Varietal influence on bioactive compounds and antioxidant activity in chilies during development stages.

Numerous cultivars of chili are grown in Bangladesh for their nutritional and sensory attributes, serving as both spices and food items. Among many, indigenous chili cultivars in Bangladesh include Sada Akshi, Kajini, Dhani, and Naga are the important ones. The functional qualities of chili peppers are attributed to the plentiful presence of bioactive substances. Consequently, this study aimed to determine the variations in bioactive compounds, antioxidant activities, and hotness among the pre-mature, mature, pre-ripening, and ripening stages of four distinct chili cultivars. Four different cultivars of chilis at four different maturity stages were collected and analyzed for their antioxidant and bioactive profiles. The findings of the research revealed that all chili varieties exhibited a notable range of vitamin C concentration, ranging from 1.67 to 8.45 mg/g FW during the maturity stages. The values of TPC, TFC, total carotenoids, and chlorophyll a and b ranged from 16.68 to 46.76 mg GAE/g, 2.80-8.53 mg QE/g, 4.31-85.79 µg/g DW, 2.83-15.54 and 0.74-5.66 µg/g DW on a dry weight basis, respectively. The antioxidant activity was assessed using the FRAP and the DPPH scavenging assay and the values ranged from 142.62 to 311.03 mM Fe (II) Equivalent/100g DW and 216.36-329.52 µM Trolox Equivalent/g DW, respectively. The content of vitamin C, TPC, total carotenoids, and chlorophyll b was increased with the stages of development. The hotness of chili also increased with the development stages. However, the antioxidant activity fluctuated during the development stages of chili. Furthermore, the study incorporated the evaluation of physical parameters, such as height, weight, and color attributes concerning chilies. The Naga variety of chili demonstrated the highest level of efficacy when compared to other varieties. The nutritional and physicochemical information of the different cultivars of chili in this study might be useful to the breeders, spice processors, and consumers for desired size, taste, and hotness with health-promoting bioactive compounds, eventually for determining the harvest time.

Gelatin/EGDE Ultrafine Composite Fibers Reinforced with 3D Spacer Fabric as Bicomponent Scaffolds for Tissue Engineering.

Protein-based ultrafine fibrous scaffolds can mimic the native extracellular matrices (ECMs) with regard to the morphology and chemical composition but suffer from poor mechanical and wet stability. As a result, cells cannot get a true three-dimensional (3D) environment as they find in native ECMs. In this study, an epoxide, ethylene glycol diglycidylether (EGDE), with high reactivity to active hydrogen is introduced to gelatin solution, serving as an effective cross-linker. The gelatin/EGDE 3D-ultrafine (∼500 nm in diameter) fibrous composite scaffolds are made by an ultralow-concentration phase separation technique (ULCPS). The effects of the polymer content and modification conditions on the morphology and wet stability of the constructs are investigated. It is revealed that ultrafine fibers with 3D random orientation could be formed at low concentrations (0.01, 0.05, and 0.1 wt %, respectively). The wet stability of the constructs could be effectively improved by introducing EGDE into the gelatin system. The shrinkage is reduced to merely 2.14% after the modification at 120 °C for 2 h and could be maintained for up to 3 days. In order to improve the compression properties, the same technique is utilized with the presence of a poly(lactic acid) (PLA) spacer fabric to produce a bicomponent scaffold. The mechanical property and cell viability of the bicomponent scaffolds are investigated, and it is found that cells could enter deep inside and orient themselves randomly at the central area of the bicomponent scaffold. The modification and design approach presented in this study has the potential to provide various protein-based ultrafine fibrous biomaterials for a variety of biomedical applications.

Exploring the nutraceutical potential: Evaluating the nutritional and bioactive functions of five pomelo fruit varieties in Bangladesh.

