Search

While the field of medical image analysis has undergone a transformative shift with the integration of machine learning techniques, the main challenge of these techniques is often the scarcity of large, diverse, and well-annotated datasets. Medical images vary in format, size, and other parameters and therefore require extensive preprocessing and standardization, for usage in machine learning. Addressing these challenges, we introduce the Medical Imaging Meta-Dataset (MedIMeta), a novel multi-domain, multi-task meta-dataset. MedIMeta contains 19 medical imaging datasets spanning 10 different domains and encompassing 54 distinct medical tasks, all of which are standardized to the same format and readily usable in PyTorch or other ML frameworks. We perform a technical validation of MedIMeta, demonstrating its utility through fully supervised and cross-domain few-shot learning baselines.

Magnetic Resonance Imaging (MRI) offers strong soft tissue contrast but suffers from long acquisition times and requires tedious annotation from radiologists. Traditionally, these challenges have been addressed separately with reconstruction and image analysis algorithms. To see if performance could be improved by treating both as end-to-end, we hosted the K2S challenge, in which challenge participants segmented knee bones and cartilage from 8× undersampled k-space. We curated the 300-patient K2S dataset of multicoil raw k-space and radiologist quality-checked segmentations. 87 teams registered for the challenge and there were 12 submissions, varying in methodologies from serial reconstruction and segmentation to end-to-end networks to another that eschewed a reconstruction algorithm altogether. Four teams produced strong submissions, with the winner having a weighted Dice Similarity Coefficient of 0.910 ± 0.021 across knee bones and cartilage. Interestingly, there was no correlation between reconstruction and segmentation metrics. Further analysis showed the top four submissions were suitable for downstream biomarker analysis, largely preserving cartilage thicknesses and key bone shape features with respect to ground truth. K2S thus showed the value in considering reconstruction and image analysis as end-to-end tasks, as this leaves room for optimization while more realistically reflecting the long-term use case of tools being developed by the MR community.

Distribution shifts remain a fundamental problem for the safe application of machine learning systems. If undetected, they may impact the real-world performance of such systems or will at least render original performance claims invalid. In this paper, we focus on the detection of subgroup shifts, a type of distribution shift that can occur when subgroups have a different prevalence during validation compared to the deployment setting. For example, algorithms developed on data from various acquisition settings may be predominantly applied in hospitals with lower quality data acquisition, leading to an inadvertent performance drop. We formulate subgroup shift detection in the framework of statistical hypothesis testing and show that recent state-of-the-art statistical tests can be effectively applied to subgroup shift detection on medical imaging data. We provide synthetic experiments as well as extensive evaluation on clinically meaningful subgroup shifts on histopathology as well as retinal fundus images. We conclude that classifier-based subgroup shift detection tests could be a particularly useful tool for post-market surveillance of deployed ML systems., Comment: Under review

Interpretability is essential for machine learning algorithms in high-stakes application fields such as medical image analysis. However, high-performing black-box neural networks do not provide explanations for their predictions, which can lead to mistrust and suboptimal human-ML collaboration. Post-hoc explanation techniques, which are widely used in practice, have been shown to suffer from severe conceptual problems. Furthermore, as we show in this paper, current explanation techniques do not perform adequately in the multi-label scenario, in which multiple medical findings may co-occur in a single image. We propose Attri-Net, an inherently interpretable model for multi-label classification. Attri-Net is a powerful classifier that provides transparent, trustworthy, and human-understandable explanations. The model first generates class-specific attribution maps based on counterfactuals to identify which image regions correspond to certain medical findings. Then a simple logistic regression classifier is used to make predictions based solely on these attribution maps. We compare Attri-Net to five post-hoc explanation techniques and one inherently interpretable classifier on three chest X-ray datasets. We find that Attri-Net produces high-quality multi-label explanations consistent with clinical knowledge and has comparable classification performance to state-of-the-art classification models., Comment: Accepted to MIDL 2023

Understanding the interactions of different cell types inside the immune tumor microenvironment (iTME) is crucial for the development of immunotherapy treatments as well as for predicting their outcomes. Highly multiplexed tissue imaging (HMTI) technologies offer a tool which can capture cell properties of tissue samples by measuring expression of various proteins and storing them in separate image channels. HMTI technologies can be used to gain insights into the iTME and in particular how the iTME differs for different patient outcome groups of interest (e.g., treatment responders vs. non-responders). Understanding the systematic differences in the iTME of different patient outcome groups is crucial for developing better treatments and personalising existing treatments. However, such analyses are inherently limited by the fact that any two tissue samples vary due to a large number of factors unrelated to the outcome. Here, we present CF-HistoGAN, a machine learning framework that employs generative adversarial networks (GANs) to create artificial counterfactual tissue samples that resemble the original tissue samples as closely as possible but capture the characteristics of a different patient outcome group. Specifically, we learn to "translate" HMTI samples from one patient group to create artificial paired samples. We show that this approach allows to directly study the effects of different patient outcomes on the iTMEs of individual tissue samples. We demonstrate that CF-HistoGAN can be employed as an explorative tool for understanding iTME effects on the pixel level. Moreover, we show that our method can be used to identify statistically significant differences in the expression of different proteins between patient groups with greater sensitivity compared to conventional approaches.

