Search

• We propose a novel Deep Learning model, namely the ResQu-Net, specifically tailored for Peripheral Zone Segmentation on T2W MR images. • Six DL architectures were implemented and compared using three openly available datasets with 392 patient cases. • Qualitative Explainability Analysis reveals that conventional segmentation metrics, such as Dice Score, and Hausdorff Distance, might not reflect properly the performance of a DL segmentation model. Prostate cancer is a leading cause of male cancer worldwide. With more than 70 % of prostate cancers arising in the peripheral zone of the prostate, accurate segmentation of this region is of paramount importance for the effective diagnosis and treatment of the disease. Although peripheral zone is well recognized as one of the most challenging regions to delineate within the prostate, no algorithms specifically tailored for this segmentation task are currently available. The present study introduces a new deep learning (DL) algorithm, named as ResQu-Net, which is designed to accurately segment the peripheral zone (PZ) of the prostate on T2-weighted magnetic resonance imaging (MRI). Using three publicly available datasets, the ResQu-Net outperformed the six DL segmentation models used for comparison, namely the Attention U-Net, the Dense2U-Net, the Proper-Net, the TransU-net, the U-Net, and the USE-Net, demonstrating superior performance for different anatomical regions, such as the apex, the midgland and the base. The assessment of the suggested approach was conducted not only quantitatively (Sensitivity, Balanced Accuracy, Dice Score, 95 % Hausdorff Distance, and Average Surface Distance) but also qualitatively. For the qualitative evaluation the feature maps obtained from the last layers of each model were compared with the Density Map of the Ground Truth annotations using root mean squared error. Overall, the ResQu-Net model exhibits improved performance compared to other models, of more than 5 % and 1.87 mm in terms of Dice Score and 95 % Hausdorff Distance, respectively. These advancements may contribute significantly in addressing the challenges associated with PZ segmentation, and ultimately enabling improved clinical decision-making and patient outcomes. [ABSTRACT FROM AUTHOR]

• T2, T2* relaxometry can be used to support diagnosis for lipomatous neoplasms. • The amount of signal loss related to spin coupling phenomena is indicative of lipomatous tumor histological grading. • Pre-operative biopsy guidance can be facilitated as areas of good or poor differentiation are identified on a pixel basis. Subcutaneous fat may have variable signal intensity on T2w images depending on the choice of imaging parameters. However, fatty components within tumors have a different degree of signal dependence on the acquisition scheme. This study examined the use of T2, T2* relaxometry and spin coupling related signal changes (Spin Coupling ratio, SCr) on two different imaging protocols as clinically relevant descriptors of benign and malignant lipomatous tumors. 20 patients with benign lipomas or liposarcomas of variable histologic grade were examined at an 1.5 T scanner with Multi Echo Spin Echo (MESE) different echo spacing (ESP) in order to produce bright fat T2w images (ESP: 13.4 ms, 25 equidistant echoes) and dark fat images (ESP: 26.8 ms with 10 equidistant echoes). T2* relaxometry acquisition comprises 4 sets of in-opposed echoes (2.4–19.2 ms, ESP: 2.4 ms) Multi Echo Gradient Echo (MEGRE) sequence. All parametric maps were calculated on a pixel basis. Significant differences of SCr were found for five different types of lipomatous tumors (Pairwise t -test with Bonferroni correction): lipomas, well differentiated liposarcomas, myxoid liposarcomas, pleomorphic liposarcomas and poorly differentiated liposarcomas. SCr surpassed the classification performance of T2 and T2* relaxometry. A novel biomarker based on spin coupling related signal loss, SCr, is indicative of lipomatous tumor histological grading. We concluded that T2, T2* and SCr can be used for the classification of fat containing tumors, which may be important for biopsy guidance in heterogeneous masses and treatment planning. [ABSTRACT FROM AUTHOR]

