Epidemiological description and trajectories of patients with prostate cancer in Denmark: an observational study of 7448 patients.

OBJECTIVE: Identification of patients at high risk of aggressive prostate cancer is a major clinical challenge. With the view of developing artificial intelligence-based methods for identification of these patients, we are constructing a comprehensive clinical database including 7448 prostate cancer (PCa) Danish patients. In this paper we provide an epidemiological description and patients' trajectories of this retrospective observational population, to contribute to the understanding of the characteristics and pathways of PCa patients in Denmark. RESULTS: Individuals receiving a PCa diagnosis during 2008-2014 in Region Southern Denmark were identified, and all diagnoses, operations, investigations, and biochemistry analyses, from 4 years prior, to 5 years after PCa diagnosis were obtained. About 85.1% were not diagnosed with metastatic PCa during the study period (unaggressive PCa); 9.2% were simultaneously diagnosed with PCa and metastasis (aggressive-advanced PCa), while 5.7% were not diagnosed with metastatic PCa at first, but they were diagnosed with metastasis at some point during the 5 years follow-up (aggressive-not advanced PCa). Patients with unaggressive PCa had more clinical investigations directly related to PCa detection (prostate ultrasounds and biopsies) during the 4 years prior to PCa diagnosis, compared to patients with aggressive PCa, which may have contributed to the early detection of PCa.

AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images.

Semantic segmentation of biomedical images found its niche in screening and diagnostic applications. Recent methods based on deep learning convolutional neural networks have been very effective, since they are readily adaptive to biomedical applications and outperform other competitive segmentation methods. Inspired by the U-Net, we designed a deep learning network with an innovative architecture, hereafter referred to as AID-U-Net. Our network consists of direct contracting and expansive paths, as well as a distinguishing feature of containing sub-contracting and sub-expansive paths. The implementation results on seven totally different databases of medical images demonstrated that our proposed network outperforms the state-of-the-art solutions with no specific pre-trained backbones for both 2D and 3D biomedical image segmentation tasks. Furthermore, we showed that AID-U-Net dramatically reduces time inference and computational complexity in terms of the number of learnable parameters. The results further show that the proposed AID-U-Net can segment different medical objects, achieving an improved 2D F1-score and 3D mean BF-score of 3.82% and 2.99%, respectively.

Artificial intelligence outperforms standard blood-based scores in identifying liver fibrosis patients in primary care.

For years, hepatologists have been seeking non-invasive methods able to detect significant liver fibrosis. However, no previous algorithm using routine blood markers has proven to be clinically appropriate in primary care. We present a novel approach based on artificial intelligence, able to predict significant liver fibrosis in low-prevalence populations using routinely available patient data. We built six ensemble learning models (LiverAID) with different complexities using a prospective screening cohort of 3352 asymptomatic subjects. 463 patients were at a significant risk that justified performing a liver biopsy. Using an unseen hold-out dataset, we conducted a head-to-head comparison with conventional methods: standard blood-based indices (FIB-4, Forns and APRI) and transient elastography (TE). LiverAID models appropriately identified patients with significant liver stiffness (> 8 kPa) (AUC of 0.86, 0.89, 0.91, 0.92, 0.92 and 0.94, and NPV ≥ 0.98), and had a significantly superior discriminative ability (p < 0.01) than conventional blood-based indices (AUC = 0.60-0.76). Compared to TE, LiverAID models showed a good ability to rule out significant biopsy-assessed fibrosis stages. Given the ready availability of the required data and the relatively high performance, our artificial intelligence-based models are valuable screening tools that could be used clinically for early identification of patients with asymptomatic chronic liver diseases in primary care.

[Colon capsuleendoscopy].

Colon capsule endoscopy (CCE) was introduced in 2006 as a novel way to visualise the colonic mucosa. Initially, CCE validity was limited by low completion rates (CR) and poor image quality. Through technical progress and improved bowel preparations, CCE now offers an adjunct to diagnostic colonoscopy. As referred in this review, several studies have shown promising results regarding polyp detection rates by the use of CCE. Improvements in CR and quality of bowel preparation are needed for CCE to be on a par with conventional colonoscopy. Research in artificial intelligence is evolving to aid in diagnostics and staging using CCE.