Generative modeling of 3D brain MRIs presents difficulties in achieving high visual fidelity while ensuring sufficient coverage of the data distribution. In this work, we propose to address this challenge with composable, multiscale morphological transformations in a variational autoencoder (VAE) framework. These transformations are applied to a chosen reference brain image to generate MRI volumes, equipping the model with strong anatomical inductive biases. We structure the VAE latent space in a way such that the model covers the data distribution sufficiently well. We show substantial performance improvements in FID while retaining comparable, or superior, reconstruction quality compared to prior work based on VAEs and generative adversarial networks (GANs)., Comment: Accepted to the NeurIPS 2022 Workshop on Medical Imaging meets NeurIPS

Background and AimsProblem gambling constitutes a public health concern associated with psychopathological comorbidity, substance use, and financial difficulties. Most individuals with gambling problems avoid counseling services due to perceived stigma and their preference for self-reliance. Treatment accessibility could be improved through web-based interventions.MethodsWe recruited 360 individuals with gambling problems and randomized them to a web-based intervention (n = 185) or an active control group consisting of a self-help manual for problem gambling (n = 175). The primary outcome was the number of days of gambling in the last 30 days. Secondary outcomes included money spent in the last 30 days, time gambling in the last 7 days, gambling-related problems, consumption of alcohol and cigarettes, and psychopathological comorbidity measured at posttreatment and 6-month follow-up.ResultsThe primary outcome decreased significantly for both groups, with no significant difference between the groups. There were significant group × time interactions according to the Gambling Symptom Assessment Scale (F = 8.83, p <0 .001), the Problem Gambling Severity Index (F = 3.54, p = 0.030), for cigarettes smoked in the last 7 days (F = 26.68, p < 0.001), the Patient Health Questionnaire-9 (F = 19.41, p <0 .001), and the Generalized Anxiety Disorder-7 (F = 41.09, p <0 .001) favoring the intervention group. We experienced an overall high dropout rate (76%).ConclusionsWin Back Control seems to be an effective low-threshold treatment option for individuals with gambling problems that might otherwise be unapproachable for outpatient treatment services. Nevertheless, the high dropout rate should be considered when interpreting the study results, as they may have introduced a degree of variability.

Background and aimsProblem gambling and tobacco use are highly comorbid among adults. However, there are few treatment frameworks that target both gambling and tobacco use simultaneously (i.e., an integrated approach), while also being accessible and evidence-based. The aim of this two-arm open label RCT was to examine the efficacy of an integrated online treatment for problem gambling and tobacco use.MethodsA sample of 209 participants (M$_{age}$ = 37.66, SD = 13.81; 62.2% female) from North America were randomized into one of two treatment conditions (integrated [n = 91] or gambling only [n = 118]) that lasted for eight weeks and consisted of seven online modules. Participants completed assessments at baseline, after treatment completion, and at 24-week follow-up.ResultsWhile a priori planned generalized linear mixed models showed no condition differences on primary (gambling days, money spent, time spent) and secondary outcomes, both conditions did appear to significantly reduce problem gambling and smoking behaviours over time. Post hoc analyses showed that reductions in smoking and gambling craving were correlated with reductions in days spent gambling, as well as with gambling disorder symptoms. Relatively high (versus low) nicotine replacement therapy use was associated with greater reductions in gambling behaviours in the integrated treatment condition.Discussion and conclusionsWhile our open label RCT does not support a clear benefit of integrated treatment, findings suggest that changes in smoking and gambling were correlated over time, regardless of treatment condition, suggesting that more research on mechanisms of smoking outcomes in the context of gambling treatment may be relevant.

Early detection of anomalies in medical images such as brain MRI is highly relevant for diagnosis and treatment of many conditions. Supervised machine learning methods are limited to a small number of pathologies where there is good availability of labeled data. In contrast, unsupervised anomaly detection (UAD) has the potential to identify a broader spectrum of anomalies by spotting deviations from normal patterns. Our research demonstrates that existing state-of-the-art UAD approaches do not generalise well to diverse types of anomalies in realistic multi-modal MR data. To overcome this, we introduce a new UAD method named Aggregated Normative Diffusion (ANDi). ANDi operates by aggregating differences between predicted denoising steps and ground truth backwards transitions in Denoising Diffusion Probabilistic Models (DDPMs) that have been trained on pyramidal Gaussian noise. We validate ANDi against three recent UAD baselines, and across three diverse brain MRI datasets. We show that ANDi, in some cases, substantially surpasses these baselines and shows increased robustness to varying types of anomalies. Particularly in detecting multiple sclerosis (MS) lesions, ANDi achieves improvements of up to 178% in terms of AUPRC.

MRI reconstruction techniques based on deep learning have led to unprecedented reconstruction quality especially in highly accelerated settings. However, deep learning techniques are also known to fail unexpectedly and hallucinate structures. This is particularly problematic if reconstructions are directly used for downstream tasks such as real-time treatment guidance or automated extraction of clinical paramters (e.g. via segmentation). Well-calibrated uncertainty quantification will be a key ingredient for safe use of this technology in clinical practice. In this paper we propose a novel probabilistic reconstruction technique (PHiRec) building on the idea of conditional hierarchical variational autoencoders. We demonstrate that our proposed method produces high-quality reconstructions as well as uncertainty quantification that is substantially better calibrated than several strong baselines. We furthermore demonstrate how uncertainties arising in the MR econstruction can be propagated to a downstream segmentation task, and show that PHiRec also allows well-calibrated estimation of segmentation uncertainties that originated in the MR reconstruction process.

While deep neural network models offer unmatched classification performance, they are prone to learning spurious correlations in the data. Such dependencies on confounding information can be difficult to detect using performance metrics if the test data comes from the same distribution as the training data. Interpretable ML methods such as post-hoc explanations or inherently interpretable classifiers promise to identify faulty model reasoning. However, there is mixed evidence whether many of these techniques are actually able to do so. In this paper, we propose a rigorous evaluation strategy to assess an explanation technique's ability to correctly identify spurious correlations. Using this strategy, we evaluate five post-hoc explanation techniques and one inherently interpretable method for their ability to detect three types of artificially added confounders in a chest x-ray diagnosis task. We find that the post-hoc technique SHAP, as well as the inherently interpretable Attri-Net provide the best performance and can be used to reliably identify faulty model behavior., Comment: Accepted to MICCAI 2023