Abstract Purpose The purpose of this study was to correlate diffusion and perfusion quantitative and semi-quantitative MR parameters, on patients with peripheral arterial disease. In addition, we investigated which perfusion model better describes the behavior of the dynamic contrast-enhanced (DCE) MR data signal on ischemic regions of the lower limb. Methods Linear and nonlinear least squares algorithms, were incorporated for the quantification of the parameters through a variety of widely used models, able to extract physiological information from each imaging technique. All numerical calculations were implemented in Python 3.5 and include the: Intra voxel incoherent motion for diffusion and Patlak's, Extended Toft's and Gamma Capillary Transit time (GCTT) models for perfusion MRI. Results Our initial voxel by voxel correlation analysis didn't show any significant correlation based on the Pearson's Correlation metric between diffusion and perfusion parameters. To account for the inherited noise from the raw data, a Gaussian filter was applied to the parametric maps in order for the data to be comparable. By repeating our analysis in the filtered image maps, a good correlation (>0.5) of diffusion and perfusion parameters was achieved. Conclusions Perfusion and diffusion MRI quantitative and semi-quantitative parameters can be obtained through a variety of physiological-pharmacokinetic models. This paper compares most of the widely-known models and parameters in both techniques with data from patients with peripheral arterial disease. Initial analysis showed no correlation in the perfusion parametric maps of DWI and DCE MRI data but a good correlation was obtained after smoothing the parametric maps indicating that perfusion information could be obtained from diffusion MRI images in patients with peripheral arterial disease. [ABSTRACT FROM AUTHOR]

To assess the progression of coronary artery disease, Optical Coherence Tomography (OCT) pullbacks acquired at different timepoints should be compared. However, the assessment of temporal sequences is a difficult task, as motion artifacts in the longitudinal and axial plane can decrease the quality of the manual inspection. To address this challenge, the current study presents a two-stage computational framework for the longitudinal and axial registration of two OCT pullbacks. During the first stage of the process, we focus on the accurate detection of the matching image pairs from the respective series, while during the second stage we focus on the axial registration of the matched pairs so that their common features are aligned. The dataset used includes 19 patients from two clinical centers, with two OCT pullbacks per patient: one before the stent implantation procedure and one after it. We applied our method on a synthetic dataset of OCT pullbacks, which was generated based on the in-vivo OCT pullbacks to reproduce the motion artifacts across the planes. In addition, the proposed method was validated on the 19 pairs of in-vivo OCT pullbacks with annotated pre/post stent deployment data. The method was able to reduce the alignment error from 32. 17 ± 26. 14 to 5. 6 ± 6. 6 frames, the rotational error from 11. 59 ° ± 11. 22 ° to 1. 18 ° ± 0. 81 ° and the distance error from 3. 07 m m ± 1. 52 m m to 0. 46 m m ± 0. 44 m m. In addition, the mean Mutual Information similarity increased by 13.47% after the longitudinal registration and an additional 123.33% after the axial registration on top of the previous one. • Longitudinal and axial registration of OCT pullbacks. • DTW algorithm based on lumen contour's features for OCT longitudinal registration. • Modified Mutual Information based on a variant of Harmony Search optimizer. • Validation of the method 19 patients achieved state of the art performance. [ABSTRACT FROM AUTHOR]

As the field of brain monitoring is evolving rapidly, there is an increasing demand for innovative approaches to handle relevant signals. Recently, graph signal processing, which enables the treatment of signal ensembles, emerges as a powerful alternative to a per-signal analysis. This is especially the case for electroencephalogram (EEG) signals that naturally admit graph representations, with each electrode corresponding to one graph node. These signals are often corrupted by impulsive noise best characterized by heavy-tailed statistics, thus driving conventional denoising techniques to failure. To address this problem, we propose an efficient regularized graph filtering method based on fractional lower-order moments, which better adapt to heavy-tailed statistics. An experimental evaluation on real EEG measurements, including the publicly available P300 dataset and epilepsy signals, reveals a superior denoising performance of our method when compared against well-established EEG signal denoising methods. • Graph-based denoising of impulsive signals. • Symmetric alpha-stable theory applied on EEG signals. • Graph representation of EEG signals in impulsive environments. [ABSTRACT FROM AUTHOR]

