A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction.

Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.

I-Cubid: a nonlinear cubic graph-based approach to visualize and in-depth browse Flickr image results.

The existing image search engines allow web users to explore images from the grids. The traditional interaction is linear and lookup-based. Notably, scanning web search results is horizontal-vertical and cannot support in-depth browsing. This research emphasizes the significance of a multidimensional exploration scheme over traditional grid layouts in visually exploring web image search results. This research aims to antecedent the implications of visualization and related in-depth browsing via a multidimensional cubic graph representation over a search engine result page (SERP). Furthermore, this research uncovers usability issues in the traditional grid and 3-dimensional web image search space. We provide multidimensional cubic visualization and nonlinear in-depth browsing of web image search results. The proposed approach employs textual annotations and descriptions to represent results in cubic graphs that further support in-depth browsing via a search user interface (SUI) design. It allows nonlinear navigation in web image search results and enables exploration, browsing, visualization, previewing/viewing, and accessing images in a nonlinear, interactive, and usable way. The usability tests and detailed statistical significance analysis confirm the efficacy of cubic presentation over grid layouts. The investigation reveals improvement in overall user satisfaction, screen design, information & terminology, and system capability in exploring web image search results.

A hybrid mask RCNN-based tool to localize dental cavities from real-time mixed photographic images.

Nearly 3.5 billion humans have oral health issues, including dental caries, which requires dentist-patient exposure in oral examinations. The automated approaches identify and locate carious regions from dental images by localizing and processing either colored photographs or X-ray images taken via specialized dental photography cameras. The dentists' interpretation of carious regions is difficult since the detected regions are masked using solid coloring and limited to a particular dental image type. The software-based automated tools to localize caries from dental images taken via ordinary cameras requires further investigation. This research provided a mixed dataset of dental photographic (colored or X-ray) images, instantiated a deep learning approach to enhance the existing dental image carious regions' localization procedure, and implemented a full-fledged tool to present carious regions via simple dental images automatically. The instantiation mainly exploits the mixed dataset of dental images (colored photographs or X-rays) collected from multiple sources and pre-trained hybrid Mask RCNN to localize dental carious regions. The evaluations performed by the dentists showed that the correctness of annotated datasets is up to 96%, and the accuracy of the proposed system is between 78% and 92%. Moreover, the system achieved the overall satisfaction level of dentists above 80%.

An architecture for non-linear discovery of aggregated multimedia document web search results.

The recent proliferation of multimedia information on the web enhances user information need from simple textual lookup to multi-modal exploration activities. The current search engines act as major gateways to access the immense amount of multimedia data. However, access to the multimedia content is provided by aggregating disjoint multimedia search verticals. The aggregation of the multimedia search results cannot consider relationships in them and are partially blended. Additionally, the search results' presentation is via linear lists, which cannot support the users' non-linear navigation patterns to explore the multimedia search results. Contrarily, users' are demanding more services from search engines. It includes adequate access to navigate, explore, and discover multimedia information. Our discovery approach allow users to explore and discover multimedia information by semantically aggregating disjoint verticals using sentence embeddings and transforming snippets into conceptually similar multimedia document groups. The proposed aggregation approach retains the relationship in the retrieved multimedia search results. A non-linear graph is instantiated to augment the users' non-linear information navigation and exploration patterns, which leads to discovering new and interesting search results at various aggregated granularity levels. Our method's empirical evaluation results achieve 99% accuracy in the aggregation of disjoint search results at different aggregated search granularity levels. Our approach provides a standard baseline for the exploration of multimedia aggregation search results.

mTOR/HDAC1 Crosstalk Mediated Suppression of ADH1A and ALDH2 Links Alcohol Metabolism to Hepatocellular Carcinoma Onset and Progression in silico.