Deep Learning (DL) methods have shown promising results for solving ill-posed inverse problems such as MR image reconstruction from undersampled $k$-space data. However, these approaches currently have no guarantees for reconstruction quality and the reliability of such algorithms is only poorly understood. Adversarial attacks offer a valuable tool to understand possible failure modes and worst case performance of DL-based reconstruction algorithms. In this paper we describe adversarial attacks on multi-coil $k$-space measurements and evaluate them on the recently proposed E2E-VarNet and a simpler UNet-based model. In contrast to prior work, the attacks are targeted to specifically alter diagnostically relevant regions. Using two realistic attack models (adversarial $k$-space noise and adversarial rotations) we are able to show that current state-of-the-art DL-based reconstruction algorithms are indeed sensitive to such perturbations to a degree where relevant diagnostic information may be lost. Surprisingly, in our experiments the UNet and the more sophisticated E2E-VarNet were similarly sensitive to such attacks. Our findings add further to the evidence that caution must be exercised as DL-based methods move closer to clinical practice., Comment: Accepted at the MICCAI-2022 workshop: Machine Learning for Medical Image Reconstruction

Featured Application Nanoelectromechanical systems and nanorobots can be used to treat cancers associated with the Kv10.1 voltage-gated ion channel activity. The Kv10.1 model was developed by applying the control engineering theory. Nanoelectromechanical systems play the role of a PID regulator. The use of nanoelectromechanical systems or nanorobots offers a new concept for sensing and controlling subcellular structures, such as ion channels. We present here a novel method for mathematical modeling of ion channels based on control system theory and system identification. We investigated the use of nanoelectromechanical devices to control the activity of ion channels, particularly the activity of the voltage-gated ion channel Kv10.1, an important channel in cancer development and progression. A mathematical model of the dynamic behavior of the selected ion channel Kv10.1 in the Laplace (s) domain was developed, which is given in the representation of a transfer function. In addition, we addressed the possibilities of controlling ion channel activity by nanoelectromechanical devices and nanorobots and finally presented a control algorithm for the Kv10.1 as a control object. A use case demonstrates the potential of a Kv10.1 controlled nanorobot for cancer treatment at a single-cell level.

The mathematical modeling of ion channel kinetics is an important tool for studying the electrophysiological mechanisms of the nerves, heart, or cancer, from a single cell to an organ. Common approaches use either a Hodgkin-Huxley (HH) or a hidden Markov model (HMM) description, depending on the level of detail of the functionality and structural changes of the underlying channel gating, and taking into account the computational effort for model simulations. Here, we introduce for the first time a novel system theory-based approach for ion channel modeling based on the concept of transfer function characterization, without a priori knowledge of the biological system, using patch clamp measurements. Using the shaker-related voltage-gated potassium channel Kv1.1 (KCNA1) as an example, we compare the established approaches, HH and HMM, with the system theory-based concept in terms of model accuracy, computational effort, the degree of electrophysiological interpretability, and methodological limitations. This highly data-driven modeling concept offers a new opportunity for the phenomenological kinetic modeling of ion channels, exhibiting exceptional accuracy and computational efficiency compared to the conventional methods. The method has a high potential to further improve the quality and computational performance of complex cell and organ model simulations, and could provide a valuable new tool in the field of next-generation in silico electrophysiology.

Biomechanical and clinical gait research observes muscles and tendons in limbs to study their functions and behaviour. Therefore, movements of distinct anatomical landmarks, such as muscle-tendon junctions, are frequently measured. We propose a reliable and time efficient machine-learning approach to track these junctions in ultrasound videos and support clinical biomechanists in gait analysis. In order to facilitate this process, a method based on deep-learning was introduced. We gathered an extensive dataset, covering 3 functional movements, 2 muscles, collected on 123 healthy and 38 impaired subjects with 3 different ultrasound systems, and providing a total of 66864 annotated ultrasound images in our network training. Furthermore, we used data collected across independent laboratories and curated by researchers with varying levels of experience. For the evaluation of our method a diverse test-set was selected that is independently verified by four specialists. We show that our model achieves similar performance scores to the four human specialists in identifying the muscle-tendon junction position. Our method provides time-efficient tracking of muscle-tendon junctions, with prediction times of up to 0.078 seconds per frame (approx. 100 times faster than manual labeling). All our codes, trained models and test-set were made publicly available and our model is provided as a free-to-use online service on https://deepmtj.org/., Comment: in IEEE Transactions on Biomedical Engineering

Background: Prevalence rates for lifetime cannabis use and cannabis use disorder are much higher in people with attention deficit/hyperactivity disorder than in those without. CANreduce 2.0 is an intervention that is generally effective at reducing cannabis use in cannabis misusers. This self-guided web-based intervention (6-week duration) consists of modules grounded in motivational interviewing and cognitive behavioral therapy. Objective: We aimed to evaluate whether the CANreduce 2.0 intervention affects cannabis use patterns and symptom severity in adults who screen positive for attention deficit/hyperactivity disorder more than in those who do not. Methods: We performed a secondary analysis of data from a previous study with the inclusion criterion of cannabis use at least once weekly over the last 30 days. Adults with and without attention deficit/hyperactivity disorder (based on the Adult Attention deficit/hyperactivity disorder Self-Report screener) who were enrolled to the active intervention arms of CANreduce 2.0 were compared regarding the number of days cannabis was used in the preceding 30 days, the cannabis use disorder identification test score (CUDIT) and the severity of dependence scale score (SDS) at baseline and the 3-month follow-up. Secondary outcomes were Generalized Anxiety Disorder score, Center for Epidemiological Studies Depression scale score, retention, intervention adherence, and safety. Results: Both adults with (n=94) and without (n=273) positive attention-deficit/hyperactivity disorder screening reported significantly reduced frequency (reduction in consumption days: with: mean 11.53, SD 9.28, P<.001; without: mean 8.53, SD 9.4, P<.001) and severity of cannabis use (SDS: with: mean 3.57, SD 3.65, P<.001; without: mean 2.47, SD 3.39, P<.001; CUDIT: with: mean 6.38, SD 5.96, P<.001; without: mean 5.33, SD 6.05, P<.001), as well as anxiety (with: mean 4.31, SD 4.71, P<.001; without: mean 1.84, SD 4.22, P<.001) and depression (with: mean