Video-based eye tracking performance for computer-assisted diagnostic support of diabetic neuropathy.

Diabetes is currently one of the major public health threats. The essential components for effective treatment of diabetes include early diagnosis and regular monitoring. However, health-care providers are often short of human resources to closely monitor populations at risk. In this work, a video-based eye-tracking method is proposed as a low-cost alternative for detection of diabetic neuropathy. The method is based on the tracking of the eye-trajectories recorded on videos while the subject follows a target on a screen, forcing saccadic movements. Upon extraction of the eye trajectories, representation of the obtained time-series is made with the help of heteroscedastic ARX (H-ARX) models, which capture the dynamics and latency on the subject's response, while features based on the H-ARX model's predictive ability are subsequently used for classification. The methodology is evaluated on a population constituted by 11 control and 20 insulin-treated diabetic individuals suffering from diverse diabetic complications including neuropathy and retinopathy. Results show significant differences on latency and eye movement precision between the populations of control subjects and diabetics, while simultaneously demonstrating that both groups can be classified with an accuracy of 95%. Although this study is limited by the small sample size, the results align with other findings in the literature and encourage further research.

Feature Point Tracking-Based Localization of Colon Capsule Endoscope.

In large bowel investigations using endoscopic capsules and upon detection of significant findings, physicians require the location of those findings for a follow-up therapeutic colonoscopy. To cater to this need, we propose a model based on tracking feature points in consecutive frames of videos retrieved from colon capsule endoscopy investigations. By locally approximating the colon as a cylinder, we obtained both the displacement and the orientation of the capsule using geometrical assumptions and by setting priors on both physical properties of the intestine and the image sample frequency of the endoscopic capsule. Our proposed model tracks a colon capsule endoscope through the large intestine for different prior selections. A discussion on validating the findings in terms of intra and inter capsule and expert panel validation is provided. The performance of the model is evaluated based on the average difference in multiple reconstructed capsule's paths through the large intestine. The path difference averaged over all videos was as low as 4±0.7 cm, with min and max error corresponding to 1.2 and 6.0 cm, respectively. The inter comparison addresses frame classification for the rectum, descending and sigmoid, splenic flexure, transverse, hepatic, and ascending, with an average accuracy of 86%.

Facial erythema detects diabetic neuropathy using the fusion of machine learning, random matrix theory and self organized criticality.

Rubeosis faciei diabeticorum, caused by microangiopathy and characterized by a chronic facial erythema, is associated with diabetic neuropathy. In clinical practice, facial erythema of patients with diabetes is evaluated based on subjective observations of visible redness, which often goes unnoticed leading to microangiopathic complications. To address this major shortcoming, we designed a contactless, non-invasive diagnostic point-of-care-device (POCD) consisting of a digital camera and a screen. Our solution relies on (1) recording videos of subject's face (2) applying Eulerian video magnification to videos to reveal important subtle color changes in subject's skin that fall outside human visual limits (3) obtaining spatio-temporal tensor expression profile of these variations (4) studying empirical spectral density (ESD) function of the largest eigenvalues of the tensors using random matrix theory (5) quantifying ESD functions by modeling the tails and decay rates using power law in systems exhibiting self-organized-criticality and (6) designing an optimal ensemble of learners to classify subjects into those with diabetic neuropathy and those of a control group. By analyzing a short video, we obtained a sensitivity of 100% in detecting subjects diagnosed with diabetic neuropathy. Our POCD paves the way towards the development of an inexpensive home-based solution for early detection of diabetic neuropathy and its associated complications.

Non-invasive detection of diabetic complications via pattern analysis of temporal facial colour variations.