• Investigation of the cross recurrence quantification analysis (CRQA). • Application on 16 brain regions which consist the visuomotor network. • Comparison with static functional connectivity (FC)-Pearson's correlation. • Comparison with temporal-based dFC alternative approach. • CRQA proved to be more efficient in separating NPSLE patients from HC volunteers. There is growing interest in dynamic approaches to functional brain connectivity (FC), and their potential applications in understanding atypical brain function. In this study, we assess the relative sensitivity of cross recurrence quantification analysis CRQA) to identify aberrant FC in patients with neuropsychiatric systemic lupus erythematosus (NPSLE) in comparison with conventional static and dynamic bivariate FC measures, as well as univariate (nodal) RQA. This technique was applied to resting-state fMRI data obtained from 45 NPSLE patients and 35 healthy volunteers (HC). Cross recurrence plots were computed for all pairs of 16 frontoparietal brain regions known to be critically involved in visuomotor control and suspected to show hemodynamic disturbance in NPSLE. Multivariate group comparisons revealed that the combination of six CRQA measures differentiated the two groups with large effect sizes (. 214 > η 2 >. 061) in 40 out of the 120 region pairs. The majority of brain regions forming these pairs also showed group differences on nodal RQA indices (. 146 > η 2 >. 09) Overall, larger values were found in NPSLE patients vs. HC with the exception of FC formed by the paracentral lobule. Determinism within five pairs of right-hemisphere sensorimotor regions (paracentral lobule, primary somatosensory, primary motor, and supplementary motor areas), correlated positively with visuomotor performance among NPSLE patients (p <. 001). By comparison, group differences on static FC displayed large effect sizes in only 4 of the 120 region pairs (. 126 > η 2 >. 061), none of which correlated significantly with visuomotor performance. Indices derived from dynamic, temporal-based FC analyses displayed large effect sizes in 11 / 120 region pairs (. 11 > η 2 >. 063). These findings further support the importance of feature-based dFC in advancing current knowledge on correlates of cognitive dysfunction in a clinically challenging disorder, such as NPSLE. [ABSTRACT FROM AUTHOR]

We present an image analysis method that can detect and measure breast density from digitised mammograms. We present initial results on applying our method to characterise breast changes, in particular, changes due to Hormone Replacement Therapy (HRT). It has been established that long-term use of certain hormone replacement therapies can increase the risk of breast cancer, a fact that encourages the notion that objective measures of tissue density can be an important development in breast cancer image analysis. A set of 59 temporal pairs of mammograms of patients undergoing HRT (two images per patient) were used. The clinician’s assessment of density changes constituted the ground truth for evaluating the proposed quantitative measures of density change. The measures we developed are based on the Standard Mammogram Form (SMF) representation of interesting tissue and their performance (agreement with the expert’s description) is also compared to the “interactive thresholding” method that has been used in the past to characterise mammographic density. The results clearly indicate that present methods for measuring mammographic density fail to characterise temporal changes while the proposed measures have the potential to aid the radiologist in assessing temporal density changes both on a global and a local basis. [Copyright &y& Elsevier]

Purpose T2 relaxation constant has been established as an accurate biomarker from the early days of MRI for tissue or material identification as it expresses physical properties without dependence on the MR protocol used. T2 * expresses acceleration of T2 dephasing process by local field inhomogeneities that can be produced by paramagnetic blood products, i.e. deoxyhemoglobin, hemosiderin. Therefore, long R2 ′  = 1/T2 *  − 1/T2 relaxation rates are found in tissues with low oxygenation and/or high oxygen consumption. The present is a study of T2 and R2 ′ for the differentiation between benign and malignant lipomatous tumors. Methods 16 patients with lipomatous tumors underwent preoperatively MRI examination including T2/T2 * relaxometry protocol. T2 relaxometry data were acquired from a Multi Echo Spin Echo CPMG sequence with initial echo at 26.8 ms followed by 9 equidistant echoes (echo spacing 26.8 ms) to avoid spin coupling signal modulation. T2 * protocol comprised 4 opposed-phased echoes (TE: 2.38/7.18/12.0/16.82 ms) and 4 in-phase echoes (4.77/9.59/14.41/19.23 ms). Histologic examination of surgical specimen showed 4 benign lipomas (bl), 4 well differentiated liposarcomas (wdl, Histologic Specific Differentiation Score (HSDS) 1), 2 non round cell myxoid liposarcomas (intermediately differentiated sarcomas, idl, HSDS 2) and 6 poorly differentiated liposarcomas (pdl, HSDS 3). 3D ROI based measurements were performed on areas indicated from histopathologic analysis as indicative of histologic subtype. Results Average T2 (SD) constant for bl/wdl/idl/pdl is 102.2 (1.6)/101.9 (6.7)/562.55 (120.1)/131.8 (12.1) ms. R2 ′ for bl/wdl/idl/pdl is 23.1 (1.1)/17.2 (9.3)/1.6 (0.5)/4.6 (1.0) ms −1 . Similar metrics were taken on healthy subcutaneous tissue to ensure protocol robustness on healthy tissue (Normal fat T2/R2 ′ range: 98.9–102.0 ms/24.2–25.9 ms −1 ). Conclusion Average T2 differs significantly between lipomatous masses of variable differentiation score in a limited sample of benign and malignant lipomatous tumors. R2 ′ is larger for lipomas and well differentiated liposarcomas compared to intermediate or poorly differentiated liposarcomas suggesting lower oxygen supply/consumption of the lesion. [ABSTRACT FROM AUTHOR]

