In radiation oncology, predicting patient risk stratification allows specialization of therapy intensification as well as selecting between systemic and regional treatments, all of which helps to ...improve patient outcome and quality of life. Deep learning offers an advantage over traditional radiomics for medical image processing by learning salient features from training data originating from multiple datasets. However, while their large capacity allows to combine high-level medical imaging data for outcome prediction, they lack generalization to be used across institutions. In this work, a pseudo-volumetric convolutional neural network with a deep preprocessor module and self-attention (PreSANet) is proposed for the prediction of distant metastasis, locoregional recurrence, and overall survival occurrence probabilities within the 10 year follow-up time frame for head and neck cancer patients with squamous cell carcinoma. The model is capable of processing multi-modal inputs of variable scan length, as well as integrating patient data in the prediction model. These proposed architectural features and additional modalities all serve to extract additional information from the available data when availability to additional samples is limited. This model was trained on the public Cancer Imaging Archive Head-Neck-PET-CT dataset consisting of 298 patients undergoing curative radio/chemo-radiotherapy and acquired from 4 different institutions. The model was further validated on an internal retrospective dataset with 371 patients acquired from one of the institutions in the training dataset. An extensive set of ablation experiments were performed to test the utility of the proposed model characteristics, achieving an AUROC of Formula: see text, Formula: see text and Formula: see text for DM, LR and OS respectively on the public TCIA Head-Neck-PET-CT dataset. External validation was performed on a retrospective dataset with 371 patients, achieving Formula: see text AUROC in all outcomes. To test for model generalization across sites, a validation scheme consisting of single site-holdout and cross-validation combining both datasets was used. The mean accuracy across 4 institutions obtained was Formula: see text, Formula: see text and Formula: see text for DM, LR and OS respectively. The proposed model demonstrates an effective method for tumor outcome prediction for multi-site, multi-modal combining both volumetric data and structured patient clinical data.
This paper investigates the energy management of a fuel cell/ultra-capacitor hybrid electric vehicle (FCHEV) under uncertainty. In addition to fuel economy and fuel cell (FC) system slow dynamics, ...solutions’ robustness is also considered as a key performance criterion. As previous studies focus on expected optimal performance under a deterministic framework and ignore possible data ambiguity, this paper considers uncertainties affecting power production, conversion and demand levels. Changing operation conditions, modeling and estimation claim several sources of errors. In practice, ignoring such uncertainties leads to high operation cost, poor overall system efficiency, performance failure and even infeasible solutions due to constraints violation. A robust optimization (RO) based energy management system (EMS) is studied in order to ensure optimal yet robust performance under uncertain parameters. The adopted RO based algorithm includes uncertainty in the cost function and constraints set and thus protects the system performance from feasibility and optimality issues. As RO approach is considered over conservative, conservatism level parameters are introduced to enable more flexible decision making and performance cost. Three different optimization case studies, namely classical deterministic, complete robust and variable conservatism level were investigated in order to assess the performance of the proposed approach.
•A robust optimization based EMS for a FCHEV under uncertainty is presented.•Uncertainties affecting both the cost function and the constraints set are studied.•Solution feasibility and optimality are guaranteed even for the worst-case scenario.•Flexible conservatism level scenarios are investigated for a suitable cost tradeoff.
•In this paper, we present an AI-based technique for automatically detecting osteoporosis by analyzing X-ray images of bone tissue.•In this study, we developed a model for diagnosing osteoporosis ...based on handcrafted features taken from descriptors obtained from a thorough analysis of the bone image using a set of Gabor filters with different orientations.•To achieve a high level of performance, we used a bat-based optimization method to determine appropriate Gabor filter parameters.•Additionally, we combined information at two distinct levels.•In fact, our tests resulted in an excellent performance (ACC = 89.66%) that outperformed several previously published studies.
Recently, automated disease diagnosis based on medical images has become an integral component of digital pathology packages. Texture analysis is commonly used to address this issue, particularly in the context of estimating the osteoporosis progression in bone samples. Most research in this context uses handcrafted methods to directly extract bones image features despite the substantial correlation between sick and healthy bones, which explains the limited results. In this work, the handcrafted feature extraction method (e.g. HOG and/or LPQ) will be applied to a set of descriptors obtained from a deep analysis of bone texture images using Gabor's filter bank. In addition, the classifier automatically adjusts the Gabor filters settings, using the bat-inspired algorithm based optimization, to achieve deep analysis behavior and optimal performance. Using a typically osteoporosis database, our experimental results reveal a significant improvement over the state-of-the-art deep/handcrafted techniques, resulting in an excellent performance of 89.66% for osteoporosis diagnosis.