BACKGROUND AND OBJECTIVE: Diabetes mellitus is a common disorder amounting to 400 million patients worldwide. It is often accompanied by a number of complications, including neuropathy, nephropathy, and cardiovascular diseases. For example, peripheral neuropathy is present among 20-30% of diabetics before the diagnosis is substantiated. For this reason, a reliable detection method for diabetic complications is crucial and attracts a lot of research attention. METHODS: In this paper, we introduce a non-invasive detection framework for patients with diabetic complications that only requires short video recordings of faces from a standard commercial camera. We employed multiple image processing and pattern recognition techniques to process video frames, extract relevant information, and predict the health status. To evaluate our framework, we collected a dataset of 114 video files from diabetic patients, who were diagnosed with diabetes for years and 60 video files from the control group. Extracted features from videos were tested using two conceptually different classifiers. RESULTS: We found that our proposed framework correctly identifies patients with diabetic complications with 92.86% accuracy, 100% sensitivity, and 80% specificity. CONCLUSIONS: Our study brings a novel perspective on diagnosis procedures in this field. We used multiple techniques from image processing, pattern recognition, and machine learning to robustly process video frames and predict the health status of our subjects with high efficiency.

Invisible Color Variations of Facial Erythema: A Novel Early Marker for Diabetic Complications?

AIM: (1) To quantify the invisible variations of facial erythema that occur as the blood flows in and out of the face of diabetic patients, during the blood pulse wave using an innovative image processing method, on videos recorded with a conventional digital camera and (2) to determine whether this "unveiled" facial red coloration and its periodic variations present specific characteristics in diabetic patients different from those in control subjects. METHODS: We video recorded the faces of 20 diabetic patients with peripheral neuropathy, retinopathy, and/or nephropathy and 10 nondiabetic control subjects, using a Canon EOS camera, for 240 s. Only one participant presented visible facial erythema. We applied novel image processing methods to make the facial redness and its variations visible and automatically detected and extracted the redness intensity of eight facial patches, from each frame. We compared average and standard deviations of redness in the two groups using t-tests. RESULTS: Facial redness varies, imperceptibly and periodically, between redder and paler, following the heart pulsation. This variation is consistently and significantly larger in diabetic patients compared to controls (p value < 0.001). CONCLUSIONS: Our study and its results (i.e., larger variations of facial redness with the heartbeats in diabetic patients) are unprecedented. One limitation is the sample size. Confirmation in a larger study would ground the development of a noninvasive cost-effective automatic tool for early detection of diabetic complications, based on measuring invisible redness variations, by image processing of facial videos captured at home with the patient's smartphone.

Addressing priority challenges in the detection and assessment of colorectal polyps from capsule endoscopy and colonoscopy in colorectal cancer screening using machine learning.

BACKGROUND: Colorectal capsule endoscopy (CCE) is a potentially valuable patient-friendly technique for colorectal cancer screening in large populations. Before it can be widely applied, significant research priorities need to be addressed. We present two innovative data science algorithms which can considerably improve acquisition and analysis of relevant data on colorectal polyps obtained from capsule endoscopy. MATERIAL AND METHODS: A fully paired study was performed (2015-2016), where 255 participants from the Danish national screening program had CCE, colonoscopy, and histopathology of all detected polyps. We developed: (1) a new algorithm to match CCE and colonoscopy polyps, based on objective measures of similarity between polyps, and (2) a deep convolutional neural network (CNN) for autonomous detection and localization of colorectal polyps in colon capsule endoscopy. RESULTS AND CONCLUSION: Unlike previous matching methods, our matching algorithm is able to objectively quantify the similarity between CCE and colonoscopy polyps based on their size, morphology and location, and provides a one-to-one unequivocal match between CCE and colonoscopy polyps. Compared to previous methods, the autonomous detection algorithm showed unprecedented high accuracy (96.4%), sensitivity (97.1%) and specificity (93.3%), calculated in respect to the number of polyps detected by trained nurses and gastroenterologists after visualizing frame-by-frame the CCE videos.

Assessment of bowel cleansing quality in colon capsule endoscopy using machine learning: a pilot study.