Background: Cannabis is the most-frequently used illicit drug in Europe. Over the last few years in Spain, treatment demand has increased, yet most cannabis users do not seek treatment despite the related problems. A web-based self-help tool, like CANreduce 2.0, could help these users to control their consumption. Methods: This study protocol describes a three-arm randomized controlled trial (RCT) comparing the effectiveness of three approaches, in terms of reducing cannabis use among problematic cannabis users, the first two treatment arms including the Spanish version of CANreduce 2.0 (an adherence-focused, guidance-enhanced, web-based self-help tool) (1) with and (2) without psychological support; and the third group (3) treatment as usual (TAU). Study hypotheses will be tested concerning the primary outcome: change in the number of days of cannabis use over the previous week, comparing assessments at 6 weeks and 3 and 6 months follow-up between groups and against baseline. Secondary outcomes related to cannabis use will be tested similarly. Mental disorders will be explored as predictors of adherence and outcomes. Analyses will be performed on an intention-to-treat basis, then verified by complete case analyses. Discussion: This study will test how effective the Spanish version of CANreduce 2.0 (CANreduce-SP) is at reducing both the frequency and quantity of cannabis use in problematic users and whether adding psychological support increases its effectiveness. Trial registration: This trial is registered with the Clinical Trials Protocol Registration and Results System (PRS) number: NCT04517474 . Registered 18 August 2020, (Archived by archive.is https://archive.is/N1Y64 ). The project commenced in November 2020 and recruitment is anticipated to end by November 2022. Keywords: Adherence; CANreduce; Cannabis use disorder; Cognitive behavioural therapy; Guidance; Psychological support; Randomized controlled trial; Reducing cannabis; Self-help tool

Given prevalent alcohol misuse-emotional comorbidities among young adults, we developed an internet-based integrated treatment called Take Care of Me. Although the treatment had an impact on several secondary outcomes, effects were not observed for the primary outcome. Therefore, the goal of the current study was to examine heterogeneity in treatment responses. The initial RCT randomized participants to either a treatment or psychoeducational control condition. We conducted an exploratory latent class analysis to distinguish individuals based on pre-treatment risk and then used moderated regressions to examine differential treatment responses based on class membership. We found evidence for three distinct groups. Most participants fell in the “low severity” group (n = 123), followed by the “moderate severity” group (n = 57) who had a higher likelihood of endorsing a previous mental health diagnosis and treatment and higher symptom severity than the low group. The “high severity” group (n = 42) endorsed a family history of alcoholism, and the highest symptom severity and executive dysfunction. Moderated regressions revealed significant class differences in treatment responses. In the treatment condition, high severity (relative to low) participants reported higher alcohol consumption and hazardous drinking and lower quality of life at follow-up, whereas moderate severity (relative to low) individuals had lower alcohol consumption at follow-up, and lower hazardous drinking at end-of-treatment. No class differences were found for participants in the control group. Higher risk individuals in the treatment condition had poorer responses to the program. Tailoring interventions to severity may be important to examine in future research.

Background: Though Internet- and mobile-based interventions (IMIs) and mindfulness-based interventions (generally delivered in-situ) appear effective for people with substance use disorders, IMIs incorporating mindfulness are largely missing, including those targeting frequent cannabis use. Methods: This paper details the protocol for a three-arm randomized controlled trial comparing a mindfulness-based self-help IMI (arm 1) and cognitive-behavioral therapy (CBT)-based self-help IMI (arm 2) versus being on a waiting list (arm 3) in their effectiveness reducing cannabis use in frequent cannabis users. Predictors of retention, adherence and treatment outcomes will be identified and similarities between the two active intervention arms explored. Both active interventions last six weeks and consist of eight modules designed to reduce cannabis use and common mental health symptoms. With a targeted sample size of n = 210 per treatment arm, data will be collected at baseline immediately before program use is initiated; at six weeks, immediately after program completion; and at three and six months post baseline assessment to assess the retention of any gains achieved during treatment. The primary outcome will be number of days of cannabis use over the preceding 30 days. Secondary outcomes will include further measures of cannabis use and use of other substances, changes in mental health symptoms and mindfulness, client satisfaction, intervention retention and adherence, and adverse effects. Data analysis will follow ITT principles and primarily employ (generalized) linear mixed models. Discussion: This RCT will provide important insights into the effectiveness of an IMI integrating mindfulness to reduce cannabis use in frequent cannabis users. Trial registration: International Standard Randomized Controlled Trial Number Registry: ISRCTN14971662 ; date of registration: 09/09/2021. Keywords: Cannabis; Cognitive-behavioral therapy; Internet-based intervention; Mindfulness; Ra

ObjectiveTo identify and highlight research papers representing noteworthy developments in signals, sensors, and imaging informatics in 2020.MethodA broad literature search was conducted on PubMed and Scopus databases. We combined Medical Subject Heading (MeSH) terms and keywords to construct particular queries for sensors, signals, and image informatics. We only considered papers that have been published in journals providing at least three articles in the query response. Section editors then independently reviewed the titles and abstracts of preselected papers assessed on a three-point Likert scale. Papers were rated from 1 (do not include) to 3 (should be included) for each topical area (sensors, signals, and imaging informatics) and those with an average score of 2 or above were subsequently read and assessed again by two of the three co-editors. Finally, the top 14 papers with the highest combined scores were considered based on consensus.ResultsThe search for papers was executed in January 2021. After removing duplicates and conference proceedings, the query returned a set of 101, 193, and 529 papers for sensors, signals, and imaging informatics, respectively. We filtered out journals that had less than three papers in the query results, reducing the number of papers to 41, 117, and 333, respectively. From these, the co-editors identified 22 candidate papers with more than 2 Likert points on average, from which 14 candidate best papers were nominated after intensive discussion. At least five external reviewers then rated the remaining papers. The four finalist papers were found using the composite rating of all external reviewers. These best papers were approved by consensus of the International Medical Informatics Association (IMIA) Yearbook editorial board.ConclusionsSensors, signals, and imaging informatics is a dynamic field of intense research. The four best papers represent advanced approaches for combining, processing, modeling, and analyzing heterogene

