Joanna Czajkowska

Multi-scale textural feature extraction and particle swarm optimization based model selection for false positive reduction in mammography

The high number of false positives and the resulting number of avoidable breast biopsies are the major problems faced by current mammography Computer Aided Detection (CAD) systems. False positive reduction is not only a requirement for mass but also for calcification CAD systems which are currently deployed for clinical use. This paper tackles two problems related to reducing the number of false positives in the detection of all lesions and masses, respectively. Firstly, textural patterns of breast tissue have been analyzed using several multi-scale textural descriptors based on wavelet and gray level co-occurrence matrix. The second problem addressed in this paper is the parameter selection and performance optimization. For this, we adopt a model selection procedure based on Particle Swarm Optimization (PSO) for selecting the most discriminative textural features and for strengthening the generalization capacity of the supervised learning stage based on a Support Vector Machine (SVM) classifier. For evaluating the proposed methods, two sets of suspicious mammogram regions have been used. The first one, obtained from Digital Database for Screening Mammography (DDSM), contains 1494 regions (1000 normal and 494 abnormal samples). The second set of suspicious regions was obtained from database of Mammographic Image Analysis Society (mini-MIAS) and contains 315 (207 normal and 108 abnormal) samples. Results from both datasets demonstrate the efficiency of using PSO based model selection for optimizing both classifier hyper-parameters and parameters, respectively. Furthermore, the obtained results indicate the promising performance of the proposed textural features and more specifically, those based on co-occurrence matrix of wavelet image representation technique.

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.

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.

HoG feature based detection of tissue deformations in ultrasound data.

The fast development of imaging techniques during last decades makes it possible to introduce intra-operative visualization as the integral part of surgical procedures. Therefore, the automated analysis of intra-operative ultrasound images is appreciated. The image processing, registration and visualization techniques help in better understanding and locate the operated region. To meet these needs, the paper presents an advanced algorithm for automated detection of tissue deformations caused by a biopsy needle. For this, feature set of Histogram of Gradients (HoG) is introduced. The extracted feature vectors are then used in image cell clustering step resulting in tissue deformation as well as biopsy needle detection. The applied there Kernelized Weighted C-Means clustering technique enables robust and accurate needle detection proven by sensitivity and specificity values at levels of 0.846 and 0.99, respectively.

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.

3D object retrieval by 3D curve matching

In this paper, we introduce a novel approach to 3D object retrieval by 3D curve matching. First, we project 2D object edges obtained from a depth image into 3D space. Second, we find distinctive feature points on the object. Third, we represent the shortest paths between the features by robust descriptors invariant to rotation, scaling, and translation. Finally, we match two 3D objects using the Maximum Weight Subgraph search. The most important contribution of this paper is the powerful object representation by 3D curves together with the corresponding matching algorithm. Excellent retrieval results achieved with our method show its benefits compared to the state-of-the-art.

A new parametric model-based technique in bone tumour analysis.

The study presents a new statistical model based segmentation technique dedicated to inhomogeneous bone tumours structure analysis. The presented 3-D segmentation procedure applies a statistic description of the structure based on Gaussian mixture model and an adaptive model-based relative fuzzy connectedness technique. It has been tested on 94 different MR series of 38 young patients. The final segmentation results have been evaluated using two different verification techniques and compared with other segmentation methods. The developed technique yields higher bone tumours segmentation accuracy compared to results obtained with conventional fuzzy connectedness approach and different segmentation methods presented in the literature, and based on active contour models or statistical analysis.

A new fuzzy support vectors machine for biomedical data classification

In this paper a new approach to a fuzzy support vector machine (FSVM) for solving multi-class problems is presented. The developed algorithm combines two separate methods based on fuzzy support vector machine, one for solving two-class problems and the second for multi-class problems. The first method deals with the problem of selecting the best support vector machine (SVM) kernel function and the second method enables classification of unclassified regions that appear when classical SVM methods for solving multi-class problems are used. Presented tool has been subjected to the dataset from Kent Ridge Biomedical Data Set Repository and showed its superiority comparing with conventional SVM and FSVM methods.

ToF-Data-Based Modelling of Skin Surface Deformation

Nowadays, the imaging techniques followed by advanced image processing algorithms become an indispensable part of diagnostic and surgical procedures. During recent years, an increasing demand for intra-surgical modalities can be noticed. The work aims at modelling the deformation of human skin surface caused by a navigated stick based on the point cloud acquired by a Time-of-Flight (ToF) camera. The data acquired by ToF and optical tracker are synchronized. Then, the skin deformation is modelled by applying a physics engine. The model evaluation is based on a Hausdorff distance. The results prove the applicability of the developed workflow.

Biopsy Needle and Tissue Deformations Detection in Elastography Supported Ultrasound

During last decades a fast development of imaging techniques has offered the intra-operative visualization as the integral part of surgical tools. For this, the automated and robust analysis of ultrasound images is required. The paper meets these requirements targeting in detection of tissue deformations caused by biopsy needle inserted in the body. The presented novel technique uses ultrasound data supported by elastography images. In the feature set, the automated detection algorithm introduces Histogram of Oriented Gradients and image entropy. The further classification steps applies Weighted Fuzzy C-Means (WFCM) clustering technique resulting in deformation detection sensitivity and specificity at levels 0.793 and 0.94, respectively.