BACKGROUND AND STUDY AIMS: The aim of this study was to develop a machine learning-based model to classify bowel cleansing quality and to test this model in comparison to a pixel analysis model and assessments by four colon capsule endoscopy (CCE) readers. METHODS: A pixel analysis and a machine learning-based model with four cleanliness classes (unacceptable, poor, fair and good) were developed to classify CCE videos. Cleansing assessments by four CCE readers in 41 videos from a previous study were compared to the results both models yielded in this pilot study. RESULTS: The machine learning-based model classified 47 % of the videos in agreement with the averaged classification by CCE readers, as compared to 32 % by the pixel analysis model. A difference of more than one class was detected in 12 % of the videos by the machine learning-based model and in 32 % by the pixel analysis model, as the latter tended to overestimate cleansing quality. A specific analysis of unacceptable videos found that the pixel analysis model classified almost all of them as fair or good, whereas the machine learning-based model identified five out of 11 videos in agreement with at least one CCE reader as unacceptable. CONCLUSIONS: The machine learning-based model was superior to the pixel analysis in classifying bowel cleansing quality, due to a higher sensitivity to unacceptable and poor cleansing quality. The machine learning-based model can be further improved by coming to a consensus on how to classify cleanliness of a complete CCE video, by means of an expert panel.

Capsule endoscopy vs. colonoscopy vs. histopathology in colorectal cancer screening: matched analyses of polyp size, morphology, and location estimates.

PURPOSE: Colon capsule endoscopy (CCE) is considered a potential alternative to optical colonoscopy (OC) for colorectal cancer screening. However, the accuracy of CCE in polyp size and morphology estimation is unknown. METHODS: A fully paired study was performed (2015-2016), where 255 participants from the Danish national screening program had CCE, OC, and histopathology (HP) of all detected polyps. We developed a new algorithm to match CCE and OC polyps, based on objective measures of similarity between polyps. We performed paired comparisons of size, morphology and location of CCE, and OC- and HP-matched polyps. We used cross-validation to develop a model able to predict HP polyp size, based on CCE. RESULTS: CCE overestimated size assessed by HP (by 4.3 mm; 95%CI 3.3-5.2 mm) and OC (by 2.7 mm; 95%CI 1.4-3.9 mm). Polyps were more likely to being assessed as "pedunculated" and less likely to being assessed as "flat" in CCE, compared to OC (p < 0.0001). Our model could predict HP polyp size ≥ 6 mm, solely using CCE-assessed size, location, and morphology as model inputs, with a sensitivity = 0.93 (95%CI 0.66-1.00) and specificity = 0.50 (95%CI 0.32-0.68). CONCLUSIONS: If CCE is to be used as a screening test, it is essential: (1) to translate CCE polyp estimations into histopathologic polyp sizes and (2) to consider that, compared to OC, CCE has a higher tendency to assess polyps as pedunculated and a lower tendency to assess them as flat. TRIAL REGISTRATION: Clinicaltrials.gov No. NCT02303756.

A novel approach for exposure assessment in air pollution epidemiological studies using neuro-fuzzy inference systems: Comparison of exposure estimates and exposure-health associations.

Many epidemiological studies have used proximity to sources as air pollution exposure assessment method. However, proximity measures are not generally good surrogates because of their complex non-linear relationship with exposures. Neuro-fuzzy inference systems (NFIS) can be used to map complex non-linear systems, but its usefulness in exposure assessment has not been extensively explored. We present a novel approach for exposure assessment using NFIS, where the inputs of the model were easily-obtainable proximity measures, and the output was residential exposure to an air pollutant. We applied it to a case-study on NH3 pollution, and compared health effects and exposures estimated from NFIS, with those obtained from emission-dispersion models, and linear and non-linear regression proximity models, using 10-fold cross validation. The agreement between emission-dispersion and NFIS exposures was high (Root-mean-square error (RMSE) =0.275, correlation coefficient (r)=0.91) and resulted in similar health effect estimates. Linear models showed poor performance (RMSE=0.527, r=0.59), while non-linear regression models resulted in heterocedasticity, non-normality and clustered data. NFIS could be a useful tool for estimating individual air pollution exposures in epidemiological studies on large populations, when emission-dispersion data are not available. The tradeoff between simplicity and accuracy needs to be considered.

Thickness estimation of the subcutaneous fat using coaxial probe.

