Multi-path Aggregation U-Net for Lung Segmentation in Chest Radiographs

Lung segmentation from chest X-ray images is a fundamental and crucial step for computer-aid diagnosis (CAD) system. Although many techniques for this problem have been proposed, it still remains as a challenge. Recently, Fully Convolutional Networks (FCNs) especially U-Net has been hugely successful for many image segmentation tasks. In this paper, we propose a revised variant of U-Net, specifically, we design two main components. The first component is multi-path dilated convolutions with different dilation rate to extract multi-scale features. It was used to replace the basic convolutions used in the original U-Net. The second component is skip connections with dense deep layer aggregation to further aggregate features across different scales. We perform extensive experiments on three publicly available datasets (in total 951 images). Our proposed method outperforms many other segmentation methods and achieves state-of-the-art segmentation performance (Dice’s coefficient of 96.5%, 97.9% and 96.7% on the three datasets, respectively).

Median Filter Aided CNN Based Image Denoising: An Ensemble Aprroach

Image denoising is a challenging research problem that aims to recover noise-free images from those that are contaminated with noise. In this paper, we focus on the denoising of images that are contaminated with additive white Gaussian noise. For this purpose, we propose an ensemble learning model that uses the output of three image denoising models, namely ADNet, DnCNN, and IRCNN, in the ratio of 2:3:6, respectively. The first model (ADNet) consists of Convolutional Neural Networks with attention along with median filter layers after every convolutional layer and a dilation rate of 8. In the case of the second model, it is a feed forward denoising CNN or DnCNN with median filter layers after half of the convolutional layers. For the third model, which is Deep CNN Denoiser Prior or IRCNN, the model contains dilated convolutional layers and median filter layers up to the dilated convolutional layers with a dilation rate of 6. By quantitative analysis, we note that our model performs significantly well when tested on the BSD500 and Set12 datasets.

A retrospective, observational, real-world evidence study to understand the clinical and obstetric characteristics and tolerability profile of women in labor managed with camylofin dihydrochloride injection

Background: To determine the clinical and obstetric characteristics and tolerability profile of pregnant women in the active phase of labor who were managed with Camylofin dihydrochloride injection.Methods: Retrospective data of 210 full-term pregnant women in the active phase of labor who were managed with Camylofin injection doses of 50 mg, 50+25 mg and 50+50 mg were considered in the study. The comparative effectiveness of 3 doses was evaluated using independent T-test and ANOVA at 5% level of significance.Results: The overall mean maternal age was 25.4 (±4.14) years with mean gestational age of 38.8 (±1.04) weeks. In total, 77.1% (n=162) of patients needed 50 mg dose of Camylofin injection for adequate cervical dilatation, and additional doses of 25 mg or 50 mg were required in 16.7% (n=35) and 6.2% (n=13), of patients, respectively to accelerate the labor. The mean cervical dilatation rates increasing dose viz 2.8 cm/hr, 4.1 cm/hr and 2.9 cm/hr, respectively. The adverse events were 14.8% (n=23) in 50 mg arm, 34.3% (n=12) in 50+25 arm and 69.0% (n=9) in 50+50 arm. Of the total, 34 events (50.0%) were related to Camylofin dihydrochloride injection, i.e. ADRs.The means of cervical dilation rate, active phase duration and total duration of labor were statistically significant (p-value <0.001) for 50 mg versus 50+25 mg.Conclusions: The study infers Camylofin injection usage with consideration of dose escalation in the routine clinical management of labor. Both mother and neonate had shown comparable tolerability profile across the three dosage arms with minimal events.

PDE5 Inhibitors in Type 2 Diabetes Cardiovascular Complications

Pharmacological inhibition of Phosphodiesterase type 5 (PDE5) proved its efficacy treating several pathological conditions, such as erectile dysfunction and pulmonary hypertension. Nowadays, its benefits on cardiovascular diseases are well documented, particularly in the treatment of type 2 diabetes (T2DM)-related cardiovascular complications. In this context, treatment of T2DM with PDE5 inhibitors, such as sildenafil, tadalafil or vardenafil ameliorates endothelial dysfunction both in patients and animal models through an augmented flow mediated dilation rate and an up-regulation of endothelial markers; it also reduces the inflammatory state by down-regulating inflammatory cytokines expression and improves diabetic cardiomyopathy and ischemia-reperfusion injury mainly through the activation of NO-cGMP-PKG pathway. The present review summarizes the state of art on PDE5 inhibition in the treatment of cardiovascular complications in T2DM.

Incremental Dilations Using CNN for Brain Tumor Classification

Brain tumor classification is a challenging task in the field of medical image processing. Technology has now enabled medical doctors to have additional aid for diagnosis. We aim to classify brain tumors using MRI images, which were collected from anonymous patients and artificial brain simulators. In this article, we carry out a comparative study between Simple Artificial Neural Networks with dropout, Basic Convolutional Neural Networks (CNN), and Dilated Convolutional Neural Networks. The experimental results shed light on the high classification performance (accuracy 97%) of Dilated CNN. On the other hand, Dilated CNN suffers from the gridding phenomenon. An incremental, even number dilation rate takes advantage of the reduced computational overhead and also overcomes the adverse effects of gridding. Comparative analysis between different combinations of dilation rates for the different convolution layers, help validate the results. The computational overhead in terms of efficiency for training the model to reach an acceptable threshold accuracy of 90% is another parameter to compare the model performance.

