Laboratoire de Traitement de l'Information Médicale

Monte Carlo simulation is an essential tool in emission tomography that can assist in the design of new medical imaging devices, the optimization of acquisition protocols and the development or assessment of image reconstruction algorithms and correction techniques. GATE, the Geant4 Application for Tomographic Emission, encapsulates the Geant4 libraries to achieve a modular, versatile, scripted simulation toolkit adapted to the field of nuclear medicine. In particular, GATE allows the description of time-dependent phenomena such as source or detector movement, and source decay kinetics. This feature makes it possible to simulate time curves under realistic acquisition conditions and to test dynamic reconstruction algorithms. This paper gives a detailed description of the design and development of GATE by the OpenGATE collaboration, whose continuing objective is to improve, document and validate GATE by simulating commercially available imaging systems for PET and SPECT. Large effort is also invested in the ability and the flexibility to model novel detection systems or systems still under design. A public release of GATE licensed under the GNU Lesser General Public License can be downloaded at http:/www-lphe.epfl.ch/GATE/. Two benchmarks developed for PET and SPECT to test the installation of GATE and to serve as a tutorial for the users are presented. Extensive validation of the GATE simulation platform has been started, comparing simulations and measurements on commercially available acquisition systems. References to those results are listed. The future prospects towards the gridification of GATE and its extension to other domains such as dosimetry are also discussed.

The Messidor database, which contains hundreds of eye fundus images, has been publicly distributed since 2008. It was created by the Messidor project in order to evaluate automatic lesion segmentation and diabetic retinopathy grading methods. Designing, producing and maintaining such a database entails significant costs. By publicly sharing it, one hopes to bring a valuable resource to the public research community. However, the real interest and benefit of the research community is not easy to quantify. We analyse here the feedback on the Messidor database, after more than 6 years of diffusion. This analysis should apply to other similar research databases.

GATE (Geant4 Application for Emission Tomography) is a Monte Carlo simulation platform developed by the OpenGATE collaboration since 2001 and first publicly released in 2004. Dedicated to the modelling of planar scintigraphy, single photon emission computed tomography (SPECT) and positron emission tomography (PET) acquisitions, this platform is widely used to assist PET and SPECT research. A recent extension of this platform, released by the OpenGATE collaboration as GATE V6, now also enables modelling of x-ray computed tomography and radiation therapy experiments. This paper presents an overview of the main additions and improvements implemented in GATE since the publication of the initial GATE paper (Jan et al 2004 Phys. Med. Biol. 49 4543-61). This includes new models available in GATE to simulate optical and hadronic processes, novelties in modelling tracer, organ or detector motion, new options for speeding up GATE simulations, examples illustrating the use of GATE V6 in radiotherapy applications and CT simulations, and preliminary results regarding the validation of GATE V6 for radiation therapy applications. Upon completion of extensive validation studies, GATE is expected to become a valuable tool for simulations involving both radiotherapy and imaging.

UNLABELLED: (18)F-FDG PET is often used in clinical routine for diagnosis, staging, and response to therapy assessment or prediction. The standardized uptake value (SUV) in the primary or regional area is the most common quantitative measurement derived from PET images used for those purposes. The aim of this study was to propose and evaluate new parameters obtained by textural analysis of baseline PET scans for the prediction of therapy response in esophageal cancer. METHODS: Forty-one patients with newly diagnosed esophageal cancer treated with combined radiochemotherapy were included in this study. All patients underwent pretreatment whole-body (18)F-FDG PET. Patients were treated with radiotherapy and alkylatinlike agents (5-fluorouracil-cisplatin or 5-fluorouracil-carboplatin). Patients were classified as nonresponders (progressive or stable disease), partial responders, or complete responders according to the Response Evaluation Criteria in Solid Tumors. Different image-derived indices obtained from the pretreatment PET tumor images were considered. These included usual indices such as maximum SUV, peak SUV, and mean SUV and a total of 38 features (such as entropy, size, and magnitude of local and global heterogeneous and homogeneous tumor regions) extracted from the 5 different textures considered. The capacity of each parameter to classify patients with respect to response to therapy was assessed using the Kruskal-Wallis test (P < 0.05). Specificity and sensitivity (including 95% confidence intervals) for each of the studied parameters were derived using receiver-operating-characteristic curves. RESULTS: Relationships between pairs of voxels, characterizing local tumor metabolic nonuniformities, were able to significantly differentiate all 3 patient groups (P < 0.0006). Regional measures of tumor characteristics, such as size of nonuniform metabolic regions and corresponding intensity nonuniformities within these regions, were also significant factors for prediction of response to therapy (P = 0.0002). Receiver-operating-characteristic curve analysis showed that tumor textural analysis can provide nonresponder, partial-responder, and complete-responder patient identification with higher sensitivity (76%-92%) than any SUV measurement. CONCLUSION: Textural features of tumor metabolic distribution extracted from baseline (18)F-FDG PET images allow for the best stratification of esophageal carcinoma patients in the context of therapy-response prediction.