In this Letter, a non-invasive method for thickness estimation of the subcutaneous fat layer of abdominal wall is presented by using a coaxial probe. Fat layer has the highest impact on the averaged attenuation parameter of the abdominal wall due to its high thickness and low permittivity. The abdominal wall is modelled as a multi-layer medium and an analytical model for the probe is derived by calculation of its aperture admittance facing to this multi-layer medium. The performance of this model is then validated by a numerical simulation using finite-difference-time-domain (FDTD) analysis. Simulation results show the high impact of the probe dimension and fat layer thickness on the sensitivity of the measured permittivity. The authors further investigate this sensitivity by statistical analysis of the permittivity variations. Finally, measuring in different locations relative to the body surface is presented as a solution to estimate the fat layer thickness in the presence of uncertainty of model parameters.

In vivo and in situ measurement and modelling of intra-body effective complex permittivity.

Radio frequency tracking of medical micro-robots in minimally invasive medicine is usually investigated upon the assumption that the human body is a homogeneous propagation medium. In this Letter, the authors conducted various trial programs to measure and model the effective complex permittivity ε in terms of refraction ε', absorption ε″ and their variations in gastrointestinal (GI) tract organs (i.e. oesophagus, stomach, small intestine and large intestine) and the porcine abdominal wall under in vivo and in situ conditions. They further investigated the effects of irregular and unsynchronised contractions and simulated peristaltic movements of the GI tract organs inside the abdominal cavity and in the presence of the abdominal wall on the measurements and variations of ε' and ε''. They advanced the previous models of effective complex permittivity of a multilayer inhomogeneous medium, by estimating an analytical model that accounts for reflections between the layers and calculates the attenuation that the wave encounters as it traverses the GI tract and the abdominal wall. They observed that deviation from the specified nominal layer thicknesses due to non-geometric boundaries of GI tract morphometric variables has an impact on the performance of the authors' model. Therefore, they derived statistical-based models for ε' and ε'' using their experimental measurements.

Chronic exposure to odorous chemicals in residential areas and effects on human psychosocial health: dose-response relationships.

Perceived air pollution, including environmental odor pollution, is known to be an environmental stressor that affects individuals' psychosocial health and well-being. However, very few studies have been able to quantify exposure-response associations based on individual-specific residential exposures to a proxy gas and to examine the mechanisms underlying these associations. In this study, individual-specific exposures in non-urban residential environments during 2005-2010 on a gas released from animal biodegradable wastes (ammonia, NH3) were calculated by the Danish Eulerian long-range transport model and the local-scale transport deposition model. We used binomial and multinomial logistic regression and mediation analyses to examine the associations between average exposures and questionnaire-based data on psychosocial responses, after controlling for person-specific covariates. About 45% of the respondents were annoyed by residential odor pollution. Exposures were associated with annoyance (adjusted odds ratio [ORadj]=3.54, 95% confidence interval [CI]=2.33-5.39), health risk perception (ORadj=4.94; 95% CI=1.95-12.5) and behavioral interference (ORadj=3.28; 95% CI=1.77-6.11), for each unit increase in loge(NH3 exposure). Annoyance was a strong mediator in exposure-behavior interference and exposure-health risk perception relationships (81% and 44% mediation, respectively). Health risk perception did not play a mediating role in exposure-annoyance or exposure-behavioral interference relationships. This is the first study to provide a quantitative estimation of the dose-response associations between ambient NH3 exposures and psychosocial effects caused by odor pollution in non-urban residential outdoor environments. It further shows that these effects are both direct and mediated by other psychosocial responses. The results support the use of NH3 as a proxy gas of air pollution from animal biodegradable wastes in epidemiologic studies.

Bayesian-based localization of wireless capsule endoscope using received signal strength.