Background: Despite increasing demand for treatment among cannabis users in many countries, most users are not in treatment. Internet-based self-help offers an alternative for those hesitant to seek face-to-face therapy, though low effectiveness and adherence issues often arise. Objective: Through adherence-focused guidance enhancement, we aimed to increase adherence to and the effectiveness of internet-based self-help among cannabis users. Methods: From July 2016 to May 2019, cannabis users (n=775; male: 406/575, 70.6%, female: 169/575, 29.4%; age: mean 28.3 years) not in treatment were recruited from the general population and were randomly assigned to (1) an adherence-focused guidance enhancement internet-based self-help intervention with social presence, (2) a similar intervention with an impersonal service team, and (3) access to internet as usual. Controls who were placed on a waiting list for the full intervention after 3 months underwent an assessment and had access to internet as usual. The primary outcome measurement was cannabis-use days over the preceding 30 days. Secondary outcomes included cannabis-dependence severity, changes in common mental disorder symptoms, and intervention adherence. Differences between the study arms in primary and secondary continuous outcome variables at baseline, posttreatment, and follow-up were tested using pooled linear models. Results: All groups exhibited reduced cannabis-use days after 3 months (social presence: -8.2 days; service team: -9.8 days; internet as usual: -4.2 days). The participants in the service team group (P=.01, d=.60) reported significantly fewer cannabis-use days than those in the internet as usual group; the reduction of cannabis use in the social presence group was not significant (P=.07, d=.40). There was no significant difference between the 2 intervention groups regarding cannabis-use reduction. The service team group also exhibited superior improvements in cannabis-use disorder, cannabis-dependen

Background Depression and harmful alcohol use are two of the top five leading causes of years of life lost to disability in high-income countries. Integrated treatment targeting both at the same time is often considered more complicated and difficult and, therefore, more expensive. Consequently, integrated internet-based interventions could be a valuable addition to traditional care. Methods A three-arm randomized controlled trial was conducted comparing the effectiveness of (1) an integrated, minimal-guidance, adherence-focused self-help intervention designed to reduce both alcohol use and depression symptoms (AFGE-AD); (2) a similar intervention designed to reduce alcohol use only (AFGE-AO), and (3) internet access as usual (IAU) as a control condition, in at least moderately depressed alcohol misusers from February 2016—March 2020. We recruited 689 alcohol misusers (51.6 % males, mean age = 42.8 years) with at least moderate depression symptoms not otherwise in treatment from the general population. Six months after baseline, 288 subjects (41.8 %) were reachable for the final assessment. Results All interventions yielded reduced alcohol-use after six months (AFGE-AD: -16.6; AFGE-AO: -19.8; IAU: -13.2). Those who undertook active-interventions reported significantly fewer standard drinks than controls (AFGE-AD: p = .048, d=0.10; AFGE-AO: p = .004, d=0.20). The two active-intervention groups also reported significantly less severe depression symptoms than controls (AFGE-AD: p = .006, d=0.41; AFGE-AO: p = .008, d=0.43). Testing revealed noninferiority between the two interventions. Conclusions This study documented sustained effectiveness of the first integrated, fully internet-based self-help intervention developed for the reduction of both alcohol use and depression symptoms in at least moderately depressed adult alcohol misusers recruited from the general population.

ackground and aims: Despite problematic pornography use (PPU) being prevalent, no previous study has examined the effectiveness of evidence-based interventions for PPU, using rigorous methods. Using a two-armed randomized controlled trial study design, we examined the feasibility and initial effectiveness of a six-week online PPU intervention. Methods: We recruited 264 participants (3.8% women, M age = 33.2, SD = 10.6) who were randomized and assigned to either the self-help intervention (n = 123) or waitlist control condition (n = 141), and completed self-report questionnaires at baseline and after the end of the intervention (six-week follow-up). Multivariable linear regression models were generated and tested on a complete case basis to investigate possible treatment effects. Participants provided quantitative and qualitative feedback regarding the intervention's content and appearance. Results: Participants evaluated all modules positively in the intervention in general. There were differential dropout rates (89.4% in intervention vs. 44.7% in control group) with an overall follow-up rate of 34.5%. The intervention group reported significantly lower levels of PPU (P < 0.001, d = 1.32) at the six-week follow-up. Moreover, they reported lower pornography use frequency (P < 0.001, d = 1.65), self-perceived pornography addiction (P = 0.01, d = 0.85), pornography craving (P = 0.02, d = 0.40), and higher pornography avoidance self-efficacy (P = 0.001, d = 0.87) at the six-week follow-up. Discussion and conclusions: The present study was only a first step in rigorous treatment studies for PPU, but the findings are promising and suggest that online interventions for PPU might help reduce PPU in some cases, even without the guidance of therapists, by reducing treatment barriers. Keywords: cognitive-behavioral therapy; compulsive sexual behavior; feasibility; online intervention; problematic pornography use.