BACKGROUND: Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining. OBJECTIVE: The primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice. METHODS: This systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed. RESULTS: A total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform. CONCLUSIONS: Machine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients' daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.

In this paper, the authors' review the applicability of the open-source GATE Monte Carlo simulation platform based on the GEANT4 toolkit for radiation therapy and dosimetry applications. The many applications of GATE for state-of-the-art radiotherapy simulations are described including external beam radiotherapy, brachytherapy, intraoperative radiotherapy, hadrontherapy, molecular radiotherapy, and in vivo dose monitoring. Investigations that have been performed using GEANT4 only are also mentioned to illustrate the potential of GATE. The very practical feature of GATE making it easy to model both a treatment and an imaging acquisition within the same framework is emphasized. The computational times associated with several applications are provided to illustrate the practical feasibility of the simulations using current computing facilities.

The detection of microaneurysms in digital color fundus photographs is a critical first step in automated screening for diabetic retinopathy (DR), a common complication of diabetes. To accomplish this detection numerous methods have been published in the past but none of these was compared with each other on the same data. In this work we present the results of the first international microaneurysm detection competition, organized in the context of the Retinopathy Online Challenge (ROC), a multiyear online competition for various aspects of DR detection. For this competition, we compare the results of five different methods, produced by five different teams of researchers on the same set of data. The evaluation was performed in a uniform manner using an algorithm presented in this work. The set of data used for the competition consisted of 50 training images with available reference standard and 50 test images where the reference standard was withheld by the organizers (M. Niemeijer, B. van Ginneken, and M. D. Abràmoff). The results obtained on the test data was submitted through a website after which standardized evaluation software was used to determine the performance of each of the methods. A human expert detected microaneurysms in the test set to allow comparison with the performance of the automatic methods. The overall results show that microaneurysm detection is a challenging task for both the automatic methods as well as the human expert. There is room for improvement as the best performing system does not reach the performance of the human expert. The data associated with the ROC microaneurysm detection competition will remain publicly available and the website will continue accepting submissions.

UNLABELLED: Intratumoral uptake heterogeneity in (18)F-FDG PET has been associated with patient treatment outcomes in several cancer types. Textural feature analysis is a promising method for its quantification. An open issue associated with textural features for the quantification of intratumoral heterogeneity concerns its added contribution and dependence on the metabolically active tumor volume (MATV), which has already been shown to be a significant predictive and prognostic parameter. Our objective was to address this question using a larger cohort of patients covering different cancer types. METHODS: A single database of 555 pretreatment (18)F-FDG PET images (breast, cervix, esophageal, head and neck, and lung cancer tumors) was assembled. Four robust and reproducible textural feature-derived parameters were considered. The issues associated with the calculation of textural features using co-occurrence matrices (such as the quantization and spatial directionality relationships) were also investigated. The relationship between these features and MATV, as well as among the features themselves, was investigated using Spearman rank coefficients for different volume ranges. The complementary prognostic value of MATV and textural features was assessed through multivariate Cox analysis in the esophageal and non-small cell lung cancer (NSCLC) cohorts. RESULTS: A large range of MATVs was included in the population considered (3-415 cm(3); mean, 35; median, 19; SD, 50). The correlation between MATV and textural features varied greatly depending on the MATVs, with reduced correlation for increasing volumes. These findings were reproducible across the different cancer types. The quantization and calculation methods both had an impact on the correlation. Volume and heterogeneity were independent prognostic factors (P = 0.0053 and 0.0093, respectively) along with stage (P = 0.002) in non-small cell lung cancer, but in the esophageal tumors, volume and heterogeneity had less complementary value because of smaller overall volumes. CONCLUSION: Our results suggest that heterogeneity quantification and volume may provide valuable complementary information for volumes above 10 cm(3), although the complementary information increases substantially with larger volumes.