Purpose Non-invasive characterization of lipomatous tumors can be challenging as several histological types have similar imaging characteristics. In this study we examine the use of a new biomarker based on spin coupling related signal loss between two acquisitions of different echo spacing to differentiate between benign lipomas, well, intermediate and poorly differentiated liposarcomas (l, wdl, idl and pdl, respectively). This study was based on previous work showing differences between vegetable oils of different botanical origin using the same protocol [1] . Methods Fourteen patients (9 male, 5 female, age: 37–87, mean 58) with soft tissue masses (5 lipomas, 2 myxoid, 5 dedifferentiated, 2 pleiomorphic liposarcomas) underwent MRI prior to any therapeutic intervention. MRI protocol, among other sequences, included two Multi Echo Spin Echo CPMG sequences with different echo spacing, 13.4 and 26.8 ms respectively, i.e. above and below the approximate threshold of 20 ms in order to have bright and dark fat appearance on T2-w images. All surgically excised specimen were histopathologically examined to determine the kind of lipomatous tumor and to localize sites of well or poor differentiation in the cases of dedifferentiated liposarcomas as distance from the upper tumor limit (z) and distance from the center (x,y). Relative signal loss between bright and dark fat images on TE 80 ms was calculated in order to measure the spin coupling Ratio (Rsc), defined as mean ROI value in the lesion divided by the same value in normal subcutaneous fat for the same patient. Results Mean (SD) of Rsc for l, wdl, idl and pdl was 1.036 (0.06), 0.77 (0.18), 0.055 (0.06) and −0.16 (0.57), respectively. Conclusions A new biomarker related on spin coupling signal loss is indicative of the differentiation grade of lipomatous tumors, with special interest regarding the clinically challenging question of benign lipomas vs. well differentiated liposarcomas. It is of note that Rsc decreases with increased differentiation grade (1–3). [ABSTRACT FROM AUTHOR]

Purpose Radiological evaluation of tumor aggressiveness is very frequently based on diffusion and/or perfusion imaging findings and conclusions are used to guide biopsy. The present work describes a post processing process that highlights areas of increased cellularity (low ADC) and also increased vascular transendothelial permeability (high K trans ), two of the most significant markers of malignancy, at the early stage of imaging. Preliminary results tested on 5 patients with soft tissue sarcomas are presented. Methods Quantitative ADC maps were generated from MR data by pixelwise mono-exponential fitting of multi-b (8b, 0–1500) DW images with custom-built tools written in Python. Similarly, K trans map was calculated based on the Extended Tofts Model from T1-w GRE data (temporal resolution 7 s, 45 time points). All pixel values assigned as tumor volume (3D ROI) were used as input for the initial whole tumor ADC and K trans histograms. As a next step, only pixels with values lower than the mean of ADC histogram and K trans values greater than the mean K trans were located and visualized in order to examine if a voxel cluster with adequate size is discriminated after thresholding. Patient population (5 male, mean age 60) comprised 3 dedifferentiated liposarcomas and 2 pleomorphic liposarcomas. Results Whole tumor pixel percentages with ADC value below the mean ADC value of the same ROI (used as histogram threshold) for the five high grade liposarcomas were: 58.7, 82.5, 52.1, 65.7, and 78.8%. Ktrans pixel percentages above the mean K trans (threshold) were: 11.8, 23.4, 4.3, 62.9, 39.9% respectively. The percentage of pixels meeting both criteria for low ADC and high K trans were: 4.2, 14.2, 0.6, 20.1, 15.3% respectively. Conclusion For 4 out of 5 patients visualization of a pixel cluster with adequate size that can be proposed as suitable site for preoperative needle biopsy was possible. Further appropriate ADC/ K trans thresholding can be used to increase disease conspicuity under certain criteria, depending on the special characteristics of each tumor subtype. [ABSTRACT FROM AUTHOR]

