Contrast-enhanced ultrasound (CEUS) has recently become an important technology for lesion detection and characterization. CEUS is used to investigate the perfusion kinetics in tissue over time, which relates to tissue vascularization. In this paper, we present an interactive segmentation method based on the neural networks, which enables to segment malignant tissue over CEUS sequences. We use Self-Organizing-Maps (SOM), an unsupervised neural network, to project high dimensional data to low dimensional space, named a map of neurons. The algorithm gathers the observations in clusters, respecting the topology of the observations space. This means that a notion of neighborhood between classes is defined. Adjacent observations in variables space belong to the same class or related classes after classification. Thanks to this neighborhood conservation property and associated with suitable feature extraction, this map provides user friendly segmentation tool. It will assist the expert in tumor segmentation with fast and easy intervention. We implement SOM on a Graphics Processing Unit (GPU) to accelerate treatment. This allows a greater number of iterations and the learning process to converge more precisely. We get a better quality of learning so a better classification. Our approach allows us to identify and delineate lesions accurately. Our results show that this method improves markedly the recognition of liver lesions and opens the way for future precise quantification of contrast enhancement.
Liver cancer is the third most common cancer in the world, and the majority of patients with liver cancer will die within one year as a result of the cancer. Liver segmentation in the abdominal area is critical for diagnosis of tumor and for surgical procedures. Moreover, it is a challenging task as liver tissue has to be separated from adjacent organs and substantially the heart. In this paper we present a novel liver segmentation iterative method based on Fuzzy C-means (FCM) coupled with a fast marching segmentation and mutual information. A prerequisite for this method is the determination of slice correspondences between ground truth that is, a few images segmented by an expert, and images that contain liver and heart at the same time.
We propose a novel interactive 3D segmentation approach and geometric model definition called tubular envelope
model. It is conceived to express the shape of tubular objects. The main challenges we have achieved are the
speed and interactivity of the construction. A computer program designed for this task gives the user full control
of the shape and precision, with no significant computational errors.
Six CT (computed tomography) aortic dissection images have been used for the tubular envelopes construction.
Hence, we have proposed a generic parametric model of the aorta for its interactive construction. It leads us to
rapid visualization and navigation inside the artery (rough virtual angioscopy). The low complexity of the model
and the ease of interactive design makes the tubular envelope suitable for aorta segmentation in comparison to
the other segmentation methods. The model accuracy is adjustable by the user according to his requirements;
the time of construction is approved by clinicians.
More generally, the tubular envelope could be used in other applications, e.g. to define a region of interest
for more precise segmentation or feature extraction inside, to develop a parametric model with deformation