, blood cells accumulate inside the wall layers and lead to a thrombus. In order to choose a suitable individual treatment, a prediction of rupture risk would be helpful. However, it is not possible to predict the ruputure risk only with quantative parameters extracted out of CT-images such as size and diameter. It is important to also include qualitative predictors like characteristics of the aortic wall and fluid dynamics.
Together with our medical and academic partners, we are interested in creating a model of the aorta and its thrombus in order to do certain calculations on wall stress and fluid dynamic computations. A further integration of other medical imaging devices such as PET/CT and IVUS into the geometrical model can provide more information about biochemical activities inside the aneurysmatic walls.

Related Publications

2012
A. Ahmadi, T. Klein, A. Plate, K. Bötzel, N. Navab
Rigid US-MRI Registration Through Segmentation of Equivalent Anatomic Structures - A feasibility study using 3D transcranial ultrasound of the midbrain.
Workshop Bildverarbeitung fuer die Medizin, Berlin (GER), March 18-20, 2012 (bib)
A. Eslami, A. Karamalis, A. Katouzian, N. Navab
Segmentation By Retrieval With Guided Random Walks: Application To Left Ventricle Segmentation in MRI
Accepted in : Medical Image Analysis, xxx, xxx, 2012, http://www.sciencedirect.com/science/article/pii/S136184151200151X (bib)
J. Beitzel, A. Ahmadi, A. Karamalis, W. Wein, N. Navab
Ultrasound Bone Detection Using Patient-Specific CT Prior
International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), San Diego, USA, September 1 2012. (bib)
A. Karamalis, W. Wein, T. Klein, N. Navab
Ultrasound Confidence Maps using Random Walks
Medical Image Analysis, 16, 6, 1101 - 1112, 2012, DOI: http://dx.doi.org/10.1016/j.media.2012.07.005 (bib)
P. Lo, B. v. Ginneken, J. M. Reinhardt, T. Yavarna, P. A. d. Jong, B. Irving, C. Fetita, M. Ortner, R. Pinho, J. Sijbers, M. Feuerstein, A. Fabijanska, C. Bauer, R. Beichel, C. S. Mendoza, R. Wiemker, J. Lee, A. P. Reeves, S. Born, weinheimer, E. M. v. Rikxoort, J. Tschirren, K. Mori, B. Odry, D. P. Naidich, I. Hartmann, E. A. Hoffman, M. Prokop, J. H. Pedersen, M. d. Bruijne
Extraction of Airways from CT (EXACT'09)
IEEE Transactions on Medical Imaging, July 2012 (bib)
P. Waelkens, A. Ahmadi, N. Navab
'Frangi goes US': Multiscale Tubular Structure Detection Adapted to 3D Ultrasound
In Proc. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nice (FR), October 01-05, 2012 (bib)
O. Pauly, A. Ahmadi, A. Plate, K. Bötzel, N. Navab
Detection of Substantia Nigra Echogenicities in 3D Transcranial Ultrasound for Early Diagnosis of Parkinson Disease
In Proc. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nice (FR), October 01-05, 2012 (bib)
M. Feuerstein, B. Glocker, T. Kitasaka, Y. Nakamura, S. Iwano, K. Mori
Mediastinal Atlas Creation from 3-D Chest Computed Tomography Images: Application to Automated Detection and Station Mapping of Lymph Nodes
Medical Image Analysis, vol. 16, no. 1, pp. 63-74, January 2012.
The original publication is available online at www.elsevier.com
(bib)
2011
A. Ahmadi, M. Baust, A. Karamalis, A. Plate, K. Bötzel, T. Klein, N. Navab
Midbrain Segmentation in Transcranial 3D Ultrasound for Parkinson Diagnosis
In Proc. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Toronto (CA), September 18-22, 2011 (bib)
D. Ugurlu, S. Demirci, N. Navab, M. S. Celebi
A Vessel Segmentation Method for MRA Images Based on Multi-scale Analysis and Level Set Framework
3rd International MICCAI-Workshop on Computation and Visualization on (Intra)Vascular Imaging, Toronto, Canada, September 18, 2011 (bib)
L. König, J. M. Raya Garcia del Olmo
Edge Aberration in MRI. Correction of Dislocations in Sub-Voxel Edge Detection—a Proof of Concept
Proc. of Bildverarbeitung für die Medizin (BVM 2011), Lübeck, Germany, March 2011.
The original publication is available online at www.springerlink.com.
(bib)
2010
A. Horng, J. M. Raya Garcia del Olmo, M. Zscharn, L. König, M. Notohamiprodjo, M. Pietschmann, U. Hoehne-Hückstädt, I. Hermanns, U. Glitsch, R. Ellegast, K. G. Hering, M. Reiser, Ch. Glaser
Locoregional Deformation Pattern of the Patellar Cartilage After Different Loading Types—High-Resolution 3D-MRI Volumetry at 3 T in-vivo
