Dominik Kutra

Automatic multi-model-based segmentation of the left atrium in cardiac MRI scans

Model-based segmentation approaches have been proven to produce very accurate segmentation results while simultaneously providing an anatomic labeling for the segmented structures. However, variations of the anatomy, as they are often encountered e.g. on the drainage pattern of the pulmonary veins to the left atrium, cannot be represented by a single model. Automatic model selection extends the model-based segmentation approach to handling significant variational anatomies without user interaction. Using models for the three most common anatomical variations of the left atrium, we propose a method that uses an estimation of the local fit of different models to select the best fitting model automatically. Our approach employs the support vector machine for the automatic model selection. The method was evaluated on 42 very accurate segmentations of MRI scans using three different models. The correct model was chosen in 88.1% of the cases. In a second experiment, reflecting average segmentation results, the model corresponding to the clinical classification was automatically found in 78.0% of the cases.

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.

Breast Conserving Surgery Outcome Prediction: A Patient-Specific, Integrated Multi-modal Imaging and Mechano-Biological Modelling Framework

Patient-specific surgical predictions of Breast Conserving Therapy, through mechano-biological simulations, could inform the shared decision making process between clinicians and patients by enabling the impact of different surgical options to be visualised. We present an overview of our processing workflow that integrates MR images and three dimensional optical surface scans into a personalised model. Utilising an interactively generated surgical plan, a multi-scale open source finite element solver is employed to simulate breast deformity based on interrelated physiological and biomechanical processes that occur post surgery. Our outcome predictions, based on the pre-surgical imaging, were validated by comparing the simulated outcome with follow-up surface scans of four patients acquired 6 to 12 months post-surgery. A mean absolute surface distance of 3.3i¾?mm between the follow-up scan and the simulation was obtained.

Inter- and intra-observer variations in the delineation of lesions in mammograms

Many clinical and research tasks require the delineation of lesions in radiological images. There is a variety of methods available for deriving such delineations, ranging from free hand manual contouring and manual positioning of lowparameter graphical objects, to (semi-)automatic computerized segmentation methods. In this paper we investigate the impact of the chosen segmentation method on the inter-observer variability of the resulting contour. Three different methods are compared in this paper, namely (1) manual positioning of an ellipse, (2) an automatic segmentation method, coined live-segmentation, which depends on the current mouse pointer position as input information and is updated in real-time as the user hovers with the mouse over the image and (3) free form segmentation which is realized by allowing the user to pull the result of method (2) to image positions that the contour is required to pass. Each of the three methods was used by three experienced radiologists to delineate a set of 215 round breast lesion images in digital mammograms. Agreement between contours was assessed by computing the Dice coefficient. The median Dice coefficient for the ellipses placed by different readers was 0.85. The intra-reader Dice coefficient comparing ellipses and livesegmentations was 0.84, thus showing that the live-segmentation results agree with ellipse segmentations to the same extent as readers agree on the ellipse placement. Inter-observer agreement when using the live-segmentation was higher than for the ellipses (median Dice = 0.91 vs. 0.85) showing that the live-segmentation is a more reproducible alternative to the ellipse placement.

An anatomically oriented breast model for MRI

Breast cancer is the most common cancer in women in the western world. In the breast cancer care-cycle, MRIis e.g. employed in lesion characterization and therapy assessment. Reading of a single three dimensional image or comparing a multitude of such images in a time series is a time consuming task. Radiological reporting is done manually by translating the spatial position of a finding in an image to a generic representation in the form of a breast diagram, outlining quadrants or clock positions. Currently, registration algorithms are employed to aid with the reading and interpretation of longitudinal studies by providing positional correspondence. To aid with the reporting of findings, knowledge about the breast anatomy has to be introduced to translate from patient specific positions to a generic representation. In our approach we fit a geometric primitive, the semi-super-ellipsoid to patient data. Anatomical knowledge is incorporated by fixing the tip of the super-ellipsoid to the mammilla position and constraining its center-point to a reference plane defined by landmarks on the sternum. A coordinate system is then constructed by linearly scaling the fitted super-ellipsoid, defining a unique set of parameters to each point in the image volume. By fitting such a coordinate system to a different image of the same patient, positional correspondence can be generated. We have validated our method on eight pairs of baseline and follow-up scans (16 breasts) that were acquired for the assessment of neo-adjuvant chemotherapy. On average, the location predicted and the actual location of manually set landmarks are within a distance of 5.6 mm. Our proposed method allows for automatic reporting simply by uniformly dividing the super-ellipsoid around its main axis.

Identification of corresponding lesions in multiple mammographic views using star-shaped iso-contours

It is common practice to assess lesions in two different mammographic views of each breast: medio-lateral oblique (MLO) and cranio-caudal (CC). We investigate methods that aim at automatic identification of a lesion which was indicated by the user in one view in the other view of the same breast. Automated matching of user indicated lesions has slightly different objectives than lesion segmentation or matching for improved computer aided detection, leading to different algorithmic choices. A novel computationally efficient algorithm is presented which is based on detection of star-shaped iso-contours with high sphericity and local consistency. The lesion likelihood is derived from a purely geometry based figure of merit and thus is invariant against monotonous intensity transformations (e.g. non-linear LUTs).Validation was carried out by virtue of FROC curves on a public database consisting of entirely digital mammograms with expert-delineated match pairs, showing superior performance as compared to gradient-based minimum cost path algorithms, with computation times faster by an order of magnitude and the potential of being fully parallelizable for GPU implementations.