Search

Optical coherence tomography angiography (OCTA) is a non-invasive imaging modality that can acquire high-resolution volumes of the retinal vasculature and aid the diagnosis of ocular, neurological and cardiac diseases. Segmenting the visible blood vessels is a common first step when extracting quantitative biomarkers from these images. Classical segmentation algorithms based on thresholding are strongly affected by image artifacts and limited signal-to-noise ratio. The use of modern, deep learning-based segmentation methods has been inhibited by a lack of large datasets with detailed annotations of the blood vessels. To address this issue, recent work has employed transfer learning, where a segmentation network is trained on synthetic OCTA images and is then applied to real data. However, the previously proposed simulations fail to faithfully model the retinal vasculature and do not provide effective domain adaptation. Because of this, current methods are unable to fully segment the retinal vasculature, in particular the smallest capillaries. In this work, we present a lightweight simulation of the retinal vascular network based on space colonization for faster and more realistic OCTA synthesis. We then introduce three contrast adaptation pipelines to decrease the domain gap between real and artificial images. We demonstrate the superior segmentation performance of our approach in extensive quantitative and qualitative experiments on three public datasets that compare our method to traditional computer vision algorithms and supervised training using human annotations. Finally, we make our entire pipeline publicly available, including the source code, pretrained models, and a large dataset of synthetic OCTA images.

Collateral circulation results from specialized anastomotic channels which are capable of providing oxygenated blood to regions with compromised blood flow caused by arterial obstruction. The quality of collateral circulation has been established as a key factor in determining the likelihood of a favorable clinical outcome and goes a long way to determining the choice of a stroke care model. Though many imaging and grading methods exist for quantifying collateral blood flow, the actual grading is mostly done through manual inspection. This approach is associated with a number of challenges. First, it is time-consuming. Second, there is a high tendency for bias and inconsistency in the final grade assigned to a patient depending on the experience level of the clinician. We present a multi-stage deep learning approach to predict collateral flow grading in stroke patients based on radiomic features extracted from MR perfusion data. First, we formulate a region of interest detection task as a reinforcement learning problem and train a deep learning network to automatically detect the occluded region within the 3D MR perfusion volumes. Second, we extract radiomic features from the obtained region of interest through local image descriptors and denoising auto-encoders. Finally, we apply a convolutional neural network and other machine learning classifiers to the extracted radiomic features to automatically predict the collateral flow grading of the given patient volume as one of three severity classes - no flow (0), moderate flow (1), and good flow (2). Results from our experiments show an overall accuracy of 72% in the three-class prediction task. With an inter-observer agreement of 16% and a maximum intra-observer agreement of 74% in a similar experiment, our automated deep learning approach demonstrates a performance comparable to expert grading, is faster than visual inspection, and eliminates the problem of grading bias., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Tetteh, Navarro, Meier, Kaesmacher, Paetzold, Kirschke, Zimmer, Wiest and Menze.)

Purpose: Although treatment planning and individualized dose application for emerging prostate-specific membrane antigen (PSMA)-targeted radioligand therapy (RLT) are generally recommended, it is still difficult to implement in practice at the moment. In this study, we aimed to prove the concept of pretherapeutic prediction of dosimetry based on imaging and laboratory measurements before the RLT treatment., Methods: Twenty-three patients with metastatic castration-resistant prostate cancer (mCRPC) treated with 177 Lu-PSMA I&T RLT were included retrospectively. They had available pre-therapy 68  Ga-PSMA-HEBD-CC PET/CT and at least 3 planar and 1 SPECT/CT imaging for dosimetry. Overall, 43 cycles of 177 Lu-PSMA I&T RLT were applied. Organ-based standard uptake values (SUVs) were obtained from pre-therapy PET/CT scans. Patient dosimetry was calculated for the kidney, liver, spleen, and salivary glands using Hermes Hybrid Dosimetry 4.0 from the planar and SPECT/CT images. Machine learning methods were explored for dose prediction from organ SUVs and laboratory measurements. The uncertainty of these dose predictions was compared with the population-based dosimetry estimates. Mean absolute percentage error (MAPE) was used to assess the prediction uncertainty of estimated dosimetry., Results: An optimal machine learning method achieved a dosimetry prediction MAPE of 15.8 ± 13.2% for the kidney, 29.6% ± 13.7% for the liver, 23.8% ± 13.1% for the salivary glands, and 32.1 ± 31.4% for the spleen. In contrast, the prediction based on literature population mean has significantly larger MAPE (p < 0.01), 25.5 ± 17.3% for the kidney, 139.1% ± 111.5% for the liver, 67.0 ± 58.3% for the salivary glands, and 54.1 ± 215.3% for the spleen., Conclusion: The preliminary results confirmed the feasibility of pretherapeutic estimation of treatment dosimetry and its added value to empirical population-based estimation. The exploration of dose prediction may support the implementation of treatment planning for RLT., (© 2022. The Author(s).)

