René Donner

Fast Active Appearance Model Search Using Canonical Correlation Analysis

A fast AAM search algorithm based on canonical correlation analysis (CCA-AAM) is introduced. It efficiently models the dependency between texture residuals and model parameters during search. Experiments show that CCA-AAMs, while requiring similar implementation effort, consistently outperform standard search with regard to convergence speed by a factor of four

Global localization of 3D anatomical structures by pre-filtered Hough Forests and discrete optimization

Graphical abstract Highlights ► Automatic localization of landmarks in complex, repetitive anatomical structures. ► Random Forest classifiers for every landmark as a pre-filtering stage. ► Hough regression model for refining the landmark candidate positions. ► Parts-based model of global landmark topology to select the final landmark positions. ► Results on three challenging data sets, median residuals of 0.80 mm, 1.19 mm, 2.71 mm.

3D and Infrared Face Reconstruction from RGB data using Canonical Correlation Analysis

In this paper, we apply a multiple regression method based on canonical correlation analysis (CCA) to face data modelling. CCA is a factor analysis method which exploits the correlation between two high dimensional signals. We first use CCA to perform 3D face reconstruction and in a separate application we predict near-infrared (NIR) face texture. In both cases, the input data are color (RGB) face images. Experiments show, that due to the correlation between input and output signal, only a small number of canonical factors are needed to describe the functional relation of RGB images to the respective output (NIR images and 3D depth maps) with reasonable accuracy

Sparse MRF Appearance Models for Fast Anatomical Structure Localisation

Image segmentation methods like active shape models, active appearance models or snakes require an initialisation that guarantees a considerable overlap with the object to be segmented. In this paper we present an approach that localises anatomical structures in a global manner by means of Markov Random Fields (MRF). It does not need initialisation, but finds the most plausible match of the query structure in the image. It provides for precise, reliable and fast detection of the structure and can serve as initialisation for more detailed segmentation steps. Sparse MRF Appearance Models (SAMs) encode a priori information about the geometric configurations of interest points, local features at these points and local features along the edges of adjacent points. This information is used to formulate a Markov Random Field and the mapping of the modeled object (e.g. a sequence of vertebrae) to the query image interest points is performed by the MAX-SUM algorithm. The local image information is captured by novel symmetry-based interest points and local descriptors derived from Gradient Vector Flow. Experimental results are reported for two data-sets showing the applicability to complex medical data.

Robust autonomous model learning from 2D and 3D data sets

In this paper we propose a weakly supervised learning algorithm for appearance models based on the minimum description length (MDL) principle. From a set of training images or volumes depicting examples of an anatomical structure, correspondences for a set of landmarks are established by group-wise registration. The approach does not require any annotation. In contrast to existing methods no assumptions about the topology of the data are made, and the topology can change throughout the data set. Instead of a continuous representation of the volumes or images, only sparse finite sets of interest points are used to represent the examples during optimization. This enables the algorithm to efficiently use distinctive points, and to handle texture variations robustly. In contrast to standard elasticity based deformation constraints the MDL criterion accounts for systematic deformations typical for training sets stemming from medical image data. Experimental results are reported for five different 2D and 3D data sets.

Superpixel-Based interest points for effective bags of visual words medical image retrieval

The present work introduces a 2D medical image retrieval system which employs interest points derived from superpixels in a bags of visual words (BVW) framework. BVWs rely on stable interest points so that the local descriptors can be clustered into representative, discriminative prototypes (the visual words). We show that using the centers of mass of superpixels as interest points yields higher retrieval accuracy when compared to using Difference of Gaussians (DoG) or a dense grid of interest points. Evaluation is performed on two data sets. The ImageCLEF 2009 data set of 14.400 radiographs is used in a categorization setting and the results compare favorable to more specialized methods. The second set contains 13 thorax CTs and is used in a hybrid 2D/3D localization task, localizing the axial position of the lung through the retrieval of representative 2D slices.

Texture bags: anomaly retrieval in medical images based on local 3d-texture similarity

Providing efficient access to the huge amounts of existing medical imaging data is a highly relevant but challenging problem. In this paper, we present an effective method for content-based image retrieval (CBIR) of anomalies in medical imaging data, based on similarity of local 3D texture. During learning, a texture vocabulary is obtained from training data in an unsupervised fashion by extracting the dominant structure of texture descriptors. It is based on a 3D extension of the Local Binary Pattern operator (LBP), and captures texture properties via descriptor histograms of supervoxels, or texture bags. For retrieval, our method computes a texture histogram of a query region marked by a physician, and searches for similar bags via diffusion distance. The retrieval result is a ranked list of cases based on the occurrence of regions with similar local texture structure. Experiments show that the proposed local texture retrieval approach outperforms analogous global similarity measures.

Active Feature Models

In this paper active feature models are proposed. They utilize local texture features and a statistical shape model for the reliable localization of landmarks in images. They are related to active appearance models, but instead of modelling the entire texture of an object they represent image texture by means of local descriptors. The approach has advantages with complex image data like anatomical structures that exhibit high texture variation with limited relevance for the recognition of the object location. Experimental results and the comparison to AAMs on different data sets indicate that active feature models can improve search speed and result accuracy, considerably

Towards Automatic Bone Age Estimation from MRI: Localization of 3D Anatomical Landmarks

Bone age estimation (BAE) is an important procedure in forensic practice which recently has seen a shift in attention from X-ray to MRI based imaging. To automate BAE from MRI, localization of the joints between hand bones is a crucial first step, which is challenging due to anatomical variations, different poses and repeating structures within the hand. We propose a landmark localization algorithm using multiple random regression forests, first analyzing the shape of the hand from information of the whole image, thus implicitly modeling the global landmark configuration, followed by a refinement based on more local information to increase prediction accuracy. We are able to clearly outperform related approaches on our dataset of 60 T1-weighted MR images, achieving a mean landmark localization error of 1.4 ± 1.5mm, while having only 0.25% outliers with an error greater than 10mm.

Thermal effects of a combined irrigation method during implant site drilling. A standardized in vitro study using a bovine rib model

OBJECTIVES The purpose of this study was to evaluate the temperature changes during implant osteotomies with a combined irrigation system as compared to the commonly used external and internal irrigation under standardized conditions. MATERIAL AND METHODS Drilling procedures were performed on VII bovine ribs using a computer-aided surgical system that ensured automated intermittent drilling cycles to simulate clinical conditions. A total of 320 drilling osteotomies were performed with twist (2 mm) and conical implant drills (3.5/4.3/5 mm) at various drilling depths (10/16 mm) and with different saline irrigation (50 ml/min) methods (without/external/internal/combined). Temperature changes were recorded in real time by two custom-built thermoprobes with 14 temperature sensors (7 sensors/thermoprobe) at defined measuring depths. RESULTS The highest temperature increase during osteotomies was observed without any coolant irrigation (median, 8.01°C), followed by commonly used external saline irrigation (median, 2.60°C), combined irrigation (median, 1.51°C) and ultimately with internal saline irrigation (median, 1.48°C). Temperature increase with different drill diameters showed significant differences (P < 0.05) regarding drill depth, confirming drill depth and time of drilling as influencing factors of heat generation. Internal saline irrigation showed a significantly smaller temperature increase (P < 0.05) compared with combined and external irrigation. A combined irrigation procedure appears to be preferable (P < 0.05) to an external irrigation method primarily with higher osteotomy depths. CONCLUSIONS Combined irrigation provides sufficient reduction in temperature changes during drilling, and it may be more beneficial in deeper site osteotomies. Further studies to optimize the effects of a combined irrigation are needed.