Miroslaw Socha

Data Processing Tasks in Wireless GI Endoscopy: Image-Based Capsule Localization & Navigation and Video Compression

The paper addresses data processing support that is required in capsule gastrointestinal endoscopy. First, capsule position estimation method using standard MPEG-7 image features (descriptors) is discussed. The proposed approach makes use of vector quantization, principal component analysis and neural networks. Next, new algorithms dedicated for virtual colonoscopy (VC) human body inspection are described. The VC images can be registered with endoscopic ones and help in capsule localization and navigation. Finally, an original, low- complexity, efficient image compression method, based on integer-to-integer 4x4 DCT transform, is presented and experimentally verified.

Fast Estimation of Broncho-Fiberoscope Egomotion for Ct-Guided Transbronchial Biopsy

The paper addresses the problem of very fast real-time estimation of forward and backward broncho-fiberoscope egomotion during the medical procedure of transbronchial biopsy. The proposed algorithm significantly differs from standard egomotion routines since it exploits specific rotational features of the bronchoscopic images resulting from the approximate cylinder-like structure of airway segments. The method is described in detail in the paper and tested on synthetic and real-word endoscopic images. Reported results explicitly confirm its efficiency.

Colon Cleansing for Virtual Colonoscopy Using Non-linear Transfer Function and Morphological Operations

The virtual colonoscopy (VC) techniques try to simulate a real colonoscopy. A doctor who makes real colonoscopy examination does not have optimal information about anatomical structures which he looks at. He sees the inner colon structure only. 3D visualization of the colon segmented from computed tomography (CT) data allows him to see the whole organ, its inner and outer part. The VC helps doctors during diagnostic processes in identification and localization of pathological changes and offers computer support for endoscopic procedures. In this paper we present new colon cleansing method based on non-linear transfer function and morphological operations. Colon cleansing is required when we receive non-clean CT data or when a patient had administered contrast before the CT scan. It allows to see the whole colon even this one lying under fluid and to compute colon centerline correctly.

The BRONCHOVID – Computer System Supporting Bronchoscopy Laboratory

The bronchoscopy diagnostics consists of numerous tasks including but not limited to the treatment planning on the basis of computed tomography, registration and analysis of endoscopic images during the inspection of the tracheo-bronchial tree and procedure management. There is no comprehensive solution for a computer system supporting bronchoscopy laboratory. Since the limited time of medical personnel, high volume and multimodal data created during bronchoscopy procedure and complex workflow we decide to build a dedicated system addressing these issues. The paper presets an overview of the bronchoscope diagnostics, user needs and requirements related to the procedure and the proposed solution. Finely, the deployment results as well as future plan is presented.

Computational tasks in computer-assisted transbronchial biopsy

The paper presents algorithmic solutions dedicated to computer navigation system which is to assist bronchoscope positioning during transbronchial needle-aspiration biopsy. The navigation exploits the principle of on-line registration of real images from endoscope camera and the virtual ones generated on the base of computed tomography (CT) data of a patient. When these images are similar an assumption is made, that the bronchoscope and virtual camera have approximately the same position and view direction. In this paper the following computational aspects are described: correction of camera lens distortion, fast approximate estimation of endoscope ego-motion, reconstruction of bronchial tree from the CT data by means of their segmentation and its centerline calculation, virtual views generation, registration of real and virtual images via maximization of their mutual information and, finally, efficient parallel and network implementation of the navigation system which is under development at present.

Virtual Colonoscopy - Technical Aspects

Virtual colonoscopy (VC) is a diagnostic method enabling the generation of twodimensional and three-dimensional images of the colon and rectum from the data obtained with relevant imaging modality, usually spiral computed tomography (CT). If CT is used, the method is also called CT colonoscopy, CT colonography, or CT pneumocolon. The main advantages of the VC which support its broader application in medical practice include: limited invasiveness, improved compliance of patients and value for screening for colorectal cancer. The introduction of virtual endoscopy technique originates from the extended processing options of the data sets obtained with available imaging modalities. The Visible Human Project and related activities (Hong et al., 1996; Hong, 1997) were of key importance for development of the VC. The quality of first VC images limited the potential of the clinical use of this technique. But with next generations of the imaging equipment and advanced processing algorithms, their applicability in medical practice was established. VC may be performed with all imaging techniques which result in cross-sections of the abdominal cavity. It can be generated both from CT and magnetic resonance imaging (MRI) cross-sections. However, the CT remains the first choice imaging modality for the VC. It is required that spiral acquisition mode with overlapping reconstructions is applied. The quality of the images generated within VC techniques depends strongly on the spatial resolution obtained with imaging modality. Nowadays, multidetector computed tomography (MDCT) is commonly available and this adds to overall quality of assessment of the colon and rectum resulting from VC. The patient undergoing helical computed tomography with the intent of obtaining VC should undergo complete bowel preparation as for other procedures within abdomen, e.g. endoscopic colonoscopy. The priority is assigned to evacuation of the contents of the colon before CT. For this purpose, many agents are used including ethylene glycol electrolyte solution, magnesium citrate or oral sodium phospate. Netherless, the quality of bowel preparation for VC varies considerably between different centres (Van Uitert et al., 2008). The trend for the optimisation of the diagnostic procedures and limitation of the burden to the patient resulted also in a strategy focusing on the performing of the optical colonoscopy just after VC, if it is positive for pathological lesions in the colon, in order to avoid repetition

3D Segmentation and Visualisation of Mediastinal Structures Adjacent to Tracheobronchial Tree from CT Data

In the paper, an advanced visualisation module of recently developed BRONCHOVID system designed for efficient data exploration and bronchoscopy guidance is presented. It brings an intuitive and user-friendly interface developed with several open source subroutines as well as diversified modes and algorithms of thoracic CT of data segmentation and visualisation including a surface shaded display (SSD), volume rendering and multiplanar reformatting. For enhanced concurrent visualisation of thoracic structures located in the vicinity of or adjacent to trachea and bronchial tree (lymph nodes, blood vessels, pathological masses) a new dedicated segmentation algorithm has been developed. It is based on a region growing method followed by the use of deformable models. The module integrates also the options of central path calculation by means of distant transform in lower airways and interactive virtual bronchoscopy. Its functionality covers also an option for measurements of dimensions in volume of CT data.

Computational Tasks in Bronchoscope Navigation During Computer-Assisted Transbronchial Biopsy

The paper presents algorithmic solutions dedicated to computer navigation system which is to assist bronchoscope positioning during transbronchial needle-aspiration biopsy. The navigation exploits principle of on-line registration of real images coming from endoscope camera and virtual ones generated on the base of computed-tomography (CT) data of a patient. When these images are similar an assumption is made that the bronchoscope and virtual camera have approximately the same position and view direction. In the paper the following computational aspects are described: correction of camera lens distortion, fast approximate estimation of endoscope ego-motion, reconstruction of bronchial tree from CT data by means of their segmentation and its centerline calculation, virtual views generation, registration of real and virtual images via maximization of their mutual information and, finally, efficient parallel and network implementation of the navigation system which is under development.