Optimal Artificial Intelligence Based Automated Skin Lesion Detection and Classification Model

Skin lesions have become a critical illness worldwide, and the earlier identification of skin lesions using dermoscopic images can raise the survival rate. Classification of the skin lesion from those dermoscopic images will be a tedious task. The accuracy of the classification of skin lesions is improved by the use of deep learning models. Recently, convolutional neural networks (CNN) have been established in this domain, and their techniques are extremely established for feature extraction, leading to enhanced classification. With this motivation, this study focuses on the design of artificial intelligence (AI) based solutions, particularly deep learning (DL) algorithms, to distinguish malignant skin lesions from benign lesions in dermoscopic images. This study presents an automated skin lesion detection and classification technique utilizing optimized stacked sparse autoencoder (OSSAE) based feature extractor with backpropagation neural network (BPNN), named the OSSAE-BPNN technique. The proposed technique contains a multi-level thresholding based segmentation technique for detecting the affected lesion region. In addition, the OSSAE based feature extractor and BPNN based classifier are employed for skin lesion diagnosis. Moreover, the parameter tuning of the SSAE model is carried out by the use of sea gull optimization (SGO) algorithm. To showcase the enhanced outcomes of the OSSAE-BPNN model, a comprehensive experimental analysis is performed on the benchmark dataset. The experimental findings demonstrated that the OSSAE-BPNN approach outperformed other current strategies in terms of several assessment metrics.     

Preparation and biological evaluation of <Superscript>99<Emphasis Type="Italic">m</Emphasis></Superscript>Tc-timonacic acid as a new complex for hepatobiliary imaging

Timonacic acid (TCA) was successfully labeled with ^99m Tc. The influence exerted on the reaction by the substrate and reducing agent concentrations, pH of the reaction mixture, and reaction time was examined, and in vitro stability of ^99m Tc-TCA was evaluated. The maximum labeling yield was 98.5 ± 0.6%. The complex was stable throughout the working period (6 h). A study of in-vivo biodistribution in mice showed that the maximum uptake of ^99m Tc-TCA in the liver was 22.3 ± 0.3% of the injected activity per gram of the tissue or organ (% ID/g) at 30 min post injection. The clearance from the mice appeared to proceed via the circulation mainly through the kidneys and urine (approximately 56% of the injected dose at 1 h after injection). The liver uptake of ^99m Tc-TCA is higher than that of ^99m Tc-UDCA (ursodeoxycholic acid); therefore, ^99m Tc-TCA shows more promise for liver SPECT.     

Fuzzy-HLSTM (Hierarchical Long Short-Term Memory) for Agricultural Based Information Mining

This research proposes a machine learning approach using fuzzy logic to build an information retrieval system for the next crop rotation. In case-based reasoning systems, case representation is critical, and thus, researchers have thoroughly investigated textual, attribute-value pair, and ontological representations. As big databases result in slow case retrieval, this research suggests a fast case retrieval strategy based on an associated representation, so that, cases are interrelated in both either similar or dissimilar cases. As soon as a new case is recorded, it is compared to prior data to find a relative match. The proposed method is worked on the number of cases and retrieval accuracy between the related case representation and conventional approaches. Hierarchical Long Short-Term Memory (HLSTM) is used to evaluate the efficiency, similarity of the models, and fuzzy rules are applied to predict the environmental condition and soil quality during a particular time of the year. Based on the results, the proposed approaches allows for rapid case retrieval with high accuracy.     

Differentiation of promonocytic U937 subclones into macrophagelike phenotypes regulates a cellular factor(s) which modulates fusion/entry of macrophagetropic human immunodeficiency virus type 1

Monocytes/macrophages (M/M) and CD4+ T cells are two important targets of human immunodeficiency virus (HIV) infection. Different strains of HIV-1 vary markedly in their abilities to infect cells belonging to the M/M lineage. Macrophagetropic (M-tropic) HIV-1 strains replicate well in primary lymphocytes as well as in primary macrophages; however, they generally infect T-cell lines poorly, if at all. Although promonocytic cell lines such as U937 have been used as in vitro models of HIV-1 infection of M/M, these cell lines are susceptible to certain T-cell-tropic (T-tropic) HIV-1 strains but are resistant to M-tropic HIV-1. In this study, we demonstrate that (i) certain U937 clones ("plus" clones), which are susceptible only to T-tropic HIV-1, become highly susceptible to M-tropic HIV-1 upon differentiation with retinoic acid (RA); (ii) other U937 clones ("minus" clones), which are resistant to both T- and M-tropic HIV-1, remain resistant to both viruses; and (iii) RA treatment induces expression of CCR5, a fusion/entry cofactor for M-tropic HIV-1 in both types of U937 clones, and yet enhances the fusogenicity of the plus clones, but not the minus clones, with M-tropic Env's. These results indicate that the major restriction of M-tropic HIV-1 infection in promonocytic cells occurs at the fusion/entry level, that differentiation into macrophage-like phenotypes renders some of these cells highly susceptible to infection with M-tropic HIV-1, and that CD4 and CCR5 may not be the only determinants of fusion/entry of M-tropic HIV-1 in these cells.     