Pomelo (Citrus maxima), the largest citrus fruit, provides a variety of nutrients that have several health benefits, including antioxidant and antidiabetic functions. Antioxidants help combat oxidative stress by neutralizing reactive oxygen species (ROS) and reducing cellular damage. On the other hand, antidiabetic properties involve mechanisms such as enhancing insulin secretion, improving insulin sensitivity, inhibiting carbohydrate digestion and absorption, and regulating glucose metabolism. However, there is a lack of data on the comparative analysis of the physicochemical composition, bioactive properties, and antidiabetic effects of pomelo fruits grown in Bangladesh. To address this issue, the most common and popular high-yielding five cultivars of pomelo fruits grown in Bangladesh including LOCAL, BARI-2 (BARI: Bangladesh Agricultural Research Institute, Batabi Lebu-2), BARI-3, BARI-4, and BARI-6 were evaluated concerning proximate, minerals, and physicochemical properties with their antidiabetic and antioxidant properties. Research has revealed that all pomelo varieties contained a significant amount of proximate compositions and major minerals (Ca, Mg, K, Na, and Fe). The highest juice yield (75.37 ± 0.33 %), vitamin C content (79.56 ± 2.26 mg/100 mL of fresh juice), and carotenoid content (919.33 ± 0.62 µM ß-Carotene Equivalent/g DM) were found in BARI-3 pomelo fruit and adhered to the sequence (p < 0.05): BARI-3 > LOCAL > BARI-4 > BARI-6 > BARI-2; BARI-3 > LOCAL > BARI-2 > BARI-4 > BARI-6, and BARI-3 > BARI-2 > BARI-6 > LOCAL > BARI-4, respectively. The anthocyanin content and inhibitory activity of α-glucosidase were found to be at their peak in the BARI-2 pomelo variety and the values were 50.65 ± 2.27 µg cyanidin 3-glucoside equivalents/100 g DM and 85.57 ± 0.00 µM acarbose equivalents/g DM, respectively. BARI-3 pomelo variety showed highest DPPH antioxidant capacity (170.47 ± 0.01 µM Trolox equivalents/g DM), while the BARI-6 pomelo variety exhibited the highest total phenolic content (6712.30 ± 1.84 µg gallic acid equivalents/g DM), and ferric-reducing antioxidant power activity (183.16 ± 0.01 µM Fe(II) equivalents/g DM). Therefore, this study explores the nutritional value and bioactivity of five popular pomelo varieties in Bangladesh, offering valuable insights for utilizing high-value citrus resources and understanding their health-promoting functions.

Trends and challenges of fruit by-products utilization: insights into safety, sensory, and benefits of the use for the development of innovative healthy food: a review.

A significant portion of the human diet is comprised of fruits, which are consumed globally either raw or after being processed. A huge amount of waste and by-products such as skins, seeds, cores, rags, rinds, pomace, etc. are being generated in our homes and agro-processing industries every day. According to previous statistics, nearly half of the fruits are lost or discarded during the entire processing chain. The concern arises when those wastes and by-products damage the environment and simultaneously cause economic losses. There is a lot of potential in these by-products for reuse in a variety of applications, including the isolation of valuable bioactive ingredients and their application in developing healthy and functional foods. The development of novel techniques for the transformation of these materials into marketable commodities may offer a workable solution to this waste issue while also promoting sustainable economic growth from the bio-economic viewpoint. This approach can manage waste as well as add value to enterprises. The goal of this study is twofold based on this scenario. The first is to present a brief overview of the most significant bioactive substances found in those by-products. The second is to review the current status of their valorization including the trends and techniques, safety assessments, sensory attributes, and challenges. Moreover, specific attention is drawn to the future perspective, and some solutions are discussed in this report.

Development of eco-friendly biofilms by utilizing microcrystalline cellulose extract from banana pseudo-stem.