New functional hybrids containing graphene oxide nanosheets (GO) and natural fibers (alfa fibers (AF) or microcrystalline cellulose (MCC)) were successfully produced using simple blending followed by ...oven drying. Such hybrids offer unique benefits of natural fibers with functionality of graphene oxide. The obtained products have been characterized using different analytical techniques such as Fourier transform infrared (FTIR) and Raman spectroscopies, scanning electron microscopy (SEM), X-ray diffraction (XRD), and thermogravilmetry (TGA). The morphological analysis revealed that the applied surface treatment of the Alfa fibers (AF) ensured a good distribution of the GO sheets on the fibers surface. It is also demonstrated that the hydrogen bonding interactions between the natural fibers and GO facilitate the dispersion of the latter on the surface of the fibers, producing homogeneous composites (AF/GO) and (MCC/GO). The thermal behavior of the obtained composites is obviously affected by the type of natural fibers. The presence of hemicellulose and lignin in AF slightly decreased the thermal stability of AF/GO hybrid compared to MCC/GO, which presented a better thermal stability. Such hybrids would open up a new way to develop composites with tunable physicochemical properties for various applications.
The uranyl(V) complexes UO2(dbm)2K(18C6)2 (dbm = dibenzoylmethanate) and UO2(L)3(L = 2-(4-tolyl)-1,3-bis(quinolyl)malondiiminate), exhibiting diamond-shaped U2O2 and triangular-shaped U3O3 cores ...respectively with 5f1–5f1 and 5f1–5f1–5f1 configurations, have been investigated using relativistic density functional theory (DFT). The bond order and QTAIM analyses reveal that the covalent contribution to the bonding within the oxo cores is slightly more important for U3O3 than for U2O2, in line with the shorter U–O distances existing in the trinuclear complex in comparison to those in the binuclear complex. Using the broken symmetry (BS) approach combined with the B3LYP functional for the calculation of the magnetic exchange coupling constants (J) between the magnetic centers, the antiferromagnetic (AF) character of these complexes was confirmed, the estimated J values being respectively equal to −24.1 and −7.2 cm–1 for the dioxo and trioxo species. It was found that the magnetic exchange is more sensitive to small variations of the core geometry of the dioxo species in comparison to the trioxo species. Although the robust AF exchange coupling within the U x O x cores is generally maintained when small variations of the UOU angle are applied, a weak ferromagnetic character appears in the dioxo species when this angle is higher than 114°, its value for the actual structure being equal to 105.9°. The electronic factors driving the magnetic coupling are discussed.
The magnetic exchange coupling between two diuranium(V) ions exhibiting the 5
f
1
-5
f
1
configuration in diimide-bridged complexes Cp
3
U
V
2
(μ-L) (L = stilbene-, naphthalene-diimide) has been ...investigated theoretically using relativistic ZORA/DFT calculations. Using two different hybrid PBE0 and B3LYP functionals, combined with the broken symmetry (BS) approach, we found that the BS states of both naphthalene and stilbene complexes have lower energy than the corresponding high-spin (HS) triplet ones. The B3LYP/BS estimated exchange coupling
J
constants (− 16.1 vs. − 9.0 cm
−1
respectively for the naphthalene and stilbene complexes) corroborate well with those obtained previously for other pentavalent diuranium(V) diimide-bridged systems. The computed
J
value is found to be sensitive to π-network linking the two magnetic U(V) centers. The natural spin density distributions and molecular orbital analyses explain well the antiferromagnetic character of these compounds and clarify the crucial role of the π aromatic spacer in promoting spin polarization and delocalization favoring the magnetic coupling. Furthermore, the effective involvement of the 6
d
/5
f
metal orbitals in metal-ligand bonding plays an important role for the magnetic communication between the two active U(V) 5
f
electrons.