Over the past decade rapid advancements in molecular imaging (MI) and artificial intelligence (AI) have revolutionized traditional musculoskeletal radiology. Molecular imaging refers to the ability of various methods to in vivo characterize and quantify biological processes, at a molecular level. The extracted information provides the tools to understand the pathophysiology of diseases and thus to early detect, to accurately evaluate the extend and to apply and evaluate targeted treatments. At present, molecular imaging mainly involves CT, MRI, radionuclide, US, and optical imaging and has been reported in many clinical and preclinical studies. Although originally MI techniques targeted at central nervous system disorders, later on their value on musculoskeletal disorders was also studied in depth. Meaningful exploitation of the large volume of imaging data generated by molecular and conventional imaging techniques, requires state-of-the-art computational methods that enable rapid handling of large volumes of information. AI allows end-to-end training of computer algorithms to perform tasks encountered in everyday clinical practice including diagnosis, disease severity classification and image optimization. Notably, the development of deep learning algorithms has offered novel methods that enable intelligent processing of large imaging datasets in an attempt to automate decision-making in a wide variety of settings related to musculoskeletal trauma. Current applications of AI include the diagnosis of bone and soft tissue injuries, monitoring of the healing process and prediction of injuries in the professional sports setting. This review presents the current applications of novel MI techniques and methods and the emerging role of AI regarding the diagnosis and evaluation of musculoskeletal trauma. [ABSTRACT FROM AUTHOR]

Magnetic Resonance (MR) images suffer from spatial inhomogeneity, known as bias field corruption. The N4ITK filter is a state-of-the-art method used for correcting the bias field to optimize MR-based quantification. In this study, a novel approach is presented to quantitatively evaluate the performance of N4 bias field correction for pelvic prostate imaging. An exploratory analysis, regarding the different values of convergence threshold, shrink factor, fitting level, number of iterations and use of mask, is performed to quantify the performance of N4 filter in pelvic MR images. The performance of a total of 240 different N4 configurations is examined using the Full Width at Half Maximum (FWHM) of the segmented periprostatic fat distribution as evaluation metric. Phantom T2weighted images were used to assess the performance of N4 for a uniform test tissue mimicking material, excluding factors such as patient related susceptibility and anatomy heterogeneity. Moreover, 89 and 204 T2weighted patient images from two public datasets acquired by scanners with a combined surface and endorectal coil at 1.5 T and a surface coil at 3 T, respectively, were utilized and corrected with a variable set of N4 parameters. Furthermore, two external public datasets were used to validate the performance of the N4 filter in T2weighted patient images acquired by various scanning conditions with different magnetic field strengths and coils. The results show that the set of N4 parameters, converging to optimal representations of fat in the image, were: convergence threshold 0.001, shrink factor 2, fitting level 6, number of iterations 100 and the use of default mask for prostate images acquired by a combined surface and endorectal coil at both 1.5 T and 3 T. The corresponding optimal N4 configuration for MR prostate images acquired by a surface coil at 1.5 T or 3 T was: convergence threshold 0.001, shrink factor 2, fitting level 5, number of iterations 25 and the use of default mask. Hence, periprostatic fat segmentation can be used to define the optimal settings for achieving T2weighted prostate images free from bias field corruption to provide robust input for further analysis. [ABSTRACT FROM AUTHOR]