Banana pseudo-stem, often considered as an underutilized plant part was explored as a potential reinforced material to develop an eco-friendly biofilm for food packaging applications. In this study, Microcrystalline cellulose (MCC) was extracted from banana pseudo-stem by alkali and acid hydrolysis treatment. The extracted MCC was used as a reinforced material in different concentrated polyvinyl alcohol (PVA) matrix alone as well as both PVA and Carboxymethyl Cellulose (CMC) matrix to develop biofilm by solvent casting method. The synthesized MCC powder was characterized by scanning electron microscope to ensure its microcrystalline structure and to observe surface morphology. The biofilms composed of MCC, PVA, and CMC were assessed through Fourier-transform infrared spectroscopy (FTIR), mechanical properties, water content, solubility, swelling degree, moisture barrier property (Water Vapor Permeability - WVP), and light barrier property (Light Transmission and Transparency). The FTIR analysis showed the rich bonding between the materials of the biofilms. The film incorporating a combination of PVA, CMC, and MCC (S6) exhibited the highest tensile strength at 26.67 ± 0.152 MPa, making it particularly noteworthy for applications in food packaging. MCC incorporation increased the tensile strength. The WVP content of the films was observed low among the MCC-induced films which is parallel to other findings. The lowest WVP content was showed by 1% concentrated PVA with MCC (S4) (0.223 ± 0.020 10-9 g/Pahm). The WVP content of S6 film was also considerably low. MCC-incorporated films also acted as a good UV barrier. Transmittance of the MCC induced films at UV range were observed on average 38% (S2), 36% (S4) and 6% (S6) which were almost 6% lower than the control films. The S6 film demonstrated the lowest swelling capacity (1.42%) and water content, indicating a significantly low solubility of the film. The film formulated with mixing of PVA, CMC and MCC (S6) was ahead in terms of food packaging characteristics than other films. Also, the outcomes of this study point out that MCC can be a great natural resource for packaging applications and in that regard, banana pseudo-stem proves to be an excellent source for waste utilization.

Development of functional noodles by encapsulating mango peel powder as a source of bioactive compounds.

Antioxidant compounds such as phenolics and carotenoids scavenge reactive oxygen species and protect against degenerative diseases such as cancer and cardiovascular disease when used as food additives or supplements. Mango peel is a by-product of mango which is a good source of bioactive substances such as phytochemicals, antioxidants, and dietary fibers. Unfortunately, the study on mango peel as a potential food additive is very limited. Accordingly, the present study aimed to develop functional noodles through extrusion technology with the encapsulation of mango peel powder as a natural source of bioactive compounds. First, mango peel powder (MPP) was prepared and incorporated during the mixing of ingredients before noodles formation at three different levels (2.5, 5 and 7.5 %). Afterward, the noodles were studied to determine how the encapsulated MPP affects the proximate composition, physicochemical characteristics, polyphenols, carotenoids, anthocyanin, antioxidant and antidiabetic activity, and sensory characteristics. The noodles exhibited a dose-dependent relationship in the content of bioactive components and functional activities with the encapsulation of MPP levels. A significantly (p 0.05) higher value was noticed in 7.5 % of MPP-encapsulated noodles than in any level of MPP encapsulation in noodles. The fiber and protein contents in the MPP-encapsulated noodles were increased by about 0-1.22 % and 0-3.16 %, respectively. However, noodles' color index and water absorption index were decreased with the level of MPP encapsulation. The cooking loss of noodles increased from 4.64 to 5.17, 6.49, and 7.32 %, whereas the cooked weight decreased from 35.11 to 34.40, 33.65, and 33.23 % with 2.5, 5.0, and 7.5 % of MPP encapsulation, respectively. However, MPP was stable during storage of noodles exhibiting higher phenolic content and antioxidant activity than control samples. The sensory evaluation showed that MPP-encapsulated noodles at levels 2.5 and 5 % had approximately similar overall acceptability values with the control sample. As a result of the findings, it appears that adding MPP up to 5 % to noodles improves their nutritional quality without changing their cooking, structural, or sensory aspects. Therefore, mango peel powder can be a potential cheap source for the development of functional noodles and food ingredients.

Inpainting surgical occlusion from laparoscopic video sequences for robot-assisted interventions.

Purpose: Medical technology for minimally invasive surgery has undergone a paradigm shift with the introduction of robot-assisted surgery. However, it is very difficult to track the position of the surgical tools in a surgical scene, so it is crucial to accurately detect and identify surgical tools. This task can be aided by deep learning-based semantic segmentation of surgical video frames. Furthermore, due to the limited working and viewing areas of these surgical instruments, there is a higher chance of complications from tissue injuries (e.g., tissue scars and tears). Approach: With the aid of digital inpainting algorithms, we present an application that uses image segmentation to remove surgical instruments from laparoscopic/endoscopic video. We employ a modified U-Net architecture (U-NetPlus) to segment the surgical instruments. It consists of a redesigned decoder and a pre-trained VGG11 or VGG16 encoder. The decoder was modified by substituting an up-sampling operation based on nearest-neighbor interpolation for the transposed convolution operation. Furthermore, these interpolation weights do not need to be learned to perform upsampling, which eliminates the artifacts generated by the transposed convolution. In addition, we use a very fast and adaptable data augmentation technique to further enhance performance. The instrument segmentation mask is filled in (i.e., inpainted) by the tool removal algorithms using the previously acquired tool segmentation masks and either previous instrument-containing frames or instrument-free reference frames. Results: We have shown the effectiveness of the proposed surgical tool segmentation/removal algorithms on a robotic instrument dataset from the MICCAI 2015 and 2017 EndoVis Challenge. We report a 90.20% DICE for binary segmentation, a 76.26% DICE for instrument part segmentation, and a 46.07% DICE for instrument type (i.e., all instruments) segmentation on the MICCAI 2017 challenge dataset using our U-NetPlus architecture, outperforming the results of earlier techniques used and tested on these data. In addition, we demonstrated the successful execution of the tool removal algorithm from surgical tool-free videos that contained moving surgical tools that were generated artificially. Conclusions: Our application successfully separates and eliminates the surgical tool to reveal a view of the background tissue that was otherwise hidden by the tool, producing results that are visually similar to the actual data.

Investigating the impact of class-dependent label noise in medical image classification.

Label noise is inevitable in medical image databases developed for deep learning due to the inter-observer variability caused by the different levels of expertise of the experts annotating the images, and, in some cases, the automated methods that generate labels from medical reports. It is known that incorrect annotations or label noise can degrade the actual performance of supervised deep learning models and can bias the model's evaluation. Existing literature show that noise in one class has minimal impact on the model's performance for another class in natural image classification problems where different target classes have a relatively distinct shape and share minimal visual cues for knowledge transfer among the classes. However, it is not clear how class-dependent label noise affects the model's performance when operating on medical images, for which different output classes can be difficult to distinguish even for experts, and there is a high possibility of knowledge transfer across classes during the training period. We hypothesize that for medical image classification tasks where the different classes share a very similar shape with differences only in texture, the noisy label for one class might affect the performance across other classes, unlike the case when the target classes have different shapes and are visually distinct. In this paper, we study this hypothesis using two publicly available datasets: a 2D organ classification dataset with target organ classes being visually distinct, and a histopathology image classification dataset where the target classes look very similar visually. Our results show that the label noise in one class has a much higher impact on the model's performance on other classes for the histopathology dataset compared to the organ dataset.

A Review of Applications, Prospects, and Challenges of Proton-Conducting Zirconates in Electrochemical Hydrogen Devices.