Fortschr Röntgenstr. 2010; 182:1–9 (bib)
T. Kitasaka, H. Yano, M. Feuerstein, K. Mori
Bronchial region extraction from 3D chest CT image by voxel classification based on local intensity structure
Third International Workshop on Pulmonary Image Analysis, September 2010 (bib)
G.Gul-Isguder, G. Unal, M. Groher, N. Navab, A.K.Kalkan, M. Degertekin, H.Hetterich, J.Rieber
Manifold Learning for Image-Based Gating of Intravascular Ultrasound(IVUS) Pullback Sequences
5th International Workshop on Medical Imaging and Augmented Reality, Sep 2010, Beijing (bib)
J. M. Raya Garcia del Olmo, A. Horng, L. König, M. Reiser, Ch. Glaser
Detecting Statistically Significant Changes in Cartilage Thickness with Sub-Voxel Precision
Proceedings of the 18th congress of the International Society for Magnetic Resonance in Medicine (ISMRM 2010), Stockholm, Sweden. Presentation 3192, electronic poster session “Meniscus & Cartilage” (bib)
M. Feuerstein, T. Kitasaka, K. Mori
Adaptive Model Based Pulmonary Artery Segmentation in 3D Chest CT
SPIE Medical Imaging, San Diego, California, USA, February 2010 (bib)
2009
S. Demirci, G. Lejeune, N. Navab
Hybrid Deformable Model for Aneurysm Segmentation
IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2009), Boston, Massachusetts, USA, June 28 - July 1, 2009 (bib)
H. Yano, M. Feuerstein, T. Kitasaka, K. Mori
Study on bronchus region extraction from 3D chest CT images using local intensity structure analysis
18th Meeting of the Japan Society of Computer Assisted Surgery, Tokyo, Japan, November 2009 (bib)
M. Feuerstein, T. Kitasaka, K. Mori
Automated Anatomical Likelihood Driven Extraction and Branching Detection of Aortic Arch in 3-D Chest CT
Second International Workshop on Pulmonary Image Analysis, September 2009 (bib)
M. Feuerstein, T. Kitasaka, K. Mori
Adaptive Branch Tracing and Image Sharpening for Airway Tree Extraction in 3-D Chest CT
Second International Workshop on Pulmonary Image Analysis, September 2009 (bib)
H. Yano, D. Deguchi, M. Feuerstein, K. Mori, T. Kitasaka, Y. Suenaga
Study on bronchus region extraction from 3D chest CT images based on analysis of local intensity value distribution
28th Meeting of the Japanese Society of Medical Imaging Technology, Nagoya, Japan, August 2009 (bib)
H. Yano, M. Feuerstein, T. Kitasaka, K. Mori
Study on bronchus region extraction from 3D chest CT images using local intensity structure analysis and CT value distribution features
Medical Imaging Workshop of the Institute of Electronics, Information and Communication Engineers, Tokyo, Japan, July 2009 (bib)
M. Feuerstein, D. Deguchi, T. Kitasaka, S. Iwano, K. Imaizumi, Y. Hasegawa, Y. Suenaga, K. Mori
Automatic Mediastinal Lymph Node Detection in Chest CT
SPIE Medical Imaging, Orlando, Florida, USA, February 2009 (bib)
2008
H. Yano, D. Deguchi, M. Feuerstein, T. Kitasaka, K. Mori, Y. Suenaga
A study on bronchial area extraction from 3D chest CT images using CT value distribution features
17th Meeting of the Japan Society of Computer Assisted Surgery, Tokyo, Japan, October/November 2008 (bib)
M. Feuerstein, D. Deguchi, T. Kitasaka, S. Iwano, K. Imaizumi, Y. Hasegawa, Y. Suenaga, K. Mori
Automatic Detection of Mediastinal Lymph Nodes in Contrast-Enhanced Chest CT
17th Meeting of the Japan Society of Computer Assisted Surgery, Tokyo, Japan, October/November 2008 (bib)
2007
B. Glocker, N. Komodakis, N. Paragios, Ch. Glaser, G. Tziritas, N. Navab
Primal/Dual Linear Programming and Statistical Atlases for Cartilage Segmentation
Medical Image Computing and Computer-Assisted Intervention (MICCAI), Brisbane, Australia, October 29 - November 2 2007 (bib)
L. König, M. Groher, A. Keil, Ch. Glaser, M. Reiser, N. Navab
Semi-Automatic Segmentation of the Patellar Cartilage in MRI
Proc. of Bildverarbeitung für die Medizin (BVM 2007), Munich, Germany, March 2007. The original publication is available online at www.springerlink.com. (bib)

Working Group

Demirci
Stefanie Demirci
Eslami
Abouzar Eslami
Matthies
Philipp Matthies
Pauly
Olivier Pauly
Peter
Loic Peter
Shah
Amit Shah


Edit | Attach | Refresh | Diffs | More | Revision r1.4 - 09 Dec 2011 - 09:59 - AhmadAhmadi

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif