Bad Image Quality Research Articles

Patient Ability to Take Dermoscopic Follow-Up Images of Atypical Melanocytic Lesions With Smartphones: A Pilot Study

Introduction: Short-term teledermoscopic monitoring helps to distinguish early melanomas from nevi. As the incidence of melanoma is increasing, there are several benefits of patients taking their own dermoscopic images, but only a few previous studies have investigated the feasibility of this approach. Objectives: We sought to examine patient ability to take evaluable dermoscopic images of atypical melanocytic lesions in need of short-term monitoring. Methods: Patients were asked to take follow-up images in their homes using a borrowed dermoscope and their own smartphone. We investigated if the management decision differed when assessing follow-up images taken by patients compared to follow-up images taken by hospital staff. Lesions were rated as either changed, unchanged, or in need of further monitoring. In addition, image quality and patients’ attitudes towards taking dermoscopic follow-up images were studied. Results: Ninety-five patients with 132 lesions completed the study. Images taken by hospital staff were of better quality than images taken by patients (P<0.001). A total of 24 dermoscopic images taken by patients (18.2%) were of poor quality and considered unsuitable for assessment at follow-up. In the remaining 108 lesions, the management decision was concordant in 95 cases (88.0%). Most patients found the procedure to be easy to perform and 76.0% of patients answered that they preferred self-photography. Conclusions: Self-photography for teledermoscopic evaluation of atypical melanocytic lesions is feasible, but it results in worse image quality, which may lead to discordant evaluations. Dermoscopes used for this purpose need to be more user-friendly and maintain a higher technical standard.

Analyzing the image quality using a quantitative index for the robotic ultrasound probe maneuver system

This paper presents a quantitative index introduced, ‘clarity,’ which can address both the ultrasound probe's brightness and full contact states to indicate ultrasound image quality for the robotic ultrasound system. Furthermore, it evaluates its performance through an experiment, a comparative analysis, and a questionnaire. The index is calculated based on pixel statistics within the predefined region of interest. Experimental validation is conducted by implementing a robotic ultrasound system and performing experiments using two phantoms. Notably, the Results demonstrate the distinction of the visible difference in ultrasound images but also show that it is hard to classify the tiny difference. Additionally, a questionnaire was carried out to ask about the recognition of good image quality. The opinions are the same trends and patterns. The 53.4 clarity value was determined from the answers as the boundary between good and bad-quality images. The experiment results, and questionnaire findings suggest that the proposed clarity index could be a reliable tool for evaluating ultrasound image quality in robotic systems, offering insights for improving diagnostic accuracy and efficiency. This research provides a clear framework for assessing ultrasound image quality in robotic applications, paving the way for advancements in the efficacy and precision of ultrasound imaging techniques.

Internalizing and externalizing behaviors in school-aged children are related to state anxiety during magnetic resonance imaging

Magnetic resonance imaging (MRI) procedures often evoke anxiety in children. Further, anxious children may be less likely to participate in MRI research, leading to a possible selection bias, and may be more likely to move during image acquisition, resulting in lower image quality and possible information bias. Therefore, state anxiety is problematic for functional and structural MRI studies. Children with behavioral problems, such as internalizing and externalizing behaviors, may be more likely to experience state anxiety prior to and during MRI scanning. Therefore, our first aim was to investigate the relationship between internalizing/externalizing behavior and children’s MRI-related state anxiety. Our second aim was to investigate the relationship between internalizing and externalizing behaviors and MRI research participation. Our final aim was to investigate the effect of internalizing and externalizing behaviors as well as MRI-related anxiety on image quality in children. We included 1,241 six- to ten-year-old children who underwent a mock MRI. Afterward, if not too anxious, these children were scanned using a 3-Tesla GE Discovery MRI system (n = 1,070). Internalizing and externalizing behaviors were assessed with the child behavior checklist. State anxiety was assessed with a visual analog scale. Internalizing behaviors were positively associated with child state anxiety, as reported by the child, parent, and researcher. For state anxiety reported by the parent and researcher, this relationship was independent of externalizing behaviors. Externalizing behaviors were related to state anxiety as reported by the child, parent, and researcher, but this difference was not independent of internalizing behaviors, pointing toward a relationship via the shared variance with internalizing behaviors. Further, children with more internalizing and externalizing behaviors were less likely to participate in the actual MRI-scanning procedure. Lastly, MRI-related state anxiety, reported by the child and the researcher, was associated with worse image quality. These results underscore the potential for biases and methodological issues related to MRI-related state anxiety in children.