In the future, when fossil fuels are exhausted, alternative energy sources will be essential for everyday needs. Hydrogen-based energy can play a vital role in this aspect. This energy is green, clean, and renewable. Electrochemical hydrogen devices have been used extensively in nuclear power plants to manage hydrogen-based renewable fuel. Doped zirconate materials are commonly used as an electrolyte in these electrochemical devices. These materials have excellent physical stability and high proton transport numbers, which make them suitable for multiple applications. Doping enhances the physical and electronic properties of zirconate materials and makes them ideal for practical applications. This review highlights the applications of zirconate-based proton-conducting materials in electrochemical cells, particularly in tritium monitors, tritium recovery, hydrogen sensors, and hydrogen pump systems. The central section of this review summarizes recent investigations and provides a comprehensive insight into the various doping schemes, experimental setup, instrumentation, optimum operating conditions, morphology, composition, and performance of zirconate electrolyte materials. In addition, different challenges that are hindering zirconate materials from achieving their full potential in electrochemical hydrogen devices are discussed. Finally, this paper lays out a few pathways for aspirants who wish to undertake research in this field.

Joint Segmentation and Uncertainty Estimation of Ventricular Structures from Cardiac MRI using a Bayesian CondenseUNet.

While convolutional neural networks (CNNs) have shown potential in segmenting cardiac structures from magnetic resonance (MR) images, their clinical applications still fall short of providing reliable cardiac segmentation. As a result, it is critical to quantify segmentation uncertainty in order to identify which segmentations might be troublesome. Moreover, quantifying uncertainty is critical in real-world scenarios, where input distributions are frequently moved from the training distribution due to sample bias and non-stationarity. Therefore, well-calibrated uncertainty estimates provide information on whether a model's output should (or should not) be trusted in such situations. In this work, we used a Bayesian version of our previously proposed CondenseUNet [1] framework featuring both a learned group structure and a regularized weight-pruner to reduce the computational cost in volumetric image segmentation and help quantify predictive uncertainty. Our study further showcases the potential of our deep-learning framework to evaluate the correlation between the uncertainty and the segmentation errors for a given model. The proposed model was trained and tested on the Automated Cardiac Diagnosis Challenge (ACDC) dataset featuring 150 cine cardiac MRI patient dataset for the segmentation and uncertainty estimation of the left ventricle (LV), right ventricle (RV), and myocardium (Myo) at end-diastole (ED) and end-systole (ES) phases.

Calibration of cine MRI segmentation probability for uncertainty estimation using a multi-task cross-task learning architecture.

While deep learning has shown potential in solving a variety of medical image analysis problems including segmentation, registration, motion estimation, etc., their applications in the real-world clinical setting are still not affluent due to the lack of reliability caused by the failures of deep learning models in prediction. Furthermore, deep learning models need a large number of labeled datasets. In this work, we propose a novel method that incorporates uncertainty estimation to detect failures in the segmentation masks generated by CNNs. Our study further showcases the potential of our model to evaluate the correlation between the uncertainty and the segmentation errors for a given model. Furthermore, we introduce a multi-task cross-task learning consistency approach to enforce the correlation between the pixel-level (segmentation) and the geometric-level (distance map) tasks. Our extensive experimentation with varied quantities of labeled data in the training sets justifies the effectiveness of our model for the segmentation and uncertainty estimation of the left ventricle (LV), right ventricle (RV), and myocardium (Myo) at end-diastole (ED) and end-systole (ES) phases from cine MRI images available through the MICCAI 2017 ACDC Challenge Dataset. Our study serves as a proof-of-concept of how uncertainty measure correlates with the erroneous segmentation generated by different deep learning models, further showcasing the potential of our model to flag low-quality segmentation from a given model in our future study.

Learning Deep Representations of Cardiac Structures for 4D Cine MRI Image Segmentation through Semi-Supervised Learning.