Graphical abstract
Alzheimer’s disease (AD) is characterized by alterations in monoamines, oxidative stress, and metabolic dysfunctions. We aim to assess the therapeutic impacts of roots or leaf extract from
Urtica ...dioica
(UD; stinging nettle) against scopolamine (SCOP)-induced memory dysfunction, amnesia, and oxidative stress in rats. Spatial memory was assessed by Y maze test. Tissue analyses of norepinephrine (NE), dopamine (DA), serotonin (5-HT), malondialdehyde (MDA), nitric oxide (NO), glutathione (GSH, GSSG), AMP, ADP, and ATP were assessed by HPLC. mRNA levels of Tau and Hsp70 were estimated by PCR. UD extracts particularly nettle root (NR) significantly normalized the SCOP-induced memory deficits even more potent than sermion (SR) and donepezil (DON). Similarly, NR had potent therapeutic impacts on the levels of cortical and hippocampal monoamines e.g. DA, NE, and 5-HT. SCOP induced a dramatic oxidative stress as measured by MDA, NO, and GSSG levels; however, UD extracts showed significant anti-oxidative stress impacts. Additionally, UD extracts restored ATP levels and reduced the levels of AMP and ADP compared to SCOP-treated rats. Furthermore, cortical Tau and hippocampal Hsp70 were modulated by UD extracts particularly NR compared to the SCOP group. In conclusion, UD extracts particularly roots have potential therapeutic impacts against SCOP-induced neuroinflammatory and/or Alzheimer-like phenotype in rats.
(Solanaceae), or tree tobacco, is found in dry arid climates of North America, Africa and Europe. It has been reported to have both toxic and medicinal properties. The main aim of this study was to ...analyze the phytochemical screening and quantitative estimation of polyphenols, flavonoids and flavonols of crude extracts from the leaves of
and to evaluate its
antioxidant properties. Three different solvents were used to extract bioactive compounds from powdered leaves of
: dichloromethane (DCM), ethyl acetate (AE) and n-buthanol (n-BuOH). The three extracts were then subjected to qualitative phytochemical screening using standard procedures. Total phenolics, total flavonoids and total flavonols contents of the extracts were measured by Folin Ciocalteu and Aluminium chloride methods respectively. Furthermore, the antioxidant capacity evaluation was performed using the DPPH, ABTS, DMSO alcalin, Phenantroline, FRAP and CUPRAC methods. The three extracts were then subjected to qualitative phytochemical screening using standard procedures. These methods showed the presence of polyphenols and comarines in all extracts. Moreover, flavonoids, tannins, steroids and quinones were reported in the AE and n-BuOH extracts. In addition, alkaloids were seen to be present in DCM extract, while saponines and phlobatannins were absent in all extracts. The antioxidant capacity evaluation was performed using the DPPH, ABTS, DMSO alcalin, Phenantroline, FRAP and CUPRAC methods.
Results using the DPPH method showed strong free radical scavinging activity for three extracts. This activity decreased with increasing concentration in the following order: n-BuOH>AE>DCM. In other assays, all extracts showed good antioxidant activity which decreased with increasing concentration in the following order: AE > n-BuOH > DCM. Extracts were compared with standards: BHT, BHA, Tanic acid and α-Tocopherol. The antioxidant of these extracts is probably related to polyphenols content (351.55±0.07, 284.98±0.08 and 133.8±0.06 mg/g), flavonoids (105.97±0.04, 164.44±0.07 and 1.18±0.005 mg/g) and flavonols (22.41±0.24, 18.75±0.46 mg/g) in AE and n-BuOH, respectively.
As a conclusion, the results of the present study indicate that
leaves could be considered as a potential source of natural antioxidants.
This paper presents a novel method for phase ac motor current reconstructing with a single current sensor in three-phase direct matrix converter (DMC) drive system using space vector modulation ...control technique. The main goal is to reduce the cost and to improve the reliability of drive systems that involve closed-loop control strategy. For this purpose, new structure and algorithm are developed which divide the zero-vector application time in two intervals and measure the phase currents using a new placement of the single Hall current sensor in DMC. These proposals constitute a good solution in the low-power-range DMC (below 15 kW), where reducing size and cost is the key objective. The simulation of the three-phase to three-phase DMC feeding an induction motor was done to demonstrate the advantages of the proposed system. Experiments were carried out owing to a DS1104 control board to check the validity of the proposed method.
This paper presents a novel low-cost and simple phase-current reconstruction algorithm for three-phase induction motor (IM) under direct torque control (DTC) using the information obtained from only ...one shunt resistor (in series with low-side switches in a conventional three-phase inverter). The aim is to develop a low-cost high-performance IM drive. The proposed algorithm is robust and very simple. It uses the dc current to reconstruct the stator currents needed to estimate the motor flux and the electromagnetic torque. A theoretical concept is developed, the modified look-up table is presented, and current-access tables are designed and used in the phase-current reconstruction. The limitations are also studied and presented.