Registration methods facilitate the comparison of multiparametric magnetic resonance images acquired at different stages of brain tumor treatments. Image-based registration solutions are influenced by the sequences chosen to compute the distance measure, and the lack of image correspondences due to the resection cavities and pathological tissues. Nonetheless, an evaluation of the impact of these input parameters on the registration of longitudinal data is still missing. This work evaluates the influence of multiple sequences, namely T1-weighted (T1), T2-weighted (T2), contrast enhanced T1-weighted (T1-CE), and T2 Fluid Attenuated Inversion Recovery (FLAIR), and the exclusion of the pathological tissues on the non-rigid registration of pre- and post-operative images. We here investigate two types of registration methods, an iterative approach and a convolutional neural network solution based on a 3D U-Net. We employ two test sets to compute the mean target registration error (mTRE) based on corresponding landmarks. In the first set, markers are positioned exclusively in the surroundings of the pathology. The methods employing T1-CE achieves the lowest mTREs, with a improvement up to 0.8 mm for the iterative solution. The results are higher than the baseline when using the FLAIR sequence. When excluding the pathology, lower mTREs are observable for most of the methods. In the second test set, corresponding landmarks are located in the entire brain volumes. Both solutions employing T1-CE obtain the lowest mTREs, with a decrease up to 1.16 mm for the iterative method, whereas the results worsen using the FLAIR. When excluding the pathology, an improvement is observable for the CNN method using T1-CE. Both approaches utilizing the T1-CE sequence obtain the best mTREs, whereas the FLAIR is the least informative to guide the registration process. Besides, the exclusion of pathology from the distance measure computation improves the registration of the brain tissues surrounding the tumor. Thus, this work provides the first numerical evaluation of the influence of these parameters on the registration of longitudinal magnetic resonance images, and it can be helpful for developing future algorithms., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Canalini, Klein, Waldmannstetter, Kofler, Cerri, Hering, Heldmann, Schlaeger, Menze, Wiestler, Kirschke and Hahn.)

Exploiting 4D-flow magnetic resonance imaging (MRI) data to quantify hemodynamics requires an adequate spatio-temporal vector field resolution at a low noise level. To address this challenge, we provide a learned solution to super-resolve in vivo 4D-flow MRI data at a post-processing level. We propose a deep convolutional neural network (CNN) that learns the inter-scale relationship of the velocity vector map and leverages an efficient residual learning scheme to make it computationally feasible. A novel, direction-sensitive, and robust loss function is crucial to learning vector-field data. We present a detailed comparative study between the proposed super-resolution and the conventional cubic B-spline based vector-field super-resolution. Our method improves the peak-velocity to noise ratio of the flow field by 10 and 30% for in vivo cardiovascular and cerebrovascular data, respectively, for 4 × super-resolution over the state-of-the-art cubic B-spline. Significantly, our method offers 10x faster inference over the cubic B-spline. The proposed approach for super-resolution of 4D-flow data would potentially improve the subsequent calculation of hemodynamic quantities., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Shit, Zimmermann, Ezhov, Paetzold, Sanches, Pirkl and Menze.)

Automatic localization and segmentation of organs-at-risk (OAR) in CT are essential pre-processing steps in medical image analysis tasks, such as radiation therapy planning. For instance, the segmentation of OAR surrounding tumors enables the maximization of radiation to the tumor area without compromising the healthy tissues. However, the current medical workflow requires manual delineation of OAR, which is prone to errors and is annotator-dependent. In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation rather than novel localization or segmentation architectures. To the best of our knowledge, our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging. In the first step, a 3D multi-variate regression network predicts organs' centroids and bounding boxes. Secondly, 3D organ-specific segmentation networks are leveraged to generate a multi-organ segmentation map. Our method achieved an overall Dice score of 0.9260 ± 0.18% on the VISCERAL dataset containing CT scans with varying fields of view and multiple organs.