Learning good data representations for medical imaging tasks ensures the preservation of relevant information and the removal of irrelevant information from the data to improve the interpretability of the learned features. In this paper, we propose a semi-supervised model-namely, combine-all in semi-supervised learning (CqSL)-to demonstrate the power of a simple combination of a disentanglement block, variational autoencoder (VAE), generative adversarial network (GAN), and a conditioning layer-based reconstructor for performing two important tasks in medical imaging: segmentation and reconstruction. Our work is motivated by the recent progress in image segmentation using semi-supervised learning (SSL), which has shown good results with limited labeled data and large amounts of unlabeled data. A disentanglement block decomposes an input image into a domain-invariant spatial factor and a domain-specific non-spatial factor. We assume that medical images acquired using multiple scanners (different domain information) share a common spatial space but differ in non-spatial space (intensities, contrast, etc.). Hence, we utilize our spatial information to generate segmentation masks from unlabeled datasets using a generative adversarial network (GAN). Finally, to reconstruct the original image, our conditioning layer-based reconstruction block recombines spatial information with random non-spatial information sampled from the generative models. Our ablation study demonstrates the benefits of disentanglement in holding domain-invariant (spatial) as well as domain-specific (non-spatial) information with high accuracy. We further apply a structured L 2 similarity ( S L 2 SIM ) loss along with a mutual information minimizer (MIM) to improve the adversarially trained generative models for better reconstruction. Experimental results achieved on the STACOM 2017 ACDC cine cardiac magnetic resonance (MR) dataset suggest that our proposed (CqSL) model outperforms fully supervised and semi-supervised models, achieving an 83.2% performance accuracy even when using only 1% labeled data. We hypothesize that our proposed model has the potential to become an efficient semantic segmentation tool that may be used for domain adaptation in data-limited medical imaging scenarios, where annotations are expensive. Code, and experimental configurations will be made available publicly.

STAMP: A Self-training Student-Teacher Augmentation-Driven Meta Pseudo-Labeling Framework for 3D Cardiac MRI Image Segmentation.

Medical image segmentation has significantly benefitted thanks to deep learning architectures. Furthermore, semi-supervised learning (SSL) has led to a significant improvement in overall model performance by leveraging abundant unlabeled data. Nevertheless, one shortcoming of pseudo-labeled based semi-supervised learning is pseudo-labeling bias, whose mitigation is the focus of this work. Here we propose a simple, yet effective SSL framework for image segmentation-STAMP (Student-Teacher Augmentation-driven consistency regularization via Meta Pseudo-Labeling). The proposed method uses self-training (through meta pseudo-labeling) in concert with a Teacher network that instructs the Student network by generating pseudo-labels given unlabeled input data. Unlike pseudo-labeling methods, for which the Teacher network remains unchanged, meta pseudo-labeling methods allow the Teacher network to constantly adapt in response to the performance of the Student network on the labeled dataset, hence enabling the Teacher to identify more effective pseudo-labels to instruct the Student. Moreover, to improve generalization and reduce error rate, we apply both strong and weak data augmentation policies, to ensure the segmentor outputs a consistent probability distribution regardless of the augmentation level. Our extensive experimentation with varied quantities of labeled data in the training sets demonstrates the effectiveness of our model in segmenting the left atrial cavity from Gadolinium-enhanced magnetic resonance (GE-MR) images. By exploiting unlabeled data with weak and strong augmentation effectively, our proposed model yielded a statistically significant 2.6% improvement ( p < 0.001 ) in Dice and a 4.4% improvement ( p < 0.001 ) in Jaccard over other state-of-the-art SSL methods using only 10% labeled data for training.

Segmentation and Removal of Surgical Instruments for Background Scene Visualization from Endoscopic / Laparoscopic Video.