Many young adults struggle with comorbid alcohol misuse and emotional problems (i.e., depression and anxiety). However, there is currently a paucity of evidence-based, integrated, accessible treatment options for individuals with these comorbidities. The main goal of this study was to examine efficacy of a novel online, minimally guided, integrated program for comorbid alcohol misuse and emotional problems in young adults. Method: The study was an open-label two-arm RCT. Participants (N = 222, M age = 24.6, 67.6% female) were randomized to one of two conditions: the Take Care of Me program (an 8-week, online integrated treatment condition consisting of 12 modules), or an online psychoeducational control condition. Intervention modules incorporated content based on principles of cognitive behavioral therapy and motivational interviewing. Participants completed assessment data at baseline, at the end of treatment (i.e., 8 weeks), and at follow-up (i.e., 24 weeks). Data were analyzed using generalized linear mixed models. Results: We observed that participants in the treatment condition showed larger reductions in depression, hazardous drinking, as well as increases in psychological quality of life and confidence at the end of treatment. We did not find group differences on total alcohol use at follow-up, but participants in the treatment group reduced their hazardous drinking and improved their quality of life at 24-week follow-up. Conclusions: Our study provides promising initial evidence for the first iteration of the comorbid alcohol misuse and emotional problems online program. Keywords: Alcohol misuse; Anxiety; Cognitive behavioural therapy; Depression; Emerging adulthood; Integrated treatment; Minimally guided; Motivational interviewing; Online.

ObjectiveTo highlight noteworthy papers that are representative of 2019 developments in the fields of sensors, signals, and imaging informatics.MethodA broad literature search was conducted in January 2020 using PubMed. Separate predefined queries were created for sensors/signals and imaging informatics using a combination of Medical Subject Heading (MeSH) terms and keywords. Section editors reviewed the titles and abstracts of both sets of results. Papers were assessed on a three-point Likert scale by two co-editors, rated from 3 (do not include) to 1 (should be included). Papers with an average score of 2 or less were then read by all three section editors, and the group nominated top papers based on consensus. These candidate best papers were then rated by at least six external reviewers.ResultsThe query related to signals and sensors returned a set of 255 papers from 140 unique journals. The imaging informatics query returned a set of 3,262 papers from 870 unique journals. Based on titles and abstracts, the section co-editors jointly filtered the list down to 50 papers from which 15 candidate best papers were nominated after discussion. A composite rating after review determined four papers which were then approved by consensus of the International Medical Informatics Association (IMIA) Yearbook editorial board. These best papers represent different international groups and journals.ConclusionsThe four best papers represent state-of-the-art approaches for processing, combining, and analyzing heterogeneous sensor and imaging data. These papers demonstrate the use of advanced machine learning techniques to improve comparisons between images acquired at different time points, fuse information from multiple sensors, and translate images from one modality to another.

The tilt of solar active regions described by Joy's law is essential for converting a toroidal field to a poloidal field in Babcock-Leighton dynamo models. In thin flux tube models the Coriolis force causes Joy's law, acting on east-west flows as they rise towards the surface. Our goal is to measure the evolution of the average tilt angle of hundreds of active regions as they emerge, so that we can constrain the origins of Joy's law. We measured the tilt angle of the primary bipoles in 153 emerging active regions in the Solar Dynamics Observatory Helioseismic Emerging Active Region survey. We used line-of-sight magnetic field measurements averaged over 6 hours to define the polarities and measure the tilt angle up to four days after emergence. We find that at the time of emergence the polarities are on average aligned east-west, and that neither the separation nor the tilt depends on latitude. We do find, however, that ARs at higher latitudes have a faster north-south separation speed than those closer to the equator at the emergence time. After emergence, the tilt angle increases and Joy's law is evident about two days later. The scatter in the tilt angle is independent of flux until about one day after emergence, when higher-flux regions have a smaller scatter in tilt angle than lower-flux regions. Our finding that active regions emerge with an east-west alignment is surprising since thin flux tube models predict that tilt angles of rising flux tubes are generated below the surface. Previously reported tilt angle relaxation of deeply anchored flux tubes can be largely explained by the change in east-west separation. We conclude that Joy's law is caused by an inherent north-south separation speed present when the flux first reaches the surface, and that the scatter in the tilt angle is consistent with buffeting of the polarities by supergranulation., Comment: accepted in Astronomy and Astrophysics

Optoelectronic neurostimulation is a promising, minimally invasive treatment modality for neuronal damage, in particular for patients with traumatic brain injury. In this work, a newly developed optoelectronic device, a so-called photocap, based on light-activated organic semiconductor structures with high spatial and temporal resolution is investigated. To prove and verify the feasibility of this new technology, a mathematical model was developed, simulating the electrical response of excitable cells to photocap stimulation. In the first step, a comprehensive technical review of the device concept was performed, building the basis for setting up the simulation model. The simulations demonstrate that photocaps may serve as a stimulation device, triggering action potentials in neural or cardiac cells. Our first results show that the model serves as a perfect tool for evaluating and further developing this new technology, showing high potential for introducing new and innovative therapy methods in the field of optoelectronic cell stimulation., Funding agency: FWF Zukunftskolleg Program as part of the project“LOGOS-TBI: Light-controlled Organic Semiconductor Implants for Regeneration afterTBI” (Project ID: ZK-17)

Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such datasets is not a favourable option because acquiring a large number of annotated samples from experts is time-consuming and expensive. Consequently, numerous methods have been proposed in the literature for learning with limited annotated examples. Unfortunately, the proposed approaches in the literature have not yet yielded significant gains over random data augmentation for image segmentation, where random augmentations themselves do not yield high accuracy. In this work, we propose a novel task-driven data augmentation method for learning with limited labeled data where the synthetic data generator, is optimized for the segmentation task. The generator of the proposed method models intensity and shape variations using two sets of transformations, as additive intensity transformations and deformation fields. Both transformations are optimized using labeled as well as unlabeled examples in a semi-supervised framework. Our experiments on three medical datasets, namely cardic, prostate and pancreas, show that the proposed approach significantly outperforms standard augmentation and semi-supervised approaches for image segmentation in the limited annotation setting. The code is made publicly available at https://github.com/krishnabits001/task$\_$driven$\_$data$\_$augmentation., Comment: 15 pages, 11 Figures, 3 tables. Accepted at Medical Image Analysis, 2020