Self-supervised pretext tasks have been introduced as an effective strategy when learning target tasks on small annotated data sets. However, while current research focuses on exploring novel pretext tasks for meaningful and reusable representation learning for the target task, the study of its robustness and generalizability has remained relatively under-explored. Specifically, it is crucial in medical imaging to proactively investigate performance under different perturbations for reliable deployment of clinical applications. In this work, we revisit medical imaging networks pre-trained with self-supervised learnings and categorically evaluate robustness and generalizability compared to vanilla supervised learning. Our experiments on pneumonia detection in X-rays and multi-organ segmentation in CT yield conclusive results exposing the hidden benefits of self-supervision pre-training for learning robust feature representations.

Background: Hyperpolarization enhances the sensitivity of nuclear magnetic resonance experiments by between four and five orders of magnitude. Several hyperpolarized sensor molecules have been introduced that enable high sensitivity detection of metabolism and physiological parameters. However, hyperpolarized magnetic resonance spectroscopy imaging (MRSI) often suffers from poor signal-to-noise ratio and spectral analysis is complicated by peak overlap. Here, we study measurements of extracellular pH (pH e ) by hyperpolarized zymonic acid, where multiple pH e compartments, such as those observed in healthy kidney or other heterogeneous tissue, result in a cluster of spectrally overlapping peaks, which is hard to resolve with conventional spectroscopy analysis routines., Methods: We investigate whether deep learning methods can yield improved pH e prediction in hyperpolarized zymonic acid spectra of multiple pH e compartments compared to conventional line fitting. As hyperpolarized 13 C-MRSI data sets are often small, a convolutional neural network (CNN) and a multilayer perceptron (MLP) were trained with either a synthetic or a mixed (synthetic and augmented) data set of acquisitions from the kidneys of healthy mice., Results: Comparing the networks' performances compartment-wise on a synthetic test data set and eight real kidney data shows superior performance of CNN compared to MLP and equal or superior performance compared to conventional line fitting. For correct prediction of real kidney pH e values, training with a mixed data set containing only 0.5% real data shows a large improvement compared to training with synthetic data only. Using a manual segmentation approach, pH maps of kidney compartments can be improved by neural network predictions for voxels including three pH compartments., Conclusion: The results of this study indicate that CNNs offer a reliable, accurate, fast and non-interactive method for analysis of hyperpolarized 13 C MRS and MRSI data, where low amounts of acquired data can be complemented to achieve suitable network training., (© 2022. The Author(s).)

The identification of bone lesions is crucial in the diagnostic assessment of multiple myeloma (MM). 68 Ga-Pentixafor PET/CT can capture the abnormal molecular expression of CXCR-4 in addition to anatomical changes. However, whole-body detection of dozens of lesions on hybrid imaging is tedious and error prone. It is even more difficult to identify lesions with a large heterogeneity. This study employed deep learning methods to automatically combine characteristics of PET and CT for whole-body MM bone lesion detection in a 3D manner. Two convolutional neural networks (CNNs), V-Net and W-Net, were adopted to segment and detect the lesions. The feasibility of deep learning for lesion detection on 68 Ga-Pentixafor PET/CT was first verified on digital phantoms generated using realistic PET simulation methods. Then the proposed methods were evaluated on real 68 Ga-Pentixafor PET/CT scans of MM patients. The preliminary results showed that deep learning method can leverage multimodal information for spatial feature representation, and W-Net obtained the best result for segmentation and lesion detection. It also outperformed traditional machine learning methods such as random forest classifier (RF), k -Nearest Neighbors ( k -NN), and support vector machine (SVM). The proof-of-concept study encourages further development of deep learning approach for MM lesion detection in population study.