Surgical tool segmentation is becoming imperative to provide detailed information during intra-operative execution. These tools can obscure surgeons' dexterity control due to narrow working space and visual field-of-view, which increases the risk of complications resulting from tissue injuries (e.g. tissue scars and tears). This paper demonstrates a novel application of segmenting and removing surgical instruments from laparoscopic/endoscopic video using digital inpainting algorithms. To segment the surgical instruments, we use a modified U-Net architecture (U-NetPlus) composed of a pre-trained VGG11 or VGG16 encoder and redesigned decoder. The decoder is modified by replacing the transposed convolution operation with an up-sampling operation based on nearest-neighbor (NN) interpolation. This modification removes the artifacts generated by the transposed convolution, and, furthermore, these new interpolation weights require no learning for the upsampling operation. The tool removal algorithms use the tool segmentation mask and either the instrument-free reference frames or previous instrument-containing frames to fill-in (i.e., inpaint) the instrument segmentation mask with the background tissue underneath. We have demonstrated the performance of the proposed surgical tool segmentation/removal algorithms on a robotic instrument dataset from the MICCAI 2015 EndoVis Challenge. We also showed successful performance of the tool removal algorithm from synthetically generated surgical instruments-containing videos obtained by embedding a moving surgical tool into surgical tool-free videos. Our application successfully segments and removes the surgical tool to unveil the background tissue view otherwise obstructed by the tool, producing visually comparable results to the ground truth.

Fruit by-products: the potential natural sources of antioxidants and α-glucosidase inhibitors.

The present effort was to obtain extracts from various fruit by-products using three extraction systems and to evaluate their polyphenolic content, antioxidant, and α-glucosidase inhibition activity. The fruit by-products were pre-processed by washing, drying, and milling methods to produce the powder. The powder samples were used to obtain extracts using pressurized hot-water (PHWE), enzyme-assisted (EnE) and organic solvent extraction (OSE) systems. The total phenolic content (TPC), total flavonoid content (TFC), antioxidant and α-glucosidase inhibition activity in all samples were assessed by Folin-Ciocalteu, AlCl3 colorimetric, DPPH· & ABST·+ and α-glucosidase inhibitory methods. The results showed that the extracts of peel, seed and other by-products exhibited outstanding TPC, TFC, and strongest antioxidant and α-glucosidase inhibition activity, eventually higher than edible parts of the fruits. For instance, the highest TPC among the peels of various fruits were in mango peel (in all cultivar) followed by litchi peel, banana peel cv. sagor, jackfruit peel, pineapple peel, papaya peel, banana peel cv. malbhog and desi on average in all tested extraction systems. PHWE system yielded significantly (p < 0.05) higher TPC and TFC than other extraction systems. In case of misribhog mango variety, the TPC (mg GAE/g DM) in peels were 180.12 ± 7.33, 73.52 ± 2.91 and 36.10 ± 3.48, and in seeds were 222.62 ± 12.11, 76.18 ± 2.63 and 42.83 ± 12.52 for PHWE, EnE and OSE respectively. This work reported the promising potential of underutilized fruit by-products as new sources to manufacture ingredients and nutraceuticals for foods and pharmaceutical products.

A Multi-Task Cross-Task Learning Architecture for Ad Hoc Uncertainty Estimation in 3D Cardiac MRI Image Segmentation.

Medical image segmentation has significantly benefitted thanks to deep learning architectures. Furthermore, semi-supervised learning (SSL) has recently been a growing trend for improving a model's overall performance by leveraging abundant unlabeled data. Moreover, learning multiple tasks within the same model further improves model generalizability. To generate smooth and accurate segmentation masks from 3D cardiac MR images, we present a Multi-task Cross-task learning consistency approach to enforce the correlation between the pixel-level (segmentation) and the geometric-level (distance map) tasks. Our extensive experimentation with varied quantities of labeled data in the training sets justifies the effectiveness of our model for the segmentation of the left atrial cavity from Gadolinium-enhanced magnetic resonance (GE-MR) images. With the incorporation of uncertainty estimates to detect failures in the segmentation masks generated by CNNs, our study further showcases the potential of our model to flag low-quality segmentation from a given model.

CondenseUNet: A memory-efficient condensely-connected architecture for bi-ventricular blood pool and myocardium segmentation.