Purpose: Subchondral insufficiency fractures (SIF) and advanced osteoarthritis (OA) of the knee are usually seen in conjunction with bone marrow lesions (BMLs) and their differentiation may pose a significant diagnostic challenge. We aimed to develop a convolutional neural network (CNN) ensemble which could successfully differentiate between these two entities.Materials and Methods: A total of 212 knees with SIF and 102 knees with advanced OA with BMLs were retrospectively included. Coronal fat suppressed PD-w images were augmented, resized and normalized, reaching a total of 1174 images. Data was used to fine-tune three ImageNet-pretrained CNNs (VGG-16, InceptionV3 and Inception-ResNet-V2). Agreement of at least two networks was recorded as the decision of the network ensemble. Ensemble performance was compared to that of two MSK radiologists on the validation set. Receiver operating characteristics (ROC) curves and the respective areas under the curve (AUC) were used to evaluate human and machine performance.Results: InceptionV3 achieved the highest AUC (93.68%) and VGG-16 the lowest AUC (82.18%) among individual CNNs. CNN ensemble achieved the highest overall performance with an AUC of 95.97%. The first of the two MSK radiologists achieved a performance similar to the ensemble, reaching an AUC of 91.95%. The second radiologist achieved lower AUC of 82.76% which was lower than both the other specialist and the ensemble (P < 0.001).Conclusion: A CNN ensemble was highly accurate in differentiating between SIF and OA, achieving a higher or equal performance to MSK radiologists. [ABSTRACT FROM AUTHOR]

Gastro-entero-pancreatic neuroendocrine tumors (GEP-NETs) represent a heterogeneous group of rare neoplasms with increasing incidence over the last decades. Localization of GEP-NETs and their metastases is a vital component for the implementation of accurate and patient-tailored treatment strategies. Addressing this challenge requires the employment of multidisciplinary imaging approaches, with hybrid positron emission tomography/computed tomography (PET/CT) imaging techniques standing at the forefront of this effort. GEP-NETs exhibit several pathophysiologic characteristics, which can serve as highly specific molecular targets that can be effectively visualized and quantified by means of PET-radiopharmaceuticals, facilitating diagnosis, accurate staging and efficient monitoring of treatment response. Furthermore, the capability for whole-body, in-vivo, non-invasive characterization of the molecular heterogeneity of the disease, provides strong prognostic information, while enabling the selection of patients suitable for precision-based theranostic approaches. The dual tracer (18F-FDG & 68Ga-DOTA-peptides) PET/CT imaging approach is the current optimal diagnostic imaging strategy, since it enables tumor localization, accurate staging, non-invasive whole-body total tumor burden characterization of disease heterogeneity, while providing strong prognostic information and guidance towards treatment strategy. Moreover, 64Cu-DOTATATE has been recently approved by FDA for SSTRs positive NETs, promising substantial diagnostic and logistical benefits. Furthermore, 18F-DOPA offers diagnostic capabilities for serotonin-secreting GEP-NETs which are not characterized by cell-surface over-expression of somatostatin receptors (SSTRs) and cannot be seen on morphological imaging. In addition, PET/CT with agents targeting the expression of glucagon-like peptide-1 receptor (GLP-R1) should be considered in cases of clinical suspicion for insulinomas that cannot be detected by morphological imaging or STTRs PET/CT imaging. [ABSTRACT FROM AUTHOR]

Abstract Accumulating evidence during the last decades revealed that androgens exert membrane-initiated actions leading to the modulation of significant cellular processes, important for cancer cell growth and metastasis (including prostate and breast), that involve signaling via specific kinases. Collectively, many nonclassical, cell surface-initiated androgen actions are mediated by novel membrane androgen receptors (mARs), unrelated to nuclear androgen receptors. Recently, our group identified the G protein coupled oxo-eicosanoid receptor 1 (OXER1) (a receptor of the arachidonic acid metabolite, 5-oxoeicosatetraenoic acid, 5-oxoETE) as a novel mAR involved in the rapid effects of androgens. However, two other membrane proteins, G protein-coupled receptor family C group 6 member A (GPRC6A) and zinc transporter member 9 (ZIP9) have also been portrayed as mARs, related to the extranuclear action of androgens. In the present work, we present a comparative study of in silico pharmacology, gene expression and immunocytochemical data of the three receptors in various prostate and breast cancer cell lines. Furthermore, we analyzed the immunohistochemical expression of these receptors in human tumor and non-tumoral specimens and provide a pattern of expression and intracellular distribution. [ABSTRACT FROM AUTHOR]