The Impact of Cataracts on the Measurement of Macular Choriocapillaris Flow Deficits Using Swept-Source OCT Angiography.

The impact of cataracts on the measurement of macular choriocapillaris flow deficits (CC FDs) was assessed by comparing the quantitative results before and after cataract surgery using an image quality algorithm developed for swept-source optical coherence tomography angiography (SS-OCTA) scans and a validated strategy for quantifying the CC FDs. SS-OCTA image quality scores and CC FDs measurements within the fovea-centered 1-mm, 3-mm, and 5-mm diameter circles were compared before and after cataract surgery. CC FDs changes in a modified Early Treatment Diabetic Retinopathy Study (ETDRS) grid were further investigated. Twenty-four eyes were studied. Overall image quality in all three circles was observed to improve significantly following the removal of cataracts (all P < 0.05). Although there was good repeatability in the measurements of CC FDs at both visits (intraclass correlation coefficients were over 0.95), significant decreases in CC FD measurements were observed after surgery within the 1-mm circle (P < 0.001) and the 3-mm circle (P = 0.011), but no changes were observed within the 5-mm circle (P = 0.509) or any of the quadrant sectors of the modified ETDRS grid (all P > 0.05). The presence of cataracts resulted in worse image quality and increased CC FD measurements within the fovea-centered 1-mm and 3-mm circles, with the 1-mm circle being impacted the most. The impaired detection of CC perfusion deficits within the central macula of cataract eyes needs to be appreciated when imaging the CC in phakic eyes, especially in clinical trials.

Development of fast scanning module with a novel bubble solution applied to scanning acoustic microscopy system for industrial nondestructive inspection

Scanning acoustic microscopy (SAM) system is a powerful nondestructive instrument owing to its capability to provide internal information and defect positions inside a material. In industrial applications of SAM, the scanning time plays an important role in enhancing efficient inspection of the product line. Several studies have used the traditional SAM system, which develops based on linear motor to inspect industrial samples, but the inspection time remained relatively long and cost-prohibitive. Herein, we reported a low-cost fast SAM (FSAM) system that provided the image results in a short time while maintaining their high resolution. In this design, FSAM fast scanning module (FSM) was developed by exploiting the slider-crank mechanism, which was optimized for a specific product to substantially reduce the inspection time. During the scanning process, bubbles were generated due to the rapid movement of transducer into the water, namely the bubble cavitation. The bubbles restricted the ultrasound wave propagation, which resulted in the bad image quality. The bubble cavitation phenomenon was examined using the incompressible flow theory to investigate the bubble inception, which was defined based on the pressure value around transducer. The bubbles appeared in areas where the pressure less than the vapor pressure. Using the OpenFOAM to analyze the pressure value, the bubble problem was solved by a novel solution that used a bubble reduction plate attaching to the transducer. The coin and aluminum samples with known dimensions and internal structure were prepared to scan using the FSAM system, which validated the simulation results and FSAM capabilities in providing good images with internal information and accurate measurements. Finally, FSAM system was designed and developed to successfully inspect industrial samples in a short time, such as an integrated circuit chip, printed circuit board, welded sheets, and silicon wafer. Using the FSAM system to scan welded sheets, the scanning time were reduced by approximately 77% compared to the traditional SAM system. These results demonstrate that the FSAM system is a potential instrument for industrial nondestructive inspection.

Left Atrial Function as a Predictor for Postoperative Atrial Fibrillation

Background: One of the most frequent complications following heart surgery is atrial fibrillation (AF). The most popular diagnostic procedure for evaluating atrial function is echocardiography, however it has certain drawbacks. Originally, 2D echocardiography has been used to measure volumes to determine left atrial function. Objective: to examine the relationship between the development of post-operative AF following isolated CABG and preoperative evaluation of LA function using 2D echocardiography and left atrium 2D speckle tracking strain echocardiography. Patients and Methods: A set of 149 consecutive patients enrolled in a prospective observational study, they admitted to cardio-thoracic surgery department for elective isolated coronary artery bypass grafting surgery, during July 2018 to June 2019. 22 patients were excluded from the study due to bad image quality. Results: Readings of speckle tracking data showed significant less LA reservoir strain (OR 1.75, 95% CI: 0.65-4.69, P≤0001), LA conduit strains (OR 0.6, 95% CI: 0.22-1.62, P=0.31) and LA contractile strain (OR 0.65, 95% CI: 0.24-1.77, P=0.40) in POAF (+). Remaining parameters were non-significant. Also, Age (P=0.03), LA diameter (P=0.04), and LAVI (P=0.03) were the only factors that were identified as potential predictors of POAF in multivariate logistic regression analysis. Conclusion: we concluded that, age, LA size and LAVI are significantly associated with the occurrence of POAF in our patients.

Low dose of contrast agent and low radiation liver computed tomography with deep-learning-based contrast boosting model in participants at high-risk for hepatocellular carcinoma: prospective, randomized, double-blind study.

To investigate the image quality and lesion conspicuity of a deep-learning-based contrast-boosting (DL-CB) algorithm on double-low-dose (DLD) CT of simultaneous reduction of radiation and contrast doses in participants at high-risk for hepatocellular carcinoma (HCC). Participants were recruited and underwent four-phase dynamic CT (NCT04722120). They were randomly assigned to either standard-dose (SD) or DLD protocol. All CT images were initially reconstructed using iterative reconstruction, and the images of the DLD protocol were further processed using the DL-CB algorithm (DLD-DL). The primary endpoint was the contrast-to-noise ratio (CNR), the secondary endpoint was qualitative image quality (noise, hepatic lesion, and vessel conspicuity), and the tertiary endpoint was lesion detection rate. The t-test or repeated measures analysis of variance was used for analysis. Sixty-eight participants with 57 focal liver lesions were enrolled (20 with HCC and 37 with benign findings). The DLD protocol had a 19.8% lower radiation dose (DLP, 855.1 ± 254.8mGy·cm vs. 713.3 ± 94.6mGy·cm, p = .003) and 27% lower contrast dose (106.9 ± 15.0mL vs. 77.9 ± 9.4mL, p < .001) than the SD protocol. The comparative analysis demonstrated that CNR (p < .001) and portal vein conspicuity (p = .002) were significantly higher in the DLD-DL than in the SD protocol. There was no significant difference in lesion detection rate for all lesions (82.7% vs. 73.3%, p = .140) and HCCs (75.7% vs. 70.4%, p = .644) between the SD protocol and DLD-DL. DL-CB on double-low-dose CT provided improved CNR of the aorta and portal vein without significant impairment of the detection rate of HCC compared to the standard-dose acquisition, even in participants at high risk for HCC. • Deep-learning-based contrast-boosting algorithm on double-low-dose CT provided an improved contrast-to-noise ratio compared to standard-dose CT. • The detection rate of focal liver lesions was not significantly differed between standard-dose CT and a deep-learning-based contrast-boosting algorithm on double-low-dose CT. • Double-low-dose CT without a deep-learning algorithm presented lower CNR and worse image quality.