With the advent of Cardiac Cine Magnetic Resonance (CMR) Imaging, there has been a paradigm shift in medical technology, thanks to its capability of imaging different structures within the heart without ionizing radiation. However, it is very challenging to conduct pre-operative planning of minimally invasive cardiac procedures without accurate segmentation and identification of the left ventricle (LV), right ventricle (RV) blood-pool, and LV-myocardium. Manual segmentation of those structures, nevertheless, is time-consuming and often prone to error and biased outcomes. Hence, automatic and computationally efficient segmentation techniques are paramount. In this work, we propose a novel memory-efficient Convolutional Neural Network (CNN) architecture as a modification of both CondenseNet, as well as DenseNet for ventricular blood-pool segmentation by introducing a bottleneck block and an upsampling path. Our experiments show that the proposed architecture runs on the Automated Cardiac Diagnosis Challenge (ACDC) dataset using half (50%) the memory requirement of DenseNet and one-twelfth (~ 8%) of the memory requirements of U-Net, while still maintaining excellent accuracy of cardiac segmentation. We validated the framework on the ACDC dataset featuring one healthy and four pathology groups whose heart images were acquired throughout the cardiac cycle and achieved the mean dice scores of 96.78% (LV blood-pool), 93.46% (RV blood-pool) and 90.1% (LV-Myocardium). These results are promising and promote the proposed methods as a competitive tool for cardiac image segmentation and clinical parameter estimation that has the potential to provide fast and accurate results, as needed for pre-procedural planning and / or pre-operative applications.

Sustained Local Delivery of Diclofenac from Three-Dimensional Ultrafine Fibrous Protein Scaffolds with Ultrahigh Drug Loading Capacity.

The three-dimensional (3D) ultrafine fibrous scaffolds loaded with functional components can not only provide support to 3D tissue repair, but also deliver the components in-situ with small dosage and low fusion frequency. However, the conventional loading methods possess drawbacks such as low loading capacity or high burst release. In this research, an ultralow concentration phase separation (ULCPS) technique was developed to form 3D ultrafine gelatin fibers and, meanwhile, load an anti-inflammatory drug, diclofenac, with high capacities for the long-term delivery. The developed scaffolds could achieve a maximum drug loading capacity of 12 wt.% and a highest drug loading efficiency of 84% while maintaining their 3D ultrafine fibrous structure with high specific pore volumes from 227.9 to 237.19 cm3/mg. The initial release at the first hour could be reduced from 34.7% to 42.2%, and a sustained linear release profile was observed with a rate of about 1% per day in the following 30 days. The diclofenac loaded in and released from the ULCPS scaffolds could keep its therapeutic molecular structure. The cell viability has not been affected by the release of drug when the loading was less than 12 wt.%. The results proved the possibility to develop various 3D ultrafine fibrous scaffolds, which can supply functional components in-situ with a long-term.

Toward Quantification and Visualization of Active Stress Waves for Myocardial Biomechanical Function Assessment.

Estimating and visualizing myocardial active stress wave patterns is crucial to understanding the mechanical activity of the heart and provides a potential non-invasive method to assess myocardial function. These patterns can be reconstructed by analyzing 2D and/or 3D tissue displacement data acquired using medical imaging. Here we describe an application that utilizes a 3D finite element formulation to reconstruct active stress from displacement data. As a proof of concept, a simple cubic mesh was used to represent a myocardial tissue "sample" consisting of a 10 × 10 × 10 lattice of nodes featuring different fiber directions that rotate with depth, mimicking cardiac transverse isotropy. In the forward model, tissue deformation was generated using a test wave with active stresses that mimic the myocardial contractile forces. The generated deformation field was used as input to an inverse model designed to reconstruct the original active stress distribution. We numerically simulated malfunctioning tissue regions (experiencing limited contractility and hence active stress) within the healthy tissue. We also assessed model sensitivity by adding noise to the deformation field generated using the forward model. The difference image between the original and reconstructed active stress distribution suggests that the model accurately estimates active stress from tissue deformation data with a high signal-to-noise ratio.

Correction to: Two-step verification of brain tumor segmentation using watershed-matching algorithm.

In the original publication of this article [1], the spelling of second author was incorrect.