BACKGROUND: Whether the antiinflammatory and immunomodulatory effects of glucocorticoids may decrease mortality among patients with severe community-acquired pneumonia is unclear. METHODS: In this phase 3, multicenter, double-blind, randomized, controlled trial, we assigned adults who had been admitted to the intensive care unit (ICU) for severe community-acquired pneumonia to receive intravenous hydrocortisone (200 mg daily for either 4 or 7 days as determined by clinical improvement, followed by tapering for a total of 8 or 14 days) or to receive placebo. All the patients received standard therapy, including antibiotics and supportive care. The primary outcome was death at 28 days. RESULTS: A total of 800 patients had undergone randomization when the trial was stopped after the second planned interim analysis. Data from 795 patients were analyzed. By day 28, death had occurred in 25 of 400 patients (6.2%; 95% confidence interval [CI], 3.9 to 8.6) in the hydrocortisone group and in 47 of 395 patients (11.9%; 95% CI, 8.7 to 15.1) in the placebo group (absolute difference, -5.6 percentage points; 95% CI, -9.6 to -1.7; P = 0.006). Among the patients who were not undergoing mechanical ventilation at baseline, endotracheal intubation was performed in 40 of 222 (18.0%) in the hydrocortisone group and in 65 of 220 (29.5%) in the placebo group (hazard ratio, 0.59; 95% CI, 0.40 to 0.86). Among the patients who were not receiving vasopressors at baseline, such therapy was initiated by day 28 in 55 of 359 (15.3%) of the hydrocortisone group and in 86 of 344 (25.0%) in the placebo group (hazard ratio, 0.59; 95% CI, 0.43 to 0.82). The frequencies of hospital-acquired infections and gastrointestinal bleeding were similar in the two groups; patients in the hydrocortisone group received higher daily doses of insulin during the first week of treatment. CONCLUSIONS: Among patients with severe community-acquired pneumonia being treated in the ICU, those who received hydrocortisone had a lower risk of death by day 28 than those who received placebo. (Funded by the French Ministry of Health; CAPE COD ClinicalTrials.gov number, NCT02517489.).

Accurate volume estimation in positron emission tomography (PET) is crucial for different oncology applications. The objective of our study was to develop a new fuzzy locally adaptive Bayesian (FLAB) segmentation for automatic lesion volume delineation. FLAB was compared with a threshold approach as well as the previously proposed fuzzy hidden Markov chains (FHMC) and the fuzzy C-Means (FCM) algorithms. The performance of the algorithms was assessed on acquired datasets of the IEC phantom, covering a range of spherical lesion sizes (10-37 mm), contrast ratios (4:1 and 8:1), noise levels (1, 2, and 5 min acquisitions), and voxel sizes (8 and 64 mm(3)). In addition, the performance of the FLAB model was assessed on realistic nonuniform and nonspherical volumes simulated from patient lesions. Results show that FLAB performs better than the other methodologies, particularly for smaller objects. The volume error was 5%-15% for the different sphere sizes (down to 13 mm), contrast and image qualities considered, with a high reproducibility (variation < 4%). By comparison, the thresholding results were greatly dependent on image contrast and noise, whereas FCM results were less dependent on noise but consistently failed to segment lesions < 2 cm. In addition, FLAB performed consistently better for lesions < 2 cm in comparison to the FHMC algorithm. Finally the FLAB model provided errors less than 10% for nonspherical lesions with inhomogeneous activity distributions. Future developments will concentrate on an extension of FLAB in order to allow the segmentation of separate activity distribution regions within the same functional volume as well as a robustness study with respect to different scanners and reconstruction algorithms.