Low dose pediatric chest computed tomography on a photon counting detector system – initial clinical experience

BackgroundWith the clinical release of a photon counting detector-based computed tomography (CT) system, the potential benefits of this new technology need to be evaluated clinically. Literature concerning this new generation of detector is sparse, especially in the field of pediatric radiology. Therefore, this study outlines our initial experience with ultra-low dose chest CT imaging on the new photon counting CT system.Materials and methodsA pediatric phantom (1-year old, CIRS ATOM phantom, model 704 [CIRS-computerized imaging reference system, Norfolk, VA]) was scanned at different dose levels and different image quality levels to define a protocol for clinical examinations. Next, 20 consecutive pediatric non-contrast ultra-low dose chest CT examinations were evaluated for radiation dose and diagnostic image quality using a 4-point Likert-scale—1 = excellent, 4 = bad image quality—by two radiologists in a consensus reading. This retrospective analysis was approved by the local research ethics committee.ResultsChest CT examinations performed at ultra-low radiation dose (effective dose 0.19 ± 0.07 mSv; size-specific dose estimate 0.45 ± 0.14 mGy) in pediatric patients ages (2.6 ± 1.8 years) show good to excellent image quality for lung structures (1.4 ± 0.4) and moderate image quality for soft tissue structures (2.8 ± 0.2).ConclusionPediatric ultra-low dose chest CT examinations are feasible with the new generation photon counting detector-based CT system. The benefits of this technology must be evaluated for pediatric patients from the outset.

Open-set face identification with automatic detection of out-of-distribution images

One of main issues in face identification is the lack of training data of specific type (bad quality image, varying scale or illumination, children/old people faces, etc.). As a result, the recogni-tion accuracy may be low for input images which are not similar to the majority of images in the dataset used to train the feature extractor. In this paper, we propose that this issue is dealt with by the automatic detection of such out-of-distribution data based on the addition of a preliminary stage of their automatic rejection using a special convolutional network trained using a set of rare data collected using various transformations. To increase the computational efficiency, the decision about the presence of a rare image is made on the basis of the same face descriptor that is used in the classifier. Experimental research confirmed the accuracy improvement of the proposed approach for several datasets of faces and modern neural network descriptors.

Evaluation of histogram equalization and contrast limited adaptive histogram equalization effect on image quality and fractal dimensions of digital periapical radiographs.

This study aims to evaluate the effects of histogram equalization (HE) and contrast limited adaptive histogram equalization (CLAHE) on periapical images and fractal dimensions in the periapical region. In this cross-sectional study, digital periapical images were selected from the archive of Dentistry School of Isfahan University of Medical Sciences. The radiographs were taken from mandibular and maxillary anterior single root teeth with healthy root and periodontium. After applying HE and CLAHE algorithms to images, two radiologists evaluated the quality of apex detection from using a 5-point Likert scale (from 5 for very good image quality to 1 for very bad image quality). Afterward, all the images were imported to the ImageJ application, and the region of interest (ROI) was specified as the region between the two central incisors. The fractal box-counting method was used to determine fractal dimensions (FD) values. Nonparametric Wilcoxon-Friedman test, Intraclass Correlation Coefficient test, T-test, and Pair T-test were performed as statistical analysis (α = 0.05). Fifty-three radiographs were analyzed and the image quality assessments were significantly different between raw images and images after performing HE, CLAHE (p value < 0.001), and using CLAHE algorithm significantly increases image quality assessments more than HE (p value = 0.009). There was a significant difference in FD values for images after applying CLAHE and HE compared to raw images (p value < 0.001), and HE decreased the FD value significantly more than CLAHE (p value = 0.019). Employing CLAHE and HE algorithm via OpenCV python library improves the periapical image quality, which is more significant using the CLAHE algorithm. Moreover, applying CLAHE and HE reduces trabecular bone structure detection and FD values in periapical images, especially in HE.

The Use of Datasets of Bad Quality Images to Define Fundus Image Quality.

Screening programs for sight-threatening diseases rely on the grading of a large number of digital retinal images. As automatic image grading technology evolves, there emerges a need to provide a rigorous definition of image quality with reference to the grading task. In this work, on two subsets of the CORD database of clinically grad able and matching non-grad able digital retinal images, a feature set based on statistical and on task-specific morphological features has been identified. A machine learning technique has then been demonstrated to classify the images as per their clinical gradeability, offering a proxy for a rigorous definition of image quality.