Recording muscle tendon junction displacements during movement, allows separate investigation of the muscle and tendon behaviour, respectively. In order to provide a fully-automatic tracking method, we employ a novel deep learning approach to detect the position of the muscle tendon junction in ultrasound images. We utilize the attention mechanism to enable the network to focus on relevant regions and to obtain a better interpretation of the results. Our data set consists of a large cohort of 79 healthy subjects and 28 subjects with movement limitations performing passive full range of motion and maximum contraction movements. Our trained network shows robust detection of the muscle tendon junction on a diverse data set of varying quality with a mean absolute error of 2.55$\pm$1 mm. We show that our approach can be applied for various subjects and can be operated in real-time. The complete software package is available for open-source use via: https://github.com/luuleitner/deepMTJ, Comment: Accepted version to be published in 2020, 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Montreal, Canada

Tissue characterisation with CMR parametric mapping has the potential to detect and quantify both focal and diffuse alterations in myocardial structure not assessable by late gadolinium enhancement. Native T1 mapping in particular has shown promise as a useful biomarker to support diagnostic, therapeutic and prognostic decision-making in ischaemic and non-ischaemic cardiomyopathies. Convolutional neural networks with Bayesian inference are a category of artificial neural networks which model the uncertainty of the network output. This study presents an automated framework for tissue characterisation from native ShMOLLI T1 mapping at 1.5T using a Probabilistic Hierarchical Segmentation (PHiSeg) network. In addition, we use the uncertainty information provided by the PHiSeg network in a novel automated quality control (QC) step to identify uncertain T1 values. The PHiSeg network and QC were validated against manual analysis on a cohort of the UK Biobank containing healthy subjects and chronic cardiomyopathy patients. We used the proposed method to obtain reference T1 ranges for the left ventricular myocardium in healthy subjects as well as common clinical cardiac conditions. T1 values computed from automatic and manual segmentations were highly correlated (r=0.97). Bland-Altman analysis showed good agreement between the automated and manual measurements. The average Dice metric was 0.84 for the left ventricular myocardium. The sensitivity of detection of erroneous outputs was 91%. Finally, T1 values were automatically derived from 14,683 CMR exams from the UK Biobank. The proposed pipeline allows for automatic analysis of myocardial native T1 mapping and includes a QC process to detect potentially erroneous results. T1 reference values were presented for healthy subjects and common clinical cardiac conditions from the largest cohort to date using T1-mapping images.

Over the past decade, deep learning has become the gold standard for automatic medical image segmentation. Every segmentation task has an underlying uncertainty due to image resolution, annotation protocol, etc. Therefore, a number of methods and metrics have been proposed to quantify the uncertainty of neural networks mostly based on Bayesian deep learning, ensemble learning methods or output probability calibration. The aim of our research is to assess how reliable the different uncertainty metrics found in the literature are. We propose a quantitative and statistical comparison of uncertainty measures based on the relevance of the uncertainty map to predict misclassification. Four uncertainty metrics were compared over a set of 144 models. The application studied is the segmentation of the lumen and vessel wall of carotid arteries based on multiple sequences of magnetic resonance (MR) images in multi-center data.

Undersampling the k-space during MR acquisitions saves time, however results in an ill-posed inversion problem, leading to an infinite set of images as possible solutions. Traditionally, this is tackled as a reconstruction problem by searching for a single "best" image out of this solution set according to some chosen regularization or prior. This approach, however, misses the possibility of other solutions and hence ignores the uncertainty in the inversion process. In this paper, we propose a method that instead returns multiple images which are possible under the acquisition model and the chosen prior to capture the uncertainty in the inversion process. To this end, we introduce a low dimensional latent space and model the posterior distribution of the latent vectors given the acquisition data in k-space, from which we can sample in the latent space and obtain the corresponding images. We use a variational autoencoder for the latent model and the Metropolis adjusted Langevin algorithm for the sampling. We evaluate our method on two datasets; with images from the Human Connectome Project and in-house measured multi-coil images. We compare to five alternative methods. Results indicate that the proposed method produces images that match the measured k-space data better than the alternatives, while showing realistic structural variability. Furthermore, in contrast to the compared methods, the proposed method yields higher uncertainty in the undersampled phase encoding direction, as expected. Keywords: Magnetic Resonance image reconstruction, uncertainty estimation, inverse problems, sampling, MCMC, deep learning, unsupervised learning., Comment: Accepted to IEEE Transactions in Medical Imaging. Main article and appendix together. GIFs and code can be found on https://github.com/kctezcan/sampling

Background and aims: The past-year prevalence of problematic pornography use (PPU) was 1-6% in adult populations. As a result of treatment obstacles and barriers, such as unaffordable treatments, only a minority of problematic pornography users may seek treatment. Having a free, online, self-help program may overcome treatment barriers and may help those individuals who cannot receive traditional or offline treatment for PPU. Although the effectiveness of such online programs reducing substance use and problematic gambling have been reported, no prior study has examined the efficacy of an online self-help intervention aiming to reduce PPU. Methods: This two-armed randomized controlled trial (RCT) will examine the effectiveness of an online self-help program (Hands-off) to reduce PPU, while also considering psychopathological comorbidities. The six-week intervention condition includes six core modules developed to reduce PPU based on motivational interviewing, cognitive behavioral therapy, mindfulness, and wise social-psychological intervention techniques. The target sample size is 242 participants. Self-report questionnaires will be administered at baseline, right after the end of the intervention, at one-month, and three-month follow-ups after the end of the intervention. The primary outcome will be the level of PPU. Secondary outcomes will include pornography use frequency, pornography craving, pornography use-avoidance self-efficacy, sex mindset, sexual satisfaction, negative and positive emotions, and life satisfaction. Data will be analyzed on an intention-to-treat basis using linear mixed models. Results: Results will be reported at conferences and published in a scientific peer-reviewed journal. The participants will be sent a lay-person-friendly summary of the results via e-mail. Keywords: cognitive-behavioral therapy; motivational interview; online intervention; problematic pornography use; wise social-psychological intervention