UNLABELLED: (18)F-FDG PET measurement of standardized uptake value (SUV) is increasingly used for monitoring therapy response and predicting outcome. Alternative parameters computed through textural analysis were recently proposed to quantify the heterogeneity of tracer uptake by tumors as a significant predictor of response. The primary objective of this study was to evaluate the reproducibility of these heterogeneity measurements. METHODS: Double baseline (18)F-FDG PET scans were acquired within 4 d of each other for 16 patients before any treatment was considered. A Bland-Altman analysis was performed on 8 parameters based on histogram measurements and 17 parameters based on textural heterogeneity features after discretization with values between 8 and 128. RESULTS: The reproducibility of maximum and mean SUV was similar to that in previously reported studies, with a mean percentage difference of 4.7% ± 19.5% and 5.5% ± 21.2%, respectively. By comparison, better reproducibility was measured for some textural features describing local heterogeneity of tracer uptake, such as entropy and homogeneity, with a mean percentage difference of -2% ± 5.4% and 1.8% ± 11.5%, respectively. Several regional heterogeneity parameters such as variability in the intensity and size of regions of homogeneous activity distribution had reproducibility similar to that of SUV measurements, with 95% confidence intervals of -22.5% to 3.1% and -1.1% to 23.5%, respectively. These parameters were largely insensitive to the discretization range. CONCLUSION: Several parameters derived from textural analysis describing heterogeneity of tracer uptake by tumors on local and regional scales had reproducibility similar to or better than that of simple SUV measurements. These reproducibility results suggest that these (18)F-FDG PET-derived parameters, which have already been shown to have predictive and prognostic value in certain cancer models, may be used to monitor therapy response and predict patient outcome.

Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of the corrupted samples, the corruption of the training set must be as stealthy as possible. Previous works have focused on the stealthiness of the perturbation injected into the training samples, however they all assume that the labels of the corrupted samples are also poisoned. This greatly reduces the stealthiness of the attack, since samples whose content does not agree with the label can be identified by visual inspection of the training set or by running a pre-classification step. In this paper we present a new backdoor attack without label poisoning Since the attack works by corrupting only samples of the target class, it has the additional advantage that it does not need to identify beforehand the class of the samples to be attacked at test time. Results obtained on the MNIST digits recognition task and the traffic signs classification task show that backdoor attacks without label poisoning are indeed possible, thus raising a new alarm regarding the use of deep learning in security-critical applications.

Abstract Since the seventies, positron emission tomography (PET) has become an invaluable medical molecular imaging modality with an unprecedented sensitivity at the picomolar level, especially for cancer diagnosis and the monitoring of its response to therapy. More recently, its combination with x-ray computed tomography (CT) or magnetic resonance (MR) has added high precision anatomic information in fused PET/CT and PET/MR images, thus compensating for the modest intrinsic spatial resolution of PET. Nevertheless, a number of medical challenges call for further improvements in PET sensitivity. These concern in particular new treatment opportunities in the context personalized (also called precision) medicine, such as the need to dynamically track a small number of cells in cancer immunotherapy or stem cells for tissue repair procedures. A better signal-to-noise ratio (SNR) in the image would allow detecting smaller size tumours together with a better staging of the patients, thus increasing the chances of putting cancer in complete remission. Moreover, there is an increasing demand for reducing the radioactive doses injected to the patients without impairing image quality. There are three ways to improve PET scanner sensitivity: improving detector efficiency, increasing geometrical acceptance of the imaging device and pushing the timing performance of the detectors. Currently, some pre-localization of the electron-positron annihilation along a line-of-response (LOR) given by the detection of a pair of annihilation photons is provided by the detection of the time difference between the two photons, also known as the time-of-flight (TOF) difference of the photons, whose accuracy is given by the coincidence time resolution (CTR). A CTR of about 10 picoseconds FWHM will ultimately allow to obtain a direct 3D volume representation of the activity distribution of a positron emitting radiopharmaceutical, at the millimetre level, thus introducing a quantum leap in PET imaging and quantification and fostering more frequent use of 11 C radiopharmaceuticals. The present roadmap article toward the advent of 10 ps TOF-PET addresses the status and current/future challenges along the development of TOF-PET with the objective to reach this mythic 10 ps frontier that will open the door to real-time volume imaging virtually without tomographic inversion. The medical impact and prospects to achieve this technological revolution from the detection and image reconstruction point-of-views, together with a few perspectives beyond the TOF-PET application are discussed.