Hepatocellular carcinoma (HCC) is ranked the third deadliest cancer worldwide whose molecular pathogenesis is not fully understood. Although deregulated metabolic pathways have been implicated in HCC onset and progression, the mechanisms triggering this metabolic imbalance are yet to be explored. Here, we identified a gene signature coding catabolic enzymes (Cat-GS) involved in key metabolic pathways like amino acid, lipid, carbohydrate, drug, and retinol metabolism as suppressed in HCC. A higher expression of deregulated Cat-GS is associated with good survival and less aggressive disease state in HCC patients. On the other hand, we identified mTOR signaling as a key determinant in HCC onset and progression, whose hyperactivation is found associated with poor survival and aggressive disease state in HCC patients. Next, out of Cat-GS, we established two key regulators of alcohol metabolism, alcohol dehydrogenase 1A (ADH1A) and aldehyde dehydrogenase 2 (ALDH2), as being transcriptionally suppressed by histone deacetylase 1 (HDAC1) at the downstream of mTORC1 signaling. Suppressed ADH1A and ALDH2 expression aligns well with HCC-specific molecular profile and can efficiently predict disease onset and progression, whereas higher ADH1A and ALDH2 expression is associated with good survival and less aggressive disease state in HCC patients. Overall, our in silico findings suggest that transcriptional suppression of alcohol metabolism regulators, ADH1A and ALDH2, at the downstream of mTOR signaling is, in part, responsible for triggering oncogenic transformation of hepatocytes resulting in disease onset and progression in HCC.

Systems biology based meth-miRNA-mRNA regulatory network identifies metabolic imbalance and hyperactive cell cycle signaling involved in hepatocellular carcinoma onset and progression.

BACKGROUND: Hepatocellular carcinoma (HCC) is one of the leading cause of cancer associated deaths worldwide. Independent studies have proposed altered DNA methylation pattern and aberrant microRNA (miRNA) levels leading to abnormal expression of different genes as important regulators of disease onset and progression in HCC. Here, using systems biology approaches, we aimed to integrate methylation, miRNA profiling and gene expression data into a regulatory methylation-miRNA-mRNA (meth-miRNA-mRNA) network to better understand the onset and progression of the disease. METHODS: Patients' gene methylation, miRNA expression and gene expression data were retrieved from the NCBI GEO and TCGA databases. Differentially methylated genes, and differentially expressed miRNAs and genes were identified by comparing respective patients' data using two tailed Student's t-test. Functional annotation and pathway enrichment, miRNA-mRNA inverse pairing and gene set enrichment analyses (GSEA) were performed using DAVID, miRDIP v4.1 and GSEA tools respectively. meth-miRNA-mRNA network was constructed using Cytoscape v3.5.1. Kaplan-Meier survival analyses were performed using R script and significance was calculated by Log-rank (Mantel-Cox) test. RESULTS: We identified differentially expressed mRNAs, miRNAs, and differentially methylated genes in HCC as compared to normal adjacent tissues by analyzing gene expression, miRNA expression, and methylation profiling data of HCC patients and integrated top miRNAs along with their mRNA targets and their methylation profile into a regulatory meth-miRNA-mRNA network using systems biology approach. Pathway enrichment analyses of identified genes revealed suppressed metabolic pathways and hyperactive cell cycle signaling as key features of HCC onset and progression which we validated in 10 different HCC patients' datasets. Next, we confirmed the inverse correlation between gene methylation and its expression, and between miRNA and its targets' expression in various datasets. Furthermore, we validated the clinical significance of identified methylation, miRNA and mRNA signatures by checking their association with clinical features and survival of HCC patients. CONCLUSIONS: Overall, we suggest that simultaneous (1) reversal of hyper-methylation and/or oncogenic miRNA driven suppression of genes involved in metabolic pathways, and (2) induction of hyper-methylation and/or tumor suppressor miRNA driven suppression of genes involved in cell cycle signaling have potential of inhibiting disease aggressiveness, and predicting good survival in HCC.

Adsorption Assisted Photocatalytic Removal of Methyl Orange by MgAl2O4-Sb2S3 Composite Material.