Tumor hypoxia is a major factor inducing resistance to radiotherapy. Spatial limitation in oxygen (O 2 ) diffusion usually leads to chronic hypoxia, whereas temporary shut-down of perfusion or fluctuations in red blood cell flux can cause acute hypoxia. Since the role of temporal heterogeneity of pO 2 in acute hypoxia during radiotherapy remains unclear, this study focuses on analyzing the influence of temporal heterogeneity of tumor hypoxia upon radiotherapy by modeling the temporal variance of acute hypoxia. The computational simulation was conducted on digital 2D tumor phantoms. The O 2 diffusion and consumption within the tumor tissues were calculated using the reaction-diffusion equation. A total of nine experimental tumor lines (FaDu, GL, C3H, RIF, SCCVII, KHT, MEF, MTG, HT29) were modeled according to known pO 2 distributions. Each tumor line was first simulated 36 times with various temporal heterogeneities (dynamic hypoxia) and once again without temporal heterogeneity (static hypoxia). Temporal pO 2 fluctuations were modeled according to known red blood cell (RBC) fluxes. All tumor phantoms were irradiated with 30 fractions of 2 Gy. Cell survival was calculated as a function of pO 2 and radiation dose via linear quadratic model. The simulation results indicate that the temporal heterogeneity varies with different tumor types, and tumor line HT29 shows the most significant impact of temporal heterogeneity upon the treatment effect. The ratio between the surviving fractions without and with temporal variance ranges from 1.44 to 6.28. Given the same mean pO 2 , the fraction of killed tumor cells in dynamic hypoxia is higher than in static hypoxia. A temporal heterogeneity index (THI) denoting normalized average pO 2 temporal variance is proposed. The results show that for similar mean tumor pO 2 , a strong inverse correlation between THI and the surviving fraction is observed for each tumor line. THI is highly proportional to the fraction of acute hypoxia and to the RBC flux. The proposed THI corresponds well to the fraction of acute hypoxia.

This paper describes a new approach for the reconstruction of complete 3-D arterial trees from partially incomplete image data. We utilize a physiologically motivated simulation framework to iteratively generate artificial, yet physiologically meaningful, vasculatures for the correction of vascular connectivity. The generative approach is guided by a simplified angiogenesis model, while at the same time topological and morphological evidence extracted from the image data is considered to form functionally adequate tree models. We evaluate the effectiveness of our method on four synthetic datasets using different metrics to assess topological and functional differences. Our experiments show that the proposed generative approach is superior to state-of-the-art approaches that only consider topology for vessel reconstruction and performs consistently well across different problem sizes and topologies.

The accurate localization of anatomical landmarks is a challenging task, often solved by domain specific approaches. We propose a method for the automatic localization of landmarks in complex, repetitive anatomical structures. The key idea is to combine three steps: (1) a classifier for pre-filtering anatomical landmark positions that (2) are refined through a Hough regression model, together with (3) a parts-based model of the global landmark topology to select the final landmark positions. During training landmarks are annotated in a set of example volumes. A classifier learns local landmark appearance, and Hough regressors are trained to aggregate neighborhood information to a precise landmark coordinate position. A non-parametric geometric model encodes the spatial relationships between the landmarks and derives a topology which connects mutually predictive landmarks. During the global search we classify all voxels in the query volume, and perform regression-based agglomeration of landmark probabilities to highly accurate and specific candidate points at potential landmark locations. We encode the candidates' weights together with the conformity of the connecting edges to the learnt geometric model in a Markov Random Field (MRF). By solving the corresponding discrete optimization problem, the most probable location for each model landmark is found in the query volume. We show that this approach is able to consistently localize the model landmarks despite the complex and repetitive character of the anatomical structures on three challenging data sets (hand radiographs, hand CTs, and whole body CTs), with a median localization error of 0.80 mm, 1.19 mm and 2.71 mm, respectively., (Copyright © 2013 Elsevier B.V. All rights reserved.)

Anatomical changes like brain atrophy or growth are usually not homogeneous in space and across spatial scales, since they map differently depending on the anatomical structures. Thus, the accurate analysis of volume changes from medical images requires to reliably localize and distinguish the spatial changes occurring at different scales, from voxel to regional level. We propose here a framework for the sparse probabilistic scale-space analysis of volume changes encoded by deformations. Our framework is based on the Helmoltz decomposition of vector fields. By scale-space analysis of the scalar pressure map associated to the irrotational component of the deformation, we robustly identify the areas of maximal volume changes, and we define a consistent sparse decomposition of the irrotational component. We show the effectiveness of our framework in the challenging problem of detecting the progression of tumor growth, and in the group-wise analysis of the longitudinal atrophy in Alzheimer's disease.