PURPOSE: To analyze the clinical outcomes after implantation of an extended range of vision intraocular lens (IOL), the Tecnis Symfony, in a routine clinical setting. SETTING: Forty clinical sites in Finland, France, Germany, Norway, Spain, Sweden, and the United Kingdom. DESIGN: Prospective case series. METHODS: The study comprised 411 patients who had bilateral implantation of the extended range of vision IOL, with intended micro-monovision in 1 group (monovision group) and intended emmetropia in the other group (non-monovision group). Visual acuity, spectacle independence, patient and surgeon satisfaction, and photic phenomena were analyzed during the 4- to 6-month follow-up. RESULTS: The monovision group comprised 112 patients and the non-monovision group, 299 patients. The mean decimal uncorrected distance (UDVA), intermediate (UIVA), and near (UNVA) visual acuities were 0.95, 0.81, and 0.69, respectively, 4 to 6 months postoperatively. Significantly better UIVA (P = .003) and UNVA (P = .011) were found in the monovision group than in the non-monovision group. Spectacle independence was high, with 14.4% of eyes requiring reading spectacles frequently. More than 90% of patients reported no or mild halos, glare, starbursts, or other photic phenomena. Patient satisfaction scores (median) for distance, intermediate, and near vision were 9.0, 10.0, and 8.0, respectively. The satisfaction score for near vision increased to 9.0 in the monovision group. More than 91% of patients said they would recommend the same procedure to their friends and family. CONCLUSION: The extended range of vision IOL provided successful visual restoration across all distances after cataract surgery, with a minimal level of disturbing photic phenomena and high levels of patient satisfaction. FINANCIAL DISCLOSURE: Dr. Cochener is a clinical investigator for Revision Optics, Inc., Horus Vision LLC, Alcon Laboratories, Inc., Abbott Medical Optics, Inc., Théa Pharma GmbH, and Santen, Inc.; she is also a consultant to Alcon Laboratories, Inc., Abbott Medical Optics, Inc., Théa Pharma GmbH, and Santen, Inc.

Respiratory motion in emission tomography leads to reduced image quality. Developed correction methodology has been concentrating on the use of respiratory synchronized acquisitions leading to gated frames. Such frames, however, are of low signal-to-noise ratio as a result of containing reduced statistics. In this work, we describe the implementation of an elastic transformation within a list-mode-based reconstruction for the correction of respiratory motion over the thorax, allowing the use of all data available throughout a respiratory motion average acquisition. The developed algorithm was evaluated using datasets of the NCAT phantom generated at different points throughout the respiratory cycle. List-mode-data-based PET-simulated frames were subsequently produced by combining the NCAT datasets with Monte Carlo simulation. A non-rigid registration algorithm based on B-spline basis functions was employed to derive transformation parameters accounting for the respiratory motion using the NCAT dynamic CT images. The displacement matrices derived were subsequently applied during the image reconstruction of the original emission list mode data. Two different implementations for the incorporation of the elastic transformations within the one-pass list mode EM (OPL-EM) algorithm were developed and evaluated. The corrected images were compared with those produced using an affine transformation of list mode data prior to reconstruction, as well as with uncorrected respiratory motion average images. Results demonstrate that although both correction techniques considered lead to significant improvements in accounting for respiratory motion artefacts in the lung fields, the elastic-transformation-based correction leads to a more uniform improvement across the lungs for different lesion sizes and locations.

UNLABELLED: Posttreatment surveillance for the recurrence of head and neck squamous cell carcinoma (HNSCC) is a diagnostic challenge. Tissue distortion from radiation and surgery can obscure early detection of recurrence by conventional follow-up approaches such as physical examination, CT, and MRI. Several studies have shown that 18F-FDG PET may be an effective technique for the detection of persistent, recurrent, and distant metastatic HNSCC after treatment. The aim of this prospective study was to determine the benefits of hybrid 18F-FDG PET/CT in detecting a subclinical locoregional recurrence of HNSCC and distant metastases. The study patients were considered cured of HNSCC on the basis of 12 mo of negative findings on conventional follow-up. We also assessed the diagnostic accuracy of 18F-FDG PET/CT in these patients. METHODS: Ninety-one patients cured of HNSCC without any clinical evidence of recurrence were included. Whole-body 18F-FDG PET/CT examination was performed 11.6+/-4.4 mo after the end of the treatment. The gold standard was histopathology or 6 mo of imaging follow-up. RESULTS: The whole-body 18F-FDG PET/CT examinations had negative results in 52 patients and positive results in 39. Nine of these patients who exhibited abnormal 18F-FDG uptake in the head and neck area did not have recurrent HNSCC (false-positive). Thirty had proven recurrence. The sensitivity and specificity of 18F-FDG PET/CT in this study for the diagnosis of HNSCC recurrence were 100% (30/30) and 85% (52/61), respectively. The positive predictive value was 77% (30/39). The negative predictive value was 100% (52/52). The overall accuracy was 90% (82/91). CONCLUSION: The results of our study confirm the high effectiveness of 18F-FDG PET/CT in the assessment of HNSCC recurrence and suggest that 18F-FDG PET/CT is more accurate than conventional follow-up physical examination alone in the assessment of recurrence after previous curative treatment for HNSCC and could be proposed systematically at 12 mo of the usual follow-up.