Refining the level for anticipated hepatotoxicity in acetaminophen poisoning

Treatment of an acetaminophen overdose with N-acetyl cysteine usually is based on the position of the 4-h acetaminophen (APAP) level on the Rumack-Matthew nomogram; however, there is disagreement on the level at which clinically relevant hepatotoxicity occurs. A retrospective review of all acute adult formulation APAP exposures reported to our poison center between 1986 and 1993 was performed and cases corresponding to the "possible risk or toxicity" range on the nomogram were identified. Our current poison center protocol for APAP poisoning does not recommend treatment with N-acetylcysteine (NAC) in low-risk patients if the 4-h serum APAP level or the extrapolated equivalent falls within the possible toxicity range on the nomogram. Seventeen cases met the inclusion criteria for the study and received no NAC; six additional patients met inclusion criteria but received one or two doses of NAC before therapy was discontinued. No patients in either group demonstrated clinical evidence of hepatotoxicity. This pilot study suggests that patients with no risk factors and APAP levels in the "possible risk" range may not require NAC therapy.     

Hamstrings and psoas lengths during normal and crouch gait: implications for muscle-tendon surgery

OBJECTIVE: To study the relative contribution of the lung and the chest wall on the total respiratory system mechanics, gas exchange, and work of breathing in sedated-paralyzed normal subjects and morbidly obese patients, in the postoperative period. SETTING: Policlinico Hospital, University of Milan, Italy. METHODS: In ten normal subjects (normal) and ten morbidly obese patients (obese), we partitioned the total respiratory mechanics (rs) into its lung (L) and chest wall (w) components using the esophageal balloon technique together with airway occlusion technique, during constant flow inflation. We measured, after abdominal surgery, static respiratory system compliance (Cst,rs), lung compliance (Cst,L), chest wall compliance (Cst,w), total lung (Rmax,L) and chest wall (Rmax,w) resistance. Rmax,L includes airway (Rmin,L) and "additional" lung resistance (DR,L). DR,L represents the component due to viscoelastic phenomena of the lung tissue and time constant inequalities (pendelluft). Functional residual capacity (FRC) was measured by helium dilution technique. RESULTS: We found that morbidly obese patients compared with normal subjects are characterized by the following: (1) reduced Cst,rs (p < 0.01), due to lower Cst,L (55.3 +/- 15.3 mL x cm H2O-1 vs 106.6 +/- 31.7 mL x cm H2O-1; p < 0.01) and Cst,w (112.4 +/- 47.4 mL x cm H2O-1 vs 190.7 +/- 45.1 mL x cm H2O-1; p < 0.01); (2) increased Rmin,L (4.7 +/- 3.1 mL x cm H2O x L-1 x s; vs 1.0 +/- 0.8 mL x cm H2O x L-1 x s; p < 0.01) and DR,L (4.9 +/- 2.6 mL x cm H2O x L-1 x s; vs 1.5 +/- 0.8 mL x cm H2O x L-1 x s; p < 0.01); (3) reduced FRC (0.665 +/- 0.191 L vs 1.691 +/- 0.325 L; p < 0.01); (4) increased work performed to inflate both the lung (0.91 +/- 0.25 J/L vs 0.34 +/- 0.08 J/L; p < 0.01) and the chest wall (0.39 +/- 0.13 J/L vs 0.18 +/- 0.04 J/L; p < 0.01); and (5) a reduced pulmonary oxygenation index (PaO2/PAO2 ratio). CONCLUSION: Sedated-paralyzed morbidly obese patients, compared with normal subjects, are characterized by marked derangements in lung and chest wall mechanics and reduced lung volume after abdominal surgery. These alterations may account for impaired arterial oxygenation in the postoperative period.     

Variational sensitivity analysis and design optimization

Variational method (VM) is employed to derive the co-state equations, boundary (transversality) conditions, and functional sensitivity derivatives. The converged solutions of the state equations together with the steady state solution of the co-state equations are integrated along the domain boundary to uniquely determine the functional sensitivity derivatives with respect to the design function. The application of the variational method to aerodynamic shape optimization problems is demonstrated on internal flow problems at supersonic Mach number range of 1.5. Optimization results for flows with and without shock phenomena are presented. The study shows that while maintaining the accuracy of aerodynamical objective function and constraint within the reasonable range for engineering prediction purposes, variational method provides a substantial gain in computational efficiency, i.e., computer time and memory, when compared with the finite difference computations.     

Rotary flexible joint control by fractional order controllers

In this paper, a fractional order control law is proposed and implemented for the evaluation of trajectory tracking performance of a rotary flexible-joint system. A state feedback based fractional integral control scheme is used in this proposed method. In this scheme, state feedback is responsible for stabilizing the system. The compensator, in series with the fractional integrator leads to obtain a similar closed-loop transient response like Bode’s ideal transfer function. The effectiveness of the proposed controller in tracking and being robust against parameter uncertainties is demonstrated through simulation. In addition, to show the usefulness of the proposed control scheme, the fractional controller is compared to an integer state feedback control by simulation and through experimentation on the Quanser’s rotary flexible-joint system.     

Multi-directional blending for heterogeneous objects

This paper presents a novel multi-directional blending method for heterogeneous object design. Contrary to earlier studies, this paper introduces material blending through multiple features with different heterogeneous material composition. Feature-based method is used to represent and design heterogeneous objects with multi-directional material composition. The Voronoi diagram of multiple curves is constructed to generate bisector of the geometric domain. Then, metamorphosis from the bounding curve to multiple internal curves is performed using dynamic programming based optimization approach in two steps. First, optimum curve matching between internal curves and enclosing Voronoi cells is obtained. Then, an optimum ruling line alignment and insertion technique between the Voronoi diagram and the bounding curve is developed. Metamorphosis through complex concavities is also achieved. Finally, multi-directional material composition is mapped based on a set of relations.