Rationale and Objectives: The aim of this study was to assess (1) automated analysis methods versus manual evaluation by human experts of three-dimensional proton magnetic resonance spectroscopic imaging (MRSI) data from patients with prostate cancer and (2) the contribution of spatial information to decision making., Materials and Methods: Three-dimensional proton MRSI was applied at 1.5 T. MRSI data from 10 patients with histologically proven prostate adenocarcinoma, scheduled either for prostatectomy or intensity-modulated radiation therapy, were evaluated. First, two readers manually labeled spectra using spatial information to identify the localization of spectra and neighborhood information, establishing the reference set of this study. Then, spectra were labeled again manually in a blinded and randomized manner and evaluated automatically using software that applied spectral line fitting as well as pattern recognition routines. Statistical analysis of the results of the different approaches was performed., Results: Altogether, 1018 spectra were evaluable by all methods. Numbers of evaluable spectra differed significantly depending on patient and evaluation method. Compared to automated analysis, the readers made rather binary decisions, using information from neighboring spectra in ambiguous cases, when evaluating MRSI data as a whole. Differences between anatomically blinded and unblinded evaluation were larger than differences between evaluations using blinded data and automated techniques., Conclusions: An automated approach, which evaluates each spectrum individually, can be as good as an anatomy-blinded human reader. Spatial information is routinely used by human experts to support their final decisions. Automated procedures that consider anatomic information for spectral evaluation will enhance the diagnostic impact of MRSI of the human prostate., (Copyright © 2012 AUR. Published by Elsevier Inc. All rights reserved.)

The landscapes of the Near East show both the first settlements and the longest trajectories of settlement systems. Mounding is a characteristic property of these settlement sites, resulting from millennia of continuing settlement activity at distinguished places. So far, however, this defining feature of ancient settlements has not received much attention, or even been the subject of systematic evaluation. We propose a remote sensing approach for comprehensively mapping the pattern of human settlement at large scale and establish the largest archaeological record for a landscape in Mesopotamia, mapping about 14,000 settlement sites--spanning eight millennia--at 15-m resolution in a 23,000-km(2) area in northeastern Syria. To map both low- and high-mounded places--the latter of which are often referred to as "tells"--we develop a strategy for detecting anthrosols in time series of multispectral satellite images and measure the volume of settlement sites in a digital elevation model. Using this volume as a proxy to continued occupation, we find a dependency of the long-term attractiveness of a site on local water availability, but also a strong relation to the relevance within a basin-wide exchange network that we can infer from our record and third millennium B.C. intersite routes visible on the ground until recent times. We believe it is possible to establish a nearly comprehensive map of human settlements in the fluvial plains of northern Mesopotamia and beyond, and site volume may be a key quantity to uncover long-term trends in human settlement activity from such a record.

We propose a Bayesian smoothness prior in the spectral fitting of MRS images which can be used in addition to commonly employed prior knowledge. By combining a frequency-domain model for the free induction decay with a Gaussian Markov random field prior, a new optimization objective is derived that encourages smooth parameter maps. Using a particular parameterization of the prior, smooth damping, frequency and phase maps can be obtained whilst preserving sharp spatial features in the amplitude map. A Monte Carlo study based on two sets of simulated data demonstrates that the variance of the estimated parameter maps can be reduced considerably, even below the Cramér-Rao lower bound, when using spatial prior knowledge. Long-TE (1)H MRSI at 1.5 T of a patient with a brain tumor shows that the use of the spatial prior resolves the overlapping peaks of choline and creatine when a single voxel method fails to do so. Improved and detailed metabolic maps can be derived from high-spatial-resolution, short-TE (1)H MRSI at 3 T. Finally, the evaluation of four series of long-TE brain MRSI data with various signal-to-noise ratios shows the general benefit of the proposed approach., (Copyright © 2011 John Wiley & Sons, Ltd.)