Multiple-instance learning (MIL) is a recent machine-learning paradigm that is particularly well suited to medical image and video analysis (MIVA) tasks. Based solely on class labels assigned globally to images or videos, MIL algorithms learn to detect relevant patterns locally in images or videos. These patterns are then used for classification at a global level. Because supervision relies on global labels, manual segmentations are not needed to train MIL algorithms, unlike traditional single-instance learning (SIL) algorithms. Consequently, these solutions are attracting increasing interest from the MIVA community: since the term was coined by Dietterich et al. in 1997, 73 research papers about MIL have been published in the MIVA literature. This paper reviews the existing strategies for modeling MIVA tasks as MIL problems, recommends general-purpose MIL algorithms for each type of MIVA tasks, and discusses MIVA-specific MIL algorithms. Various experiments performed in medical image and video datasets are compiled in order to back up these discussions. This meta-analysis shows that, besides being more convenient than SIL solutions, MIL algorithms are also more accurate in many cases. In other words, MIL is the ideal solution for many MIVA tasks. Recent trends are discussed, and future directions are proposed for this emerging paradigm.

BACKGROUND: Suicide is a major public health problem and a cause of premature mortality. With a view to prevention, a great deal of research has been devoted to the determinants of suicide, focusing mostly on individual risk factors, particularly depression. In addition to causes intrinsic to the individual, the social environment has also been widely studied, particularly social isolation. This paper examines the social dimension of suicide etiology through a review of the literature on the relationship between suicide and social isolation. METHODS: Medline searches via PubMed and PsycINFO were conducted. The keywords were "suicid*" AND "isolation." RESULTS: Of the 2,684 articles initially retrieved, 46 were included in the review. CONCLUSIONS: Supported by proven theoretical foundations, mainly those developed by E. Durkheim and T. Joiner, a large majority of the articles included endorse the idea of a causal relationship between social isolation and suicide, and conversely, a protective effect of social support against suicide. Moreover, the association between suicide and social isolation is subject to variations related to age, gender, psychopathology, and specific circumstances. The social etiology of suicide has implications for intervention and future research.

Example-based single image super-resolution (SR) has recently shown outcomes with high reconstruction performance. Several methods based on neural networks have successfully introduced techniques into SR problem. In this paper, we propose a three-dimensional (3D) convolutional neural network to generate high-resolution (HR) brain image from its input low-resolution (LR) with the help of patches of other HR brain images. Our work demonstrates the need of fitting data and network parameters for 3D brain MRI.

In this paper, we propose a new reversible watermarking scheme. One first contribution is a histogram shifting modulation which adaptively takes care of the local specificities of the image content. By applying it to the image prediction-errors and by considering their immediate neighborhood, the scheme we propose inserts data in textured areas where other methods fail to do so. Furthermore, our scheme makes use of a classification process for identifying parts of the image that can be watermarked with the most suited reversible modulation. This classification is based on a reference image derived from the image itself, a prediction of it, which has the property of being invariant to the watermark insertion. In that way, the watermark embedder and extractor remain synchronized for message extraction and image reconstruction. The experiments conducted so far, on some natural images and on medical images from different modalities, show that for capacities smaller than 0.4 bpp, our method can insert more data with lower distortion than any existing schemes. For the same capacity, we achieve a peak signal-to-noise ratio (PSNR) of about 1-2 dB greater than with the scheme of Hwang , the most efficient approach actually.