Purpose: Biomedical research is being catalyzed by the vast amount of data rapidly collected through the application of information technologies (IT). Despite IT advances, the methods for involving patients and citizens in biomedical research remain static, paper-based and organized around national boundaries and anachronistic legal frameworks. The purpose of this paper is to study the current practices for obtaining consent for biobanking and the legal requirements for reusing the available biomaterial and data in EU and finally to present a novel tool to this direction enabling the secondary use of data and biomaterial.Method: We review existing European legislation for secondary use of patient's biomaterial and data for research, identify types and scopes of consent, formal requirements for consent, and consider their implications for implementing electronic consent tools. To this direction, we proceed further to develop a modular tool, named Donor's Support Tool (DST), designed to connect researchers with participants, and to promote engagement, informed participation and individual decision making.Results: To identify the advantages of our solution we compare our tool with six other relevant approaches. The results show that our tool scores higher than the other tools in functionality, security and intelligence whereas it is the only one free and open-source. In addition, the potential of our solution is shown by a proof of concept deployment in an existing clinical setting, where it was really appreciated, as streamlining the relevant workflow. [ABSTRACT FROM AUTHOR]

Aim: We present a computerized system for the assessment of the long-term risk of developing diabetesrelated complications. Methods: The core of the system consists of a set of predictive models, developed through a data-mining/machine-learning approach, which are able to evaluate individual patient profiles and provide personalized risk assessments. Missing data is a common issue in (electronic) patient records, thus themodels are paired with a module for the intelligent management of missing information. Results: The system has been deployed and made publicly available as Web service, and it has been fully integrated within the diabetes-management platform developed by the European project REACTION. Preliminary usability tests showed that the clinicians judged the models useful for risk assessment and for communicating the risk to the patient. Furthermore, the system performs as well as the United Kingdom Prospective Diabetes Study (UKPDS) Risk Engine when both systems are tested on an independent cohort of UK diabetes patients. Conclusions: Our work provides a working example of risk-stratification tool that is (a) specific for diabetes patients, (b) able to handle several different diabetes related complications, (c) performing as well as the widely known UKPDS Risk Engine on an external validation cohort. [ABSTRACT FROM AUTHOR]

Personal health record (PHR) systems are a rapidly expanding area in the field of health information technology which motivates an ongoing research towards their evaluation in several different aspects. In this direction, we present a systematic review of the currently available PHR systems. Initially, we define a clear and concise set of requirements for efficient PHR systems which is based on real-world implementation experiences of several European research projects and also on established and widely used formal standards. Subsequently, these requirements are used to perform a systematic evaluation of existing PHR system implementations. Our evaluation study provides a thorough requirement analysis and an insight on the current status of personal health record systems. The results of the present work can therefore be used as a basis for future evaluation studies which should be conducted periodically as technology evolves and requirements are revised. [ABSTRACT FROM AUTHOR]

Purpose: To investigate and histopathologically validate the role of model selection in the design of novel parametric meta-maps towards the discrimination of low from high-grade soft tissue sarcomas (STSs) using multiple Diffusion Weighted Imaging (DWI) models.Methods: DWI data of 28 patients were quantified using the mono-exponential, bi-exponential, stretched-exponential and the diffusion kurtosis model. Akaike Weights (AW) were calculated from the corrected Akaike Information Criteria (AICc) to select the most suitable model for every pixel within the tumor volume. Pseudo-colorized classification maps were then generated to depict model suitability, hypothesizing that every single model underpins different tissue properties and cannot solely characterize the whole tumor. Single model parametric maps were turned into meta-maps using the classification map and a histological validation of the model suitability results was conducted on several subregions of different tumors. Several histogram metrics were calculated from all derived maps before and after model selection, statistical analysis was conducted using the Mann-Whitney U test, p-values were adjusted for multiple comparisons and performance of all statistically significant metrics was evaluated using the Receiver Operator Characteristic (ROC) analysis.Results: The histologic analysis on several tumor subregions confirmed model suitability results on these areas. Only 3 histogram metrics, all derived from the meta-maps, were found to be statistically significant in differentiating low from high-grade STSs with an AUC higher than 89 %.Conclusion: Embedding model selection in the design of the diffusion parametric maps yields to histogram metrics of high discriminatory power in grading STSs. [ABSTRACT FROM AUTHOR]