Pawel Badura

Soft computing approach to 3D lung nodule segmentation in CT

This paper presents a novel, multilevel approach to the segmentation of various types of pulmonary nodules in computed tomography studies. It is based on two branches of computational intelligence: the fuzzy connectedness (FC) and the evolutionary computation. First, the image and auxiliary data are prepared for the 3D FC analysis during the first stage of an algorithm - the masks generation. Its main goal is to process some specific types of nodules connected to the pleura or vessels. It consists of some basic image processing operations as well as dedicated routines for the specific cases of nodules. The evolutionary computation is performed on the image and seed points in order to shorten the FC analysis and improve its accuracy. After the FC application, the remaining vessels are removed during the postprocessing stage. The method has been validated using the first dataset of studies acquired and described by the Lung Image Database Consortium (LIDC) and by its latest release - the LIDC-IDRI (Image Database Resource Initiative) database.

Role of radiologists in CAD life-cycle

A modern CAD (computer-aided diagnosis) system development involves a multidisciplinary team whose members are experts in medical and technical fields. This study indicates the activities of medical experts at various stages of the CAD design, testing, and implementation. Those stages include a medical analysis of the diagnostic problem, data collection, image analysis, evaluation, and clinical verification. At each stage the physicians knowledge and experience are indispensable. The final implementation involves integration with the existing Picture Archiving and Communication System. The term CAD life-cycle describes an overall process of the design, testing, and implementation of a system that in its final form assists the radiologists in their daily clinical routine. Four CAD systems (applied to the bone age assessment, Multiple Sclerosis detection, lung nodule detection, and pneumothorax measurement) developed in our laboratory are given as examples of how consecutive stages are developed by the multidisciplinary team. Specific advantages of the CAD implementation that include the daily clinical routine as well as research and education activities are discussed.

Open architecture computer-aided diagnosis system

: In this study an approach to open architecture computer-aided diagnosis (CAD) is presented. The traditional goal of a CAD system, to assist the physicians in performing the diagnosis and treatment, has been extended. The platform also supports the system designer in developing a new CAD workflow by implementing general-purpose modules as well as problem-dependent procedures. A new CAD may require new procedures to be added, yet some of the already implemented functions can be employed. The CAD environment is subjected to the developmental process of three systems: the multiple sclerosis CAD, the lung nodule CAD and the pneumothorax CAD. Modules and procedures are briefly described and the CAD systems are evaluated. Results obtained during the CAD evaluation show prospective flexibility of the infrastructure. The trade-offs, well known to CAD designers, can easily be handled by the operators in a user-friendly manner by choosing various workflow paths.

Accelerometric signals in automatic balance assessment

The paper presents the automatic computer-aided balance assessment system for supporting and monitoring the diagnosis and rehabilitation process of patients with limited mobility or disabled in home environment. The system has adopted seven Berg Balance Scale activities. The assessment approach is based on the accelerometric signals acquired by the inertial sensors worn by the patient. Several specific, mostly medium frequency features of signals are introduced and discussed. The reduction of the feature vector has been performed using the multilevel Fishers linear discriminant. The classification employs the multilayer perceptron artificial neural network. The direct assessment effectiveness ranges from 75% to 94% for various activities.

Semi-automatic Seed Points Selection in Fuzzy Connectedness Approach to Image Segmentation

A new method improving the fuzzy connectedness approach to medical image segmentation is described. The segmentation based on fuzzy connectedness relies on a fuzzy connectivity scene creation by assigning a strength of connectedness to each possible path between some predefined seed point located inside an object and any other image element and performing the thresholding. The new idea is to automatically choose more seed points inside, as well as outside the segmented structure, in order to improve the method effectiveness and to reduce the computational time. The selection is based on two points marked manually.

Acceleration trajectory analysis in remote gait monitoring.

The study demonstrates part of an ambient assisted living system developed for the remote care of the elderly. Described methods and experiments involve acceleration-based trajectories analysis that yields a feature vector to be subjected to an expert system able to create an individual patients model by learning high-level features of her/his motion. At this stage we have implemented a footstep detector that permits each foot movement to be analyzed separately and described in terms of predefined features. By mounting the sensors at five various locations on the subjects body, we have indicated areas that feature a high sensitivity to the measurement of abnormal step incidents. Our experiments demonstrate also features able to distinguish abnormal patient motion.

Radiological Atlas for Patient Specific Model Generation

The paper presents the development of a radiological atlas employed in an abdomen patient specific model verification.

4D Segmentation of Ewing’s Sarcoma in MR Images

This paper presents the first stage of a semi-automatic method for the segmentation of nodules of the skeleto-muscular system from magnetic resonance (MR) imaging. Themethod suggested is efficient irrespective of the tumour location in human body. It is based on Fuzzy C-Means clustering (FCM), Gaussian Mixture Models (GMM) and Fuzzy Connectedness analysis applied to the dataset consisting of T1W and T2W series. In this study a method of transforming the results between planes is also presented. The suggested algorithm has been evaluated on the examinations of different parts of the body, where Ewing’s sarcomas have been indicated by a radiologist.

Time-Of-Flight Camera, Optical Tracker and Computed Tomography in Pairwise Data Registration.

Purpose A growing number of medical applications, including minimal invasive surgery, depends on multi-modal or multi-sensors data processing. Fast and accurate 3D scene analysis, comprising data registration, seems to be crucial for the development of computer aided diagnosis and therapy. The advancement of surface tracking system based on optical trackers already plays an important role in surgical procedures planning. However, new modalities, like the time-of-flight (ToF) sensors, widely explored in non-medical fields are powerful and have the potential to become a part of computer aided surgery set-up. Connection of different acquisition systems promises to provide a valuable support for operating room procedures. Therefore, the detailed analysis of the accuracy of such multi-sensors positioning systems is needed. Methods We present the system combining pre-operative CT series with intra-operative ToF-sensor and optical tracker point clouds. The methodology contains: optical sensor set-up and the ToF-camera calibration procedures, data pre-processing algorithms, and registration technique. The data pre-processing yields a surface, in case of CT, and point clouds for ToF-sensor and marker-driven optical tracker representation of an object of interest. An applied registration technique is based on Iterative Closest Point algorithm. Results The experiments validate the registration of each pair of modalities/sensors involving phantoms of four various human organs in terms of Hausdorff distance and mean absolute distance metrics. The best surface alignment was obtained for CT and optical tracker combination, whereas the worst for experiments involving ToF-camera. Conclusion The obtained accuracies encourage to further develop the multi-sensors systems. The presented substantive discussion concerning the system limitations and possible improvements mainly related to the depth information produced by the ToF-sensor is useful for computer aided surgery developers.

Automatic Berg Balance Scale assessment system based on accelerometric signals

Abstract This paper presents the automatic system for computer-aided balance assessment reflecting the Berg Balance Scale. The system employs inertial sensors for the data acquisition purposes. A set of features is extracted from multiple signal representations during the examination. A multilevel Fishers linear discriminant is used to select most suitable features for each of the BBS tasks. The feature space dimensionality reduction and the multilayer perceptron classifier training both involve expert scoring on the observed examinations. The system is verified using data acquired during the BBS scoring of 64 elderly patients. Both assessment modes: the entire examination as well as separate BBS items, are evaluated and discussed using introduced assessment metrics.