Biophysical models are increasingly used for medical applications at the organ scale. However, model predictions are rarely associated with a confidence measure although there are important sources of uncertainty in computational physiology methods. For instance, the sparsity and noise of the clinical data used to adjust the model parameters (personalization), and the difficulty in modeling accurately soft tissue physiology. The recent theoretical progresses in stochastic models make their use computationally tractable, but there is still a challenge in estimating patient-specific parameters with such models. In this work we propose an efficient Bayesian inference method for model personalization using polynomial chaos and compressed sensing. This method makes Bayesian inference feasible in real 3D modeling problems. We demonstrate our method on cardiac electrophysiology. We first present validation results on synthetic data, then we apply the proposed method to clinical data. We demonstrate how this can help in quantifying the impact of the data characteristics on the personalization (and thus prediction) results. Described method can be beneficial for the clinical use of personalized models as it explicitly takes into account the uncertainties on the data and the model parameters while still enabling simulations that can be used to optimize treatment. Such uncertainty handling can be pivotal for the proper use of modeling as a clinical tool, because there is a crucial requirement to know the confidence one can have in personalized models., (Copyright © 2011 Elsevier Ltd. All rights reserved.)

A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D Magnetic Resonance (MR) images. It builds on a discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume. The method uses multi-channel MR intensities (T1, T2, and FLAIR), knowledge on tissue classes and long-range spatial context to discriminate lesions from background. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an asymmetric way. Quantitative evaluation of the proposed methods is carried out on publicly available labeled cases from the MICCAI MS Lesion Segmentation Challenge 2008 dataset. When tested on the same data, the presented method compares favorably to all earlier methods. In an a posteriori analysis, we show how selected features during classification can be ranked according to their discriminative power and reveal the most important ones., (Copyright © 2011 Elsevier Inc. All rights reserved.)

The relationship between spatially distributed fMRI patterns and experimental stimuli or tasks offers insights into cognitive processes beyond those traceable from individual local activations. The multivariate properties of the fMRI signals allow us to infer interactions among individual regions and to detect distributed activations of multiple areas. Detection of task-specific multivariate activity in fMRI data is an important open problem that has drawn much interest recently. In this paper, we study and demonstrate the benefits of random forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a multivariate neural response. The Gini importance measure quantifies the predictive power of a particular feature when considered as part of the entire pattern. The measure is based on a random sampling of fMRI time points and voxels. As a consequence the resulting voxel score, or Gini contrast, is highly reproducible and reliably includes all informative features. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead, it uses the predictive power of features to characterize their relevance for encoding task information. The Gini contrast offers an additional advantage of directly quantifying the task-relevant information in a multiclass setting, rather than reducing the problem to several binary classification subproblems. In a multicategory visual fMRI study, the proposed method identified informative regions not detected by the univariate criteria, such as the t-test or the F-test. Including these additional regions in the feature set improves the accuracy of multicategory classification. Moreover, we demonstrate higher classification accuracy and stability of the detected spatial patterns across runs than the traditional methods such as the recursive feature elimination used in conjunction with support vector machines., (Copyright © 2010 Elsevier Inc. All rights reserved.)

Extensive imaging is routinely used in brain tumor patients to monitor the state of the disease and to evaluate therapeutic options. A large number of multi-modal and multi-temporal image volumes is acquired in standard clinical cases, requiring new approaches for comprehensive integration of information from different image sources and different time points. In this work we propose a joint generative model of tumor growth and of image observation that naturally handles multimodal and longitudinal data. We use the model for analyzing imaging data in patients with glioma. The tumor growth model is based on a reaction-diffusion framework. Model personalization relies only on a forward model for the growth process and on image likelihood. We take advantage of an adaptive sparse grid approximation for efficient inference via Markov Chain Monte Carlo sampling. The approach can be used for integrating information from different multi-modal imaging protocols and can easily be adapted to other tumor growth models.

Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a method for joint segmentation of corresponding regions of interest in a collection of aligned images that does not require labeled training data. Instead, a latent atlas, initialized by at most a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The algorithm is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria. We evaluate the method on two datasets, segmenting subcortical and cortical structures in a multi-subject study and extracting brain tumors in a single-subject multi-modal longitudinal experiment. We compare the segmentation results to manual segmentations, when those exist, and to the results of a state-of-the-art atlas-based segmentation method. The quality of the results supports the latent atlas as a promising alternative when existing atlases are not compatible with the images to be segmented., (Copyright 2010 Elsevier B.V. All rights reserved.)