Deep learning-based quality-controlled spleen assessment from ultrasound images

ObjectiveSplenomegaly (abnormal splenic enlargement) is a potentially life-threatening condition that occurs in a range of clinical scenarios, including in patients suffering from Sickle cell disease (SCD). Therefore, spleen size assessments from ultrasound imaging are commonly performed in SCD clinics, and typically involve measuring the length of the spleen. However, the current workflow is prone to intra- and inter-observer variability and is dependent on the experience of the sonographer. Our objective was to automate the spleen length measurement process. MethodsTwo deep learning-based approaches were investigated to achieve automated spleen length measurement from ultrasound images. One is a segmentation-based approach, where we trained a modified U-Net to obtain a spleen segmentation and then applied post-processing to measure the spleen length from the segmentation. The second approach is based on direct regression of spleen length. We also incorporated a quality control (QC) model to help less experienced sonographers ensure the quality of ultrasound images before measurement. ResultsOur best model (segmentation-based approach) reached a mean percentage length error (MPLE) of 4.58% on good quality images, which is within the range of human expert inter-observer variability (5.78%). After including bad quality images, the incorporation of the QC step resulted in a significant reduction in MPLE (from 5.76% to 4.88%). ConclusionAutomated, quality-controlled spleen length measurement from ultrasound has been achieved with human-level accuracy. SignificanceThis proposed framework has the potential to assist in making robust and accurate assessments of the spleen, especially in settings where there is a lack of experienced sonographers.

Acoustic-Field Beamforming-Based Generalized Coherence Factor for Handheld Ultrasound

Handheld ultrasound devices have been widely used for diagnostic applications. The use of the acoustic-field beamforming (AFB) method has been proposed for handheld ultrasound to reduce electricity consumption and avoid battery and unwanted heat issues. However, the image quality, such as the contrast ratio and contrast-to-noise-ratio, are poorer with this technique than with the conventional delay-and-sum method. To address the problems associated with the worse image quality in AFB imaging, in this paper we propose the use of an AFB-based generalized coherence factor (GCF) technique, in which the GCF weighting developed for adaptive beamforming is extended to AFB. Simulation data, experimental results, and in vivo testing verified the efficacy of our proposed AFB-based GCF technique.

Performance of deep learning technology for evaluation of positioning quality in periapical radiography of the maxillary canine

ObjectivesThe aim of the present study was to create and test an automatic system for assessing the technical quality of positioning in periapical radiography of the maxillary canines using deep learning classification and segmentation techniques.MethodsWe created and tested two deep learning systems using 500 periapical radiographs (250 each of good- and bad-quality images). We assigned 350, 70, and 80 images as the training, validation, and test datasets, respectively. The learning model of system 1 was created with only the classification process, whereas system 2 consisted of both the segmentation and classification models. In each model, 500 epochs of training were performed using AlexNet and U-net for classification and segmentation, respectively. The segmentation results were evaluated by the intersection over union method, with values of 0.6 or more considered as success. The classification results were compared between the two systems.ResultsThe segmentation performance of system 2 was recall, precision, and F measure of 0.937, 0.961, and 0.949, respectively. System 2 showed better classification performance values than those obtained by system 1. The area under the receiver operating characteristic curve values differed significantly between system 1 (0.649) and system 2 (0.927).ConclusionsThe deep learning systems we created appeared to have potential benefits in evaluation of the technical positioning quality of periapical radiographs through the use of segmentation and classification functions.

Perbaikan Citra Menggunakan Metode Contrast Stretching

Contrasting images that are not good because they are too bright or too dark cannot provide good information. Therefore, a method is needed to improve the image quality, so that the information in the image can be conveyed properly. Contrast stretching is one of the methods for improving image quality. With this method is expected to produce a new image that is better. The purpose of this research is to apply contrast stretching method to an application or software that can be used to improve image quality. Data used in this study in the form of grayscale image data and RGB imagery (true color), with the format . BMP or .JPG, while the application development uses the Matlab programming language.The results of the study, contrast stretching method can be used to repair image that affects bad or poor image quality such as too bright / dark image, less sharp image, blurry, and so on. Contrast stretching method can also be used to improve image enhancement by leveling the histogram that was collected in an area, so that the information contained in the image is more clearly visible compared to the original image.