BACKGROUND: The current article is about the water treatment in which colored water contaminated by methyl orange has been used for adsorption assisted photocatalysis. Coupling of photocatalysis with the traditional water treatment processes has been in practice since last couple of years for the improvement of degradation efficiencies, for example, photocatalysis coupled with ultrafilteration, adsorption, flocculation, biological methods, photolysis, membrane distillation, etc. Among all these coupling approaches, adsorption assisted photocatalysis being a very simple and highly efficient approach is suffering from few drawbacks on the account of high cost, low stability and surface area of the adsorbent support. The present study is a contribution towards improvement in this coupling approach. A low cost, highly stable spinel magnesium aluminate (MgAl2O4) material synthesized at nanoscale is used for composite formation with antimony sulphide (Sb2S3) material having high absorption coefficient in the visible light of solar spectrum. A review of recent patents shows that the field of photoctalysis is dominated by the traditional TiO2 catalyst. The modification of TiO2 by either composite formation or by doping is the main focus. METHODS: Coprecipitation method is used for the synthesis of spinel in which the desired precursors in the respective molar ratios were mixed and annealing of the resulting precipitates was carried out at 800oC for 8 h. Sb2S3 was synthesized by the hydrothermal method in which the required molar solution of precursors was mixed with urea solution and the whole mixture was maintained at 105oC for 6 hrs in a Teflon lined autoclave. The resulting suspension was then annealed at 37oC for 3 hours. The composite of Sb2S3 and MgAl2O4 has been synthesized by mixing both the materials in 1:1 and heat treated in an oven at a temperature of 200oC. RESULTS: Peaks in X-ray diffraction pattern correspond to both the Sb2S3 and spinel phase. All the peaks corresponding to the Sb2S3 and spinel phase were found to be shifted to higher d-spacing values. This indicates the expansion of unit cells of the Sb2S3 and MgAl2O4 phases. Thermal studies show that only 3% weight loss is observed at a temperature of 200-1000oC which may be due to the loss of surface water from the sample. Surface area, pore volume and pore size obtained from N2 adsorption were 143m2/g, 0.21cc/g and 23.26Å, respectively. The removal efficiency of 0.1g catalyst for methyl orange solution of 5mg/L concentration after reaction in dark conditions for the time of one hour was calculated to be 24% owing to the adsorption. The visible light degradation efficiency of the 0.1g catalyst for 1, 5, 19, 25 and 50 mg/L concentrations of MO solutions were 97, 93, 75, 72 and 62% respectively. The dosage of the catalyst was found to have a direct relationship with the degradation efficiency. Lower pH was found suitable for the degradation owing to better interaction of catalyst surface and the adsorbed dye. Percent degradation increased with the increase in the time and temperature of reaction. The degradation kinetics followed pseudo first order rate equation; the calculated value of rate constant was 0.0102 min-1. CONCLUSION: The mechanism involves the excitation of electrons in the valence band of Sb2S3 to the conduction band by the absorption of visible and UV light. The electrons and holes participate in the surface reactions resulting in the formation of superoxide and hydroxyl radicals which degrade the targeted polluted. Lower concentration of MO solutions, acidic pH, higher catalyst dosage and greater reaction times were found suitable for the degradation efficiency.

Synthesis, spectroscopic characterization, biological screenings, DNA binding study and POM analyses of transition metal carboxylates.

This article contains the synthesis of a novel carboxylic acid derivative, its transition metal complexes and evaluation of biological applications. Six carboxylate complexes of transition metals, Zn(II) and Hg(II), have been successfully synthesized and characterized by FT-IR and NMR (1H, 13C). The ligand, HL, (4-[(2,6-Diethylphenyl)amino]-4-oxobutanoic acid) was also characterized by single crystal X-ray analysis. The complexation occurs via oxygen atoms of the carboxylate moiety. FT-IR date show the bidentate nature of the carboxylate moiety of the ligand as the Δν value in all complexes is less than that of the free ligand. The ligand and its complexes were screened for antifungal and antileishmanial activities. The results showed that the ligand and its complexes are active with few exceptions. UV-visible spectroscopy and viscometry results reveal that the ligand and its complexes interact with the DNA via intercalative mode of interaction. A new and efficient strategy to identify the pharmacophores and anti-pharmacophores sites in carboxylate derivatives for the antibacterial/antifungal activity using Petra, Osiris and Molinspiration (POM) analyses was also carried out.