Reaction-diffusion based tumor growth models have been widely used in the literature for modeling the growth of brain gliomas. Lately, recent models have started integrating medical images in their formulation. Including different tissue types, geometry of the brain and the directions of white matter fiber tracts improved the spatial accuracy of reaction-diffusion models. The adaptation of the general model to the specific patient cases on the other hand has not been studied thoroughly yet. In this paper, we address this adaptation. We propose a parameter estimation method for reaction-diffusion tumor growth models using time series of medical images. This method estimates the patient specific parameters of the model using the images of the patient taken at successive time instances. The proposed method formulates the evolution of the tumor delineation visible in the images based on the reaction-diffusion dynamics; therefore, it remains consistent with the information available. We perform thorough analysis of the method using synthetic tumors and show important couplings between parameters of the reaction-diffusion model. We show that several parameters can be uniquely identified in the case of fixing one parameter, namely the proliferation rate of tumor cells. Moreover, regardless of the value the proliferation rate is fixed to, the speed of growth of the tumor can be estimated in terms of the model parameters with accuracy. We also show that using the model-based speed, we can simulate the evolution of the tumor for the specific patient case. Finally, we apply our method to two real cases and show promising preliminary results.

A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D MR images. It builds on the discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume. Our method uses multi-channel MIR intensities (T1, T2, Flair), spatial prior and long-range comparisons with 3D regions to discriminate lesions. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an asymmetric way. Quantitative evaluation of the data is carried out on publicly available labeled cases from the MS Lesion Segmentation Challenge 2008 dataset and demonstrates improved results over the state of the art.

We introduce a generative probabilistic model for segmentation of tumors in multi-dimensional images. The model allows for different tumor boundaries in each channel, reflecting difference in tumor appearance across modalities. We augment a probabilistic atlas of healthy tissue priors with a latent atlas of the lesion and derive the estimation algorithm to extract tumor boundaries and the latent atlas from the image data. We present experiments on 25 glioma patient data sets, demonstrating significant improvement over the traditional multivariate tumor segmentation.

Dynamic contrast-enhanced magnetic resonance (DCE-MR) imaging can be used to study microvascular structure in vivo by monitoring the abundance of an injected diffusible contrast agent over time. The resulting spatially resolved intensity-time curves are usually interpreted in terms of kinetic parameters obtained by fitting a pharmacokinetic model to the observed data. Least squares estimates of the highly nonlinear model parameters, however, can exhibit high variance and can be severely biased. As a remedy, we bring to bear spatial prior knowledge by means of a generalized Gaussian Markov random field (GGMRF). By using information from neighboring voxels and computing the maximum a posteriori solution for entire parameter maps at once, both bias and variance of the parameter estimates can be reduced thus leading to smaller root mean square error (RMSE). Since the number of variables gets very big for common image resolutions, sparse solvers have to be employed. To this end, we propose a generalized iterated conditional modes (ICM) algorithm operating on blocks instead of sites which is shown to converge considerably faster than the conventional ICM algorithm. Results on simulated DCE-MR images show a clear reduction of RMSE and variance as well as, in some cases, reduced estimation bias. The mean residual bias (MRB) is reduced on the simulated data as well as for all 37 patients of a prostate DCE-MRI dataset. Using the proposed algorithm, average computation times only increase by a factor of 1.18 (871 ms per voxel) for a Gaussian prior and 1.51 (1.12 s per voxel) for an edge-preserving prior compared to the single voxel approach (740 ms per voxel).

Background: Regularized regression methods such as principal component or partial least squares regression perform well in learning tasks on high dimensional spectral data, but cannot explicitly eliminate irrelevant features. The random forest classifier with its associated Gini feature importance, on the other hand, allows for an explicit feature elimination, but may not be optimally adapted to spectral data due to the topology of its constituent classification trees which are based on orthogonal splits in feature space., Results: We propose to combine the best of both approaches, and evaluated the joint use of a feature selection based on a recursive feature elimination using the Gini importance of random forests' together with regularized classification methods on spectral data sets from medical diagnostics, chemotaxonomy, biomedical analytics, food science, and synthetically modified spectral data. Here, a feature selection using the Gini feature importance with a regularized classification by discriminant partial least squares regression performed as well as or better than a filtering according to different univariate statistical tests, or using regression coefficients in a backward feature elimination. It outperformed the direct application of the random forest classifier, or the direct application of the regularized classifiers on the full set of features., Conclusion: The Gini importance of the random forest provided superior means for measuring feature relevance on spectral data, but - on an optimal subset of features - the regularized classifiers might be preferable over the random forest classifier, in spite of their limitation to model linear dependencies only. A feature selection based on Gini importance, however, may precede a regularized linear classification to identify this optimal subset of features, and to earn a double benefit of both dimensionality reduction and the elimination of noise from the classification task.