Retinal image quality assessment using transfer learning: Spatial images vs. wavelet detail subbands

Retinal image quality assessment (RIQA) is essential to assure that images used for medical analysis are of sufficient quality for reliable diagnosis. A modified VGG16 network with transfer learning is introduced in order to classify retinal images into good or bad quality images. Both spatial and wavelet detail subbands are compared as inputs to the modified VGG16 network. Three public retinal image datasets captured with different imaging devices are used, both individually and collectively. Superior performance was attained by the modified VGG16 network, where accuracies in the range of 99–100% were achieved regardless of whether retinal images from the same or different sources were considered and whether the spatial or wavelet images were used. The implemented RIQA algorithm was also found to outperform other RIQA deep learning algorithms from literature by 1.5–10% and to achieve accuracies that are up to 32% higher than traditional RIQA methods for the same dataset.

Inter- and Intraobserver Variation in the Assessment of Preoperative Colostograms in Male Anorectal Malformations: An ARM-Net Consortium Survey.

Aim: Male patients with anorectal malformations (ARM) are classified according to presence and level of the recto-urinary fistula. This is traditionally established by a preoperative high-pressure distal colostogram that may be variably interpreted by different surgeons. The aim of this study was to evaluate the inter- and intraobserver variation in the assessment by pediatric surgeons of preoperative colostograms with respect to the level of the recto-urinary fistula.Materials and Methods: Sixteen pediatric surgeons from 14 European centers belonging to the ARM-Net Consortium twice scored 130 images of distal colostograms taken in sagittal projection at a median age of 66 days of life (range: 4–1,106 days). Surgeons were asked to classify the fistula in bulbar, prostatic, bladder-neck, no fistula, and “unclear anatomy” example. Their assessments were compared with the intraoperative findings (kappa) for two scoring rounds with an interval of 6 months (intraobserver variation). Agreement among the surgeons' scores (interobserver variation) was also calculated using Krippendorff's alpha. A kappa over 0.75 is considered excellent, between 0.40 and 0.75 fair to good, and below 0.40 poor. Surgeons were asked to score the images in “poor” and “good” quality and to provide their years of experience in ARM treatment.Results: Agreement between the image-based rating of surgeons and the intraoperative findings ranges from 0.06 to 0.45 (mean 0.31). Interobserver variation is higher (Krippendorff's alpha between 0.40 and 0.45). Years of experience in ARM treatment does not seem to influence the scoring. The mean intraobserver variation between the two rounds is 0.64. Overall, the quality of the images is considered poor. Images categorized as having a good quality result in a statistically significant higher kappa (mean: 0.36 and 0.37 in the first and second round, respectively) than in the group of bad-quality images (mean: 0.25 and 0.23, respectively).Conclusions: There is poor agreement among experienced pediatric colorectal surgeons on preoperative colostograms. Techniques and analyses of images need to be improved in order to generate a homogeneous series of patients and make comparison of outcomes reliable.