Comparative study of laterite and bentonite based organoclays: implications of hydrophobic compounds remediation from aqueous solutions.

Four cost effective organoclays were synthesized, characterized, and studied for the sorption of hydrophobic compounds (edible oil/grease and hydrocarbon oil) from aqueous solutions. Organoclays were prepared by cation exchange reaction of lattice ions (present onto the surface of laterite and bentonite clay minerals) with two surfactants, hexadecyl trimethyl ammonium chloride (HDTMA-Cl) and tetradecyl trimethyl ammonium bromide (TDTMA-Br). Fourier transform infrared spectroscopy and scanning electron microscopy were used for the characterization of synthesized organoclays. It was found that the amount of surfactant loading and the nature of the surfactant molecules used in the syntheses of organoclay strongly affect the sorption capacity of the clay mineral. Further, it was found that both the laterite and bentonite based organoclays efficiently removed the edible and hydrocarbon oil content from lab prepared emulsions; however, the adsorption capacity of clay mineral was greatly influenced by the nature of hydrophobic compounds as well.

Assessment of local management practices on the population ecology of some medicinal plants in the coniferous forest of Northern Parts of Pakistan.

A study on the assessment of local management practices on the population of three medicinal plants viz.: Persicaria amplexicaule. D. Don., Valeriana jatamansi Jones and Viola serpens Wall ex Roxb was conducted during 2002-2004 in the coniferous forest of Northern Parts of Pakistan. The objective of the study was to know the impact of current management practices on the population size of targeted plants. The study showed that the involvement of locals in the gathering of targeted plants varied with the change in elevation. Among the targeted plants V. serpens was collected by large majorities of people (83.3%) at 2700 m followed by 72% at 2300 m and 37% at 1900 m. V. jatamansi was harvested by a small number of people (18.1%) at 1900 and 2300 m each, followed by 8.3% at 2700 m. While P. amplexicaule was harvested by a few collectors (9.1%) at 1900 m and 9.6% at 2300 m followed by 8.3% at 2700 m. The study concluded that these species have been extracted so heavily in the past that they are found now sparsely in some sites of the study area. Secondly, due to loss of its habitat by deforestation and encroachment of land for cultivation its population is on the decline towards extinction. Therefore, the current study recommends the conservation of the remaining populations of targeted plants through active participation of local communities.

Sonographic biophysical profile in detection of foetal hypoxia in 100 cases of suspected high risk pregnancy.

BACKGROUND: The foetus has become increasingly accessible and visible as a patient over the last two decades. Ultrasound imaging has broadened the scope of foetal assessment. Dynamic real time B-Mode ultrasound is used to monitor cluster of biophysical variables, both dynamic and static collectively termed as biophysical profile. The purpose of this study was to determine the effect of sonographic biophysical profile score on perinatal outcome in terms of mortality and morbidity. METHODS: This descriptive study was carried on 100 randomly selected high risk pregnant patients in Radiology Department PGMI, Government Lady Reading Hospital, Peshawar from December 2007 to June 2008. Manning biophysical profile including non-stress was employed for foetal screening, using Toshiba ultrasound machine model Nemio SSA-550A and 7.5 MHZ probe. RESULTS: Out of 100 cases 79 (79%) had a normal biophysical profile in the last scan of 10/10 and had a normal perinatal outcome with 5 minutes Apgar score > 7/10. In 13 (13%) cases Apgar score at 5 minute was < 7/10 and babies were shifted to nursery. There were 2 (2%) false positive cases that showed abnormal biophysical profile scores of 6/10 but babies were born with an Apgar score of 8/10 at 5 minutes. There were 2 (2%) neonatal deaths in this study group. The sensitivity of biophysical profile was 79.1%, specificity 92.9%. Predictive value for a positive test was 98.55%; predictive value for a negative test was 41.93%. CONCLUSION: Biophysical profile is highly accurate and reliable test of diagnosing foetal hypoxia.