Background Gambling and tobacco smoking are highly comorbid among North American adults. However, there is a paucity of treatment options that are integrated (i.e. targeting both gambling and tobacco smoking simultaneously), accessible, and evidence based. Methods The aim of this two-arm open-label randomized controlled trial is to examine the effectiveness of an online, self-guided integrated treatment for problem gambling and tobacco smoking. A target sample of 214 participants will be recruited and be randomized into either an 8-week integrated or gambling only control condition. Both conditions will consist of seven online modules following cognitive behavioural therapy and motivational interviewing principles. Our three primary outcomes are (1) the number of days gambled, (2) money spent on gambling activities, and (3) time spent in gambling activities. Secondary outcomes include gambling disorder symptoms, cigarette use, and nicotine dependence symptoms. Assessments will be completed at baseline, at completion (i.e. 8 weeks from baseline), and at follow-up (i.e. 24 weeks from baseline). Generalized linear mixed modelling will be used to evaluate our primary and secondary outcomes. We expect that participants receiving online integrated treatment will show larger reductions in gambling relative to those receiving a control gambling only intervention. We further hypothesize that reductions in smoking will mediate these group differences. Discussion The rates of problem gambling and tobacco smoking are high in North America; yet, the treatment options for both are limited, with no integrated treatments available. If supported, our pilot study will be a cost-effective and accessible way to improve treatments for co-occurring problem gambling and tobacco use.

ObjectiveTo identify research works that exemplify recent developments in the field of sensors, signals, and imaging informatics.MethodA broad literature search was conducted using PubMed and Web of Science, supplemented with individual papers that were nominated by section editors. A predefined query made from a combination of Medical Subject Heading (MeSH) terms and keywords were used to search both sources. Section editors then filtered the entire set of retrieved papers with each paper having been reviewed by two section editors. Papers were assessed on a three-point Likert scale by two section editors, rated from 0 (do not include) to 2 (should be included). Only papers with a combined score of 2 or above were considered.ResultsA search for papers was executed at the start of January 2019, resulting in a combined set of 1,459 records published in 2018 in 119 unique journals. Section editors jointly filtered the list of candidates down to 14 nominations. The 14 candidate best papers were then ranked by a group of eight external reviewers. Four papers, representing different international groups and journals, were selected as the best papers by consensus of the International Medical Informatics Association (IMIA) Yearbook editorial board.ConclusionsThe fields of sensors, signals, and imaging informatics have rapidly evolved with the application of novel artificial intelligence/machine learning techniques. Studies have been able to discover hidden patterns and integrate different types of data towards improving diagnostic accuracy and patient outcomes. However, the quality of papers varied widely without clear reporting standards for these types of models. Nevertheless, a number of papers have demonstrated useful techniques to improve the generalizability, interpretability, and reproducibility of increasingly sophisticated models.

Introduction The past-year prevalence of problem gambling worldwide averages 2.3%. Switzerland exhibits a slightly lower past-year prevalence rate, of 1.1%, among adults. Only a minority of these adults attend outpatient treatment. Surveyed problem gamblers have explained that they wanted to handle the problem on their own. The option of a web-based self-help programme could potentially reach those users who hesitate to approach treatment centres and help them to reduce or stop their problem gambling. The effectiveness of such web-based interventions has been shown in other countries. Methods and analysis This two-armed randomised controlled trial (RCT) will examine the efficacy of a web-based self-help intervention, relative to an active control condition with a self-help manual, at reducing problem gambling. The active intervention programme, spanning 8 weeks, consists of nine modules developed to reduce gambling and attenuate psychopathological comorbidity, including depression, anxiety and stress-related disorder symptoms, relying on motivational interviewing and cognitive behavioural therapy. With a target sample size of 352, questionnaire data will be collected at baseline, and at 8 and 24 weeks after baseline. Primary outcomes will be the number of days one has gambled in the last 30 days. Secondary outcomes will include money and time spent on gambling activities, changes in gambling-related problems (Problem Gambling Severity Index, Gambling Symptom Assessment Scale), use of alcohol and cigarettes, and psychopathological comorbidity. All data analysis will comply with the intention-to-treat principle. Ethics and dissemination The RCT will be conducted in accordance with the Declaration of Helsinki; the consort eHealth Guidelines for studies on medical devices; the European Directive on medical devices 93/42/EEC, Swiss Law and Swiss Regulatory Authority requirements. The study was approved by the ethics committee of the Canton of Zurich. Results will be publ

One of the key drawbacks of 3D convolutional neural networks for segmentation is their memory footprint, which necessitates compromises in the network architecture in order to fit into a given memory budget. Motivated by the RevNet for image classification, we propose a partially reversible U-Net architecture that reduces memory consumption substantially. The reversible architecture allows us to exactly recover each layer's outputs from the subsequent layer's ones, eliminating the need to store activations for backpropagation. This alleviates the biggest memory bottleneck and enables very deep (theoretically infinitely deep) 3D architectures. On the BraTS challenge dataset, we demonstrate substantial memory savings. We further show that the freed memory can be used for processing the whole field-of-view (FOV) instead of patches. Increasing network depth led to higher segmentation accuracy while growing the memory footprint only by a very small fraction, thanks to the partially reversible architecture., Comment: Accepted to MICCAI 2019; Edit v2: Added reference to related work of Blumberg et al

Segmentation of anatomical structures and pathologies is inherently ambiguous. For instance, structure borders may not be clearly visible or different experts may have different styles of annotating. The majority of current state-of-the-art methods do not account for such ambiguities but rather learn a single mapping from image to segmentation. In this work, we propose a novel method to model the conditional probability distribution of the segmentations given an input image. We derive a hierarchical probabilistic model, in which separate latent variables are responsible for modelling the segmentation at different resolutions. Inference in this model can be efficiently performed using the variational autoencoder framework. We show that our proposed method can be used to generate significantly more realistic and diverse segmentation samples compared to recent related work, both, when trained with annotations from a single or multiple annotators., Comment: Accepted to MICCAI 2019