DR|GRADUATE: Uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images

Diabetic retinopathy (DR) grading is crucial in determining the adequate treatment and follow up of patient, but the screening process can be tiresome and prone to errors. Deep learning approaches have shown promising performance as computer-aided diagnosis (CAD) systems, but their black-box behaviour hinders clinical application. We propose DR|GRADUATE, a novel deep learning-based DR grading CAD system that supports its decision by providing a medically interpretable explanation and an estimation of how uncertain that prediction is, allowing the ophthalmologist to measure how much that decision should be trusted. We designed DR|GRADUATE taking into account the ordinal nature of the DR grading problem. A novel Gaussian-sampling approach built upon a Multiple Instance Learning framework allow DR|GRADUATE to infer an image grade associated with an explanation map and a prediction uncertainty while being trained only with image-wise labels. DR|GRADUATE was trained on the Kaggle DR detection training set and evaluated across multiple datasets. In DR grading, a quadratic-weighted Cohen's kappa (κ) between 0.71 and 0.84 was achieved in five different datasets. We show that high κ values occur for images with low prediction uncertainty, thus indicating that this uncertainty is a valid measure of the predictions' quality. Further, bad quality images are generally associated with higher uncertainties, showing that images not suitable for diagnosis indeed lead to less trustworthy predictions. Additionally, tests on unfamiliar medical image data types suggest that DR|GRADUATE allows outlier detection. The attention maps generally highlight regions of interest for diagnosis. These results show the great potential of DR|GRADUATE as a second-opinion system in DR severity grading.

Deep Neural Networks for Chronological Age Estimation From OPG Images.

Chronological age estimation is crucial labour in many clinical procedures, where the teeth have proven to be one of the best estimators. Although some methods to estimate the age from tooth measurements in orthopantomogram (OPG) images have been developed, they rely on time-consuming manual processes whose results are affected by the observer subjectivity. Furthermore, all those approaches have been tested only on OPG image sets of good radiological quality without any conditioning dental characteristic. In this work, two fully automatic methods to estimate the chronological age of a subject from the OPG image are proposed. The first (DANet) consists of a sequential Convolutional Neural Network (CNN) path to predict the age, while the second (DASNet) adds a second CNN path to predict the sex and uses sex-specific features with the aim of improving the age prediction performance. Both methods were tested on a set of 2289 OPG images of subjects from 4.5 to 89.2 years old, where both bad radiological quality images and images showing conditioning dental characteristics were not discarded. The results showed that the DASNet outperforms the DANet in every aspect, reducing the median Error (E) and the median Absolute Error (AE) by about 4 months in the entire database. When evaluating the DASNet in the reduced datasets, the AE values decrease as the real age of the subjects decreases, until reaching a median of about 8 months in the subjects younger than 15. The DASNet method was also compared to the state-of-the-art manual age estimation methods, showing significantly less over- or under-estimation problems. Consequently, we conclude that the DASNet can be used to automatically predict the chronological age of a subject accurately, especially in young subjects with developing dentitions.

Cerebral microbleeds prevalence and risk factors from UK biobank with 3.0 T SWI sequence

To identify CMBs' prevalence and its risk factors assessed by informed criteria in a large population-based individuals from UK Biobank. 9066 subjects at mean age of 55.5 years (SD 7.4 years) were recruited. Brain susceptibility weighted imaging(SWI) data were acquired from 3.0 T scanner. 223 subjects with incomplete or bad imaging quality were excluded. Age, follow-up years, sex, education, stroke, intracerebral hemorrhage, myocardial infarction, diabetes, ever-smoke, blood pressure, body mass index(BMI), medication use, physical activity, APOE4 status and diet preference were included. The Microbleed Anatomical Rating Scale(MARS) was used to assess CMBs.We used unpaired two-samples Welch's t-test for continuous variables and Mann-Whitney test for ranked variables. Two multiple generalized linear models were evaluated: model 1, each risk factor with age, gender and follow-up years taken into account; model 2, statistically significant risk factors from model 1 to be reentered. All statistical analyses were performed using R. 8160 subjects were included (47.27% male). CMBs prevalence was 7.01%, mostly lobar(439 subjects). Adults with CMB were older, less educated, with higher hypertensive status, less BMI and more APOE4 positive presence. The model 2 showed that age, higer BMI and APOE4 were significantly associated with overall CMBs presence; BMI and APOE4 were independently related with lobar CMBs; Blood pressure and ever-smoke were associated with deep group; Dyslipidemia and lamb take were independent predictors of infratentorial CMBs. Each CMBs subgroup has its separate risk factors. More attention should be paid for earlier prevention of CMBs.