Martin Bergtholdt

A Radial Structure Tensor and Its Use for Shape-Encoding Medical Visualization of Tubular and Nodular Structures

The concept of curvature and shape-based rendering is beneficial for medical visualization of CT and MRI image volumes. Color-coding of local shape properties derived from the analysis of the local Hessian can implicitly highlight tubular structures such as vessels and airways, and guide the attention to potentially malignant nodular structures such as tumors, enlarged lymph nodes, or aneurysms. For some clinical applications, however, the evaluation of the Hessian matrix does not yield satisfactory renderings, in particular for hollow structures such as airways, and densely embedded low contrast structures such as lymph nodes. Therefore, as a complement to Hessian-based shape-encoding rendering, this paper introduces a combination of an efficient sparse radial gradient sampling scheme in conjunction with a novel representation, the radial structure tensor (RST). As an extension of the well-known general structure tensor, which has only positive definite eigenvalues, the radial structure tensor correlates position and direction of the gradient vectors in a local neighborhood, and thus yields positive and negative eigenvalues which can be used to discriminate between different shapes. As Hessian-based rendering, also RST-based rendering is ideally suited for GPU implementation. Feedback from clinicians indicates that shape-encoding rendering can be an effective image navigation tool to aid diagnostic workflow and quality assurance.

Pulmonary nodule detection using a cascaded SVM classifier

Automatic detection of lung nodules from chest CT has been researched intensively over the last decades resulting also in several commercial products. However, solutions are adopted only slowly into daily clinical routine as many current CAD systems still potentially miss true nodules while at the same time generating too many false positives (FP). While many earlier approaches had to rely on rather few cases for development, larger databases become now available and can be used for algorithmic development. In this paper, we address the problem of lung nodule detection via a cascaded SVM classifier. The idea is to sequentially perform two classification tasks in order to select from an extremely large pool of potential candidates the few most likely ones. As the initial pool is allowed to contain thousands of candidates, very loose criteria could be applied during this pre-selection. In this way, the chances that a true nodule is falsely rejected as a candidate are reduced significantly. The final algorithm is trained and tested on the full LIDC/IDRI database. Comparison is done against two previously published CAD systems. Overall, the algorithm achieved sensitivity of 0.859 at 2.5 FP/volume where the other two achieved sensitivity values of 0.321 and 0.625, respectively. On low dose data sets, only slight increase in the number of FP/volume was observed, while the sensitivity was not affected.

Single-view 2D/3D registation for X-ray guided bronchoscopy

X-ray guided bronchoscopy is commonly used for targeting peripheral lesions in the lungs which cannot be visualized directly by the bronchoscope. The airways and lesions are normally not visible in X-ray images, and as a result, transbronchial biopsy of peripheral lesions is often carried out blindly, lowering the diagnostic yield of bronchoscopy. In response to this problem, we propose to superimpose the lesions and airways segmented from preoperative 3D CT images onto 2D fluoroscopic images. A feature-based 2D/3D registration method is used for image fusion between the two datasets. The algorithm extracts features of the bony structures from both CT and X-ray images to compute the registration. Phantom and clinical studies were carried out to validate the algorithms performance, showing an accuracy of 3.48±1.38mm. The convergence range and speed of the algorithm were also evaluated to investigate the feasibility of using the algorithm clinically. The results are presented.

Heterogeneity of kinetic curve parameters as indicator for the malignancy of breast lesions in DCE MRI

Dynamic contrast enhanced Breast MRI (DCE BMRI) has emerged as powerful tool in the diagnostic work-up of breast cancer. While DCE BMRI is very sensitive, specificity remains to be an issue. Consequently, there is a need for features that support the classification of enhancing lesions into benign and malignant lesions. Traditional features include the morphology and the texture of a lesion, as well as the kinetic parameters of the time-intensity curves, i.e., the temporal change of image intensity at a given location. The kinetic parameters include initial contrast uptake of a lesion and the type of the kinetic curve. The curve type is usually assigned to one of three classes: persistent enhancement (Type I), plateau (Type II), and washout (Type III). While these curve types show a correlation with the tumor type (benign or malignant), only a small sub-volume of the lesion is taken into consideration and the curve type will depend on the location of the ROI that was used to generate the kinetic curve. Furthermore, it has been shown that the curve type significantly depends on which MR scanner was used as well as on the scan parameters. Recently, it was shown that the heterogeneity of a given lesion with respect to spatial variation of the kinetic curve type is a clinically significant indicator for malignancy of a tumor. In this work we compare four quantitative measures for the degree of heterogeneity of the signal enhancement ratio in a tumor and evaluate their ability of predicting the dignity of a tumor. All features are shown to have an area under the ROC curve of between 0.63 and 0.78 (for a single feature).