Balloon versus Amplatz for tract dilation in fluoroscopically guided percutaneous nephrolithotomy: a systematic review and meta-analysis

ObjectiveTo compare the safety and efficacy of balloon and Amplatz for tract dilation in fluoroscopically guided percutaneous nephrolithotomy (PCNL).MethodEMBASE, PUBMED, MEDLINE and the Cochrane Central Register of Controlled Trials were searched for pertinent studies up until 30 October 2019. Pooled effects were calculated as ORs with 95% CIs or mean differences (MD) with 95% CIs. Endpoints included postoperative decrease in haemoglobin, transfusion rate, complication rate, successful dilation rate, stone-free rate, fluoroscopy time, access time, total operation time and length of postoperative hospitalisation (LPH). Bonferroni’s correction was intercalated to reduce the likelihood of making a meta-analytical false positive.ResultsOne randomised controlled trial and five controlled clinical trials were included, which involved 1317 patients in total. We found a lower drop in postoperative haemoglobin for patients receiving balloon dilation compared with those in the Amplatz group (MD=−0.21, 95% CI −0.33 to 0.09, p=0.0005; Bonferroni correction a=0.005). Access time in the balloon group was also, on average, 2.61 min shorter than the Amplatz group (MD=−2.61, 95% CI −4.20 to 1.01, p=0.001; Bonferroni correction a=0.005). No significant differences were identified between the two dilation methods in terms of transfusion rate, complication rate, successful dilation rate, stone-free rate, fluoroscopy time, total operation time and LPH.ConclusionBalloon dilation is a safe and effective tract dilation technique for access creation during fluoroscopically guided PCNL. Both of methods have similar success rates although balloon dilation is associated with significantly less postoperative haemoglobin decline and shorter access time. Therefore, balloon dilation appears to be the superior tract dilation technique, but further confirmatory research is required to confirm these findings.

Anticipatory energization revealed by pupil and brain activity guides human effort-based decision making

An organism’s fitness is determined by how it chooses to adapt effort in response to challenges. Actual effort exertion correlates with activity in dorsomedial prefrontal cortex (dmPFC) and noradrenergic pupil dilation, but little is known about how these neurophysiological processes guide decisions about future efforts: They may either provide anticipatory energization helping to accept the challenge, or a cost representation weighted against expected rewards. Here we provide evidence for the former, by measuring pupil and fMRI brain responses while humans chose whether to exert efforts to obtain rewards. Pupil-dilation rate and dMPFC fMRI activity related to anticipated effort level, with stronger correlations when participants chose to accept the challenge. These choice-dependent effort representations were stronger in participants whose behavioral choices were more sensitive to effort. Our results identify a process involving the peripheral and central human nervous system that guides decisions to exert effort by simulating the required energization.

Rapid Brain Responses to Familiar vs. Unfamiliar Music – an EEG and Pupillometry study

Human listeners exhibit marked sensitivity to familiar music, perhaps most readily revealed by popular “name that tune” games, in which listeners often succeed in recognizing a familiar song based on extremely brief presentation. In this work, we used electroencephalography (EEG) and pupillometry to reveal the temporal signatures of the brain processes that allow differentiation between a familiar, well liked, and unfamiliar piece of music. In contrast to previous work, which has quantified gradual changes in pupil diameter (the so-called “pupil dilation response”), here we focus on the occurrence of pupil dilation events. This approach is substantially more sensitive in the temporal domain and allowed us to tap early activity with the putative salience network. Participants (N = 10) passively listened to snippets (750 ms) of a familiar, personally relevant and, an acoustically matched, unfamiliar song, presented in random order. A group of control participants (N = 12), who were unfamiliar with all of the songs, was also tested. We reveal a rapid differentiation between snippets from familiar and unfamiliar songs: Pupil responses showed greater dilation rate to familiar music from 100–300 ms post-stimulus-onset, consistent with a faster activation of the autonomic salience network. Brain responses measured with EEG showed a later differentiation between familiar and unfamiliar music from 350 ms post onset. Remarkably, the cluster pattern identified in the EEG response is very similar to that commonly found in the classic old/new memory retrieval paradigms, suggesting that the recognition of brief, randomly presented, music snippets, draws on similar processes.

Proximal aorta longitudinal strain predicts aortic root dilation rate and aortic events in Marfan syndrome

Aims Life expectancy in Marfan syndrome patients has improved thanks to the early detection of aortic dilation and prophylactic aortic root surgery. Current international clinical guidelines support the use of aortic root diameter as a predictor of complications. However, other imaging markers are needed to improve risk stratification. This study aim to ascertain whether proximal aorta longitudinal and circumferential strain and distensibility assessed by cardiac magnetic resonance (CMR) predict the aortic root dilation rate and aortic events in Marfan syndrome. Methods and results One hundred and seventeen Marfan patients with no previous aortic dissection, cardiac/aortic surgery, or moderate/severe aortic regurgitation were prospectively included in a multicentre protocol of clinical and imaging follow-up. At baseline, CMR was performed and proximal aorta longitudinal strain and ascending aorta circumferential strain and distensibility were obtained. During follow-up (85.7 [75.0–93.2] months), the annual growth rate of aortic root diameter was 0.62 ± 0.65 mm/year. Fifteen patients underwent elective surgical aortic root replacement and four presented aortic dissection. Once corrected for baseline clinical and demographic characteristics and aortic root diameter, proximal aorta longitudinal strain, but not circumferential strain and distensibility, was an independent predictor of the aortic root diameter growth rate (P = 0.001, P = 0.823, and P = 0.997, respectively), z-score growth rate (P = 0.013, P = 0.672, and P = 0.680, respectively), and aortic events (P = 0.023, P = 0.096, and P = 0.237, respectively). Conclusion Proximal aorta longitudinal strain is independently related to the aortic root dilation rate and aortic events in addition to aortic root diameter, clinical risk factors, and demographic characteristics in Marfan syndrome patients.