Protein identification by tandem mass spectrometry is based on the reliable processing of the acquired data. Unfortunately, the generation of a large number of poor quality spectra is commonly observed in LC-MS/MS, and the processing of these mostly noninformative spectra with its associated costs should be avoided. We present a continuous quality score that can be computed very quickly and that can be considered an approximation of the MASCOT score in case of a correct identification. This score can be used to reject low quality spectra prior to database identification, or to draw attention to those spectra that exhibit a (supposedly) high information content, but could not be identified. The proposed quality score can be calibrated automatically on site without the need for a manually generated training set. When this score is turned into a classifier and when features are used that are independent of the instrument, the proposed approach performs equally to previously published classifiers and feature sets and also gives insights into the behavior of the MASCOT score.

Besides the diagnostic evaluation of a spectrum, the assessment of its quality and a check for plausibility of its information remains a highly interactive and thus time-consuming process in MR spectroscopic imaging (MRSI) data analysis. In the automation of this quality control, a score is proposed that is obtained by training a machine learning classifier on a representative set of spectra that have previously been classified by experts into evaluable data and nonevaluable data. In the first quantitative evaluation of different quality measures on a test set of 45,312 long echo time spectra in the diagnosis of brain tumor, the proposed pattern recognition (using the random forest classifier) separated high- and low-quality spectra comparable to the human operator (area-under-the-curve of the receiver-operator-characteristic, AUC>0.993), and performed better than decision rules based on the signal-to-noise-ratio (AUC<0.934) or the estimated Cramér-Rao-bound on the errors of a spectral fitting (AUC<0.952). This probabilistic assessment of the data quality provides comprehensible confidence images and allows filtering the input of any subsequent data processing, i.e., quantitation or pattern recognition, in an automated fashion. It thus can increase robustness and reliability of the final diagnostic evaluation and allows for the automation of a tedious part of MRSI data analysis., (Copyright (c) 2008 Wiley-Liss, Inc.)

A hierarchical scheme has been developed for detection of bovine spongiform encephalopathy (BSE) in serum on the basis of its infrared spectral signature. In the first stage, binary subsets between samples originating from diseased and non-diseased cattle are defined along known covariates within the data set. Random forests are then used to select spectral channels on each subset, on the basis of a multivariate measure of variable importance, the Gini importance. The selected features are then used to establish binary discriminations within each subset by means of ridge regression. In the second stage of the hierarchical procedure the predictions from all linear classifiers are used as input to another random forest that provides the final classification. When applied to an independent, blinded validation set of 160 further spectra (84 BSE-positives, 76 BSE-negatives), the hierarchical classifier achieves a sensitivity of 92% and a specificity of 95%. Compared with results from an earlier study based on the same data, the hierarchical scheme performs better than linear discriminant analysis with features selected by genetic optimization and robust linear discriminant analysis, and performs as well as a neural network and a support vector machine.

Despite its diagnostic value and technological availability, (1)H NMR spectroscopic imaging (MRSI) has not found its way into clinical routine yet. Prerequisite for the clinical application is an automated and reliable method for the diagnostic evaluation of MRS images. In the present paper, different approaches to the estimation of tumor probability from MRSI in the prostate are assessed. Two approaches to feature extraction are compared: quantification (VARPRO, AMARES, QUEST) and subspace methods on spectral patterns (principal components, independent components, nonnegative matrix factorization, partial least squares). Linear as well as nonlinear classifiers (support vector machines, Gaussian processes, random forests) are applied and discussed. Quantification-based approaches are much more sensitive to the choice and parameterization of the quantification algorithm than to the choice of the classifier. Furthermore, linear methods based on magnitude spectra easily achieve equal performance and also allow for biochemical interpretation in combination with subspace methods. Nonlinear methods operating directly on magnitude spectra achieve the best results but are less transparent than the linear methods.