2D/3D registration for X-ray guided bronchoscopy using distance map classification

In X-ray guided bronchoscopy of peripheral pulmonary lesions, airways and nodules are hardly visible in X-ray images. Transbronchial biopsy of peripheral lesions is often carried out blindly, resulting in degraded diagnostic yield. One solution of this problem is to superimpose the lesions and airways segmented from preoperative 3D CT images onto 2D X-ray images. A feature-based 2D/3D registration method is proposed for the image fusion between the datasets of the two imaging modalities. Two stereo X-ray images are used in the algorithm to improve the accuracy and robustness of the registration. The algorithm extracts the edge features of the bony structures from both CT and X-ray images. The edge points from the X-ray images are categorized into eight groups based on the orientation information of their image gradients. An orientation dependent Euclidean distance map is generated for each group of X-ray feature points. The distance map is then applied to the edge points of the projected CT images whose gradient orientations are compatible with the distance map. The CT and X-ray images are registered by matching the boundaries of the projected CT segmentations to the closest edges of the X-ray images after the orientation constraint is satisfied. Phantom and clinical studies were carried out to validate the algorithms performance, showing a registration accuracy of 4.19(±0.5) mm with 48.39(±9.6) seconds registration time. The algorithm was also evaluated on clinical data, showing promising registration accuracy and robustness.

Detection and Localization of Landmarks in the Lower Extremities Using an Automatically Learned Conditional Random Field.

The detection and localization of single or multiple landmarks is a crucial task in medical imaging. It is often required as initialization for other tasks like segmentation or registration. A common approach to localize multiple landmarks is to exploit their spatial correlations, e.g., by using a conditional random field (CRF) to incorporate geometric information between landmark pairs. This CRF is usually applied to resolve ambiguities of a localizer, e.g., a random forest or a deep neural network. In this paper, we apply a random forest/CRF combination to the task of jointly detecting and localizing 6 landmarks in the lower extremities, taken from a dataset of 660 X-ray images. The dataset is challenging since a significant number of images does not show all the landmarks. Furthermore, 11.3% of the target landmarks are altered by prostheses or pathologies.

Automatic assessment of the quality of patient positioning in mammography

Quality assurance has been recognized as crucial for the success of population-based breast cancer screening programs using x-ray mammography. Quality guidelines and criteria have been defined in the US as well as the European Union in order to ensure the quality of breast cancer screening. Taplin et al. report that incorrect positioning of the breast is the major image quality issue in screening mammography. Consequently, guidelines and criteria for correct positioning and for the assessment of the positioning quality in mammograms play an important role in the quality standards. In this paper we present a system for the automatic evaluation of positioning quality in mammography according to the existing standardized criteria. This involves the automatic detection of anatomic landmarks in medio- lateral oblique (MLO) and cranio-caudal (CC) mammograms, namely the pectoral muscle, the mammilla and the infra-mammary fold. Furthermore, the detected landmarks are assessed with respect to their proper presentation in the image. Finally, the geometric relations between the detected landmarks are investigated to assess the positioning quality. This includes the evaluation whether the pectoral muscle is imaged down to the mammilla level, and whether the posterior nipple line diameter of the breast is consistent between the different views (MLO and CC) of the same breast. Results of the computerized assessment are compared to ground truth collected from two expert readers.

Detection and localization of spatially correlated point landmarks in medical images using an automatically learned conditional random field

Abstract The automatic detection and accurate localization of landmarks is a crucial task in medical imaging. It is necessary for tasks like diagnosis, surgical planning, and post-operative assessment. A common approach to localize multiple landmarks is to combine multiple independent localizers for individual landmarks with a spatial regularizer, e.g., a conditional random field (CRF). Its configuration, e.g., the CRF topology and potential functions, often has to be manually specified w.r.t. the application. In this paper, we present a general framework to automatically learn the optimal configuration of a CRF for localizing multiple landmarks. Furthermore, we introduce a novel “missing” label for each landmark (node in the CRF). The key idea is to define a pool of potentials and optimize their CRF weights and the potential values for missing landmarks in a learning framework. Potentials with a low weight are removed, thus optimizing the graph topology. This allows to easily transfer our framework to new applications, and to integrate different localizers. Further advantages of our algorithm are its low test runtime, low amount of training data, and interpretability. We illustrate its feasibility in a detailed evaluation on three medical datasets featuring high degrees of pathologies and outliers.

Precise anatomy localization in CT data by an improved probabilistic tissue type atlas

Automated interpretation of CT scans is an important, clinically relevant area as the number of such scans is increasing rapidly and the interpretation is time consuming. Anatomy localization is an important prerequisite for any such interpretation task. This can be done by image-to-atlas registration, where the atlas serves as a reference space for annotations such as organ probability maps. Tissue type based atlases allow fast and robust processing of arbitrary CT scans. Here we present two methods which significantly improve organ localization based on tissue types. A first problem is the definition of tissue types, which until now is done heuristically based on experience. We present a method to determine suitable tissue types from sample images automatically. A second problem is the restriction of the transformation space: all prior approaches use global affine maps. We present a hierarchical strategy to refine this global affine map. For each organ or region of interest a localized tissue type atlas is computed and used for a subsequent local affine registration step. A three-fold cross validation on 311 CT images with different fields-of-view demonstrates a reduction of the organ localization error by 33%.

Automated anatomy detection in CT localizer images

In this paper we present a system for the automated detection of multiple anatomies in computer tomography (CT) localizer images. The proposed method employs classification cascades for the fast and accurate localization of individual anatomies. In order to facilitate the joint localization of multiple anatomies, their geometric relations are described in terms of a probabilistic model. This gives rise to a part-based detection approach which allows for the consolidation of multiple detections and the prediction of missed anatomies. The performance of the approach is quantitatively evaluated on a comprehensive set of 737 CT localizer images for five individual and three combined anatomies.