In wireless body area sensor networking (WBASN) applications such as gastrointestinal (GI) tract monitoring using wireless video capsule endoscopy (WCE), the performance of out-of-body wireless link propagating through different body media (i.e. blood, fat, muscle and bone) is still under investigation. Most of the localization algorithms are vulnerable to the variations of path-loss coefficient resulting in unreliable location estimation. In this paper, we propose a novel robust probabilistic Bayesian-based approach using received-signal-strength (RSS) measurements that accounts for Rayleigh fading, variable path-loss exponent and uncertainty in location information received from the neighboring nodes and anchors. The results of this study showed that the localization root mean square error of our Bayesian-based method was 1.6 mm which was very close to the optimum Cramer-Rao lower bound (CRLB) and significantly smaller than that of other existing localization approaches (i.e. classical MDS (64.2mm), dwMDS (32.2mm), MLE (36.3mm) and POCS (2.3mm)).

Perceived annoyance from environmental odors and association with atmospheric ammonia levels in non-urban residential communities: a cross-sectional study.

OBJECTIVE: Odor exposure is an environmental stressor that is responsible of many citizens complains about air pollution in non-urban areas. However, information about the exposure-response relation is scarce. One of the main challenges is to identify a measurable compound that can be related with odor annoyance responses. We investigated the association between regional and temporal variation of ammonia (NH3) concentrations in five Danish non-urban regions and environmental odor annoyance as perceived by the local residents. METHODS: A cross-sectional study where NH3 concentration was obtained from the national air quality monitoring program and from emission-dispersion modelling, and odor pollution perception from questionnaires. The exposure-response model was a sigmoid model. Linear regression analyses were used to estimate the model constants after equation transformations. The model was validated using leave-one-out cross validation (LOOCV) statistical method. RESULTS: About 45% of the respondents were annoyed by odor pollution at their residential areas. The perceived odor was characterized by all respondents as animal waste odor. The exposure-annoyance sigmoid model showed that the prevalence of odor annoyance was significantly associated with NH3 concentrations (measured and estimated) at the local air quality monitoring stations (p < 0.01,R2 = 0.99; and p < 0.05,R2 = 0.93; respectively). Prediction errors were below 5.1% and 20% respectively. The seasonal pattern of odor perception was associated with the seasonal variation in NH3 concentrations (p < 0.001, adjusted R2 = 0.68). CONCLUSION: The results suggest that atmospheric NH3 levels at local air quality stations could be used as indicators of prevalence of odor annoyance in non-urban residential communities.

Residential exposure to outdoor air pollution from livestock operations and perceived annoyance among citizens.

Epidemiological studies have shown that residential exposure to livestock odors can affect the health and wellbeing of rural citizens. However, exposure-response models for this relationship have not been developed. One of the main challenges is to identify a compound that can be used as proxy for livestock odor exposure. In this paper we developed models that describe the relationship between long-term averaged outdoor residential ammonia (NH(3)) exposures and livestock odor annoyance experienced by rural residents, and investigated person-related variables associated with annoyance responses. We used emission-based atmospheric dispersion modeling data to estimate household-specific outdoor concentrations and survey data to characterize the study subjects. Binomial and multinomial logistic regressions were used for model development. Residential NH(3) exposure was positively associated with moderate, high and extreme odor annoyance (adjusted odds ratio=10.59; 95% confidence interval: 1.35-83.13, for each unit increase in Log(e)NH(3) exposure). Specific characteristics of the exposed subjects (i.e., age, time per week spent at home, presence of children at home and job) act as co-determinants of odor annoyance responses. Predictive models showed classification accuracies of 67-72%. The results suggest that NH(3) exposure in the residential outdoor environment can be used as a predictor of livestock odor annoyance in population studies.

The effect on wireless sensor communication when deployed in biomass.

Wireless sensor networks (WSN) have been studied in a variety of scenarios over recent years, but work has almost exclusively been done using air as the transmission media. In this article some of the challenges of deploying a WSN in a heterogeneous biomass, in this case silage, is handled. The dielectric constant of silage is measured using an open-ended coaxial probe. Results were successfully obtained in the frequency range from 400 MHz to 4 GHz, but large variations suggested that a larger probe should be used for more stable results. Furthermore, the detuning of helix and loop antennas and the transmission loss of the two types of antennas embedded in silage was measured. It was found that the loop antenna suffered less from detuning but was worse when transmitting. Lastly, it is suggested that taking the dielectric properties of silage into account during hardware development could result in much better achievable communication range.