To synthesize lithium ferrite with various Gd concentrations (Li0.5Fe2.5-xGdxO4), x = 0.00, 0.025, 0.05, 0.075, 0.1, solutes were dissolved in glycol, i.e. by using the without water and surfactant (WOWS) sol-gel method. X-ray diffraction (XRD) analysis confirmed that the material possessed an inverse spinel cubic structure and is single phase. Pellets of all samples were sintered at 700 °C and XRD confirmed that samples were crystalline, phase pure and had an inverse spinel cubic lattice. Scanning electron microscopy indicated that the grains were agglomerated and had a predominantly spherical shape. It is concluded that Gd acts as a grain refiner in lithium ferrite up to a Gd concentration of 0.05. AC conductivity and dielectric constant increased by increasing Gd concentration. The Maxwell-Wagner model and Johnsher's power law were used to explain the dielectric properties. DC conductivity was measured from 100 to 600 °C. DC conductivity was explained by the hopping mechanism. It is concluded that DC resistivity and dielectric constant values are related reciprocally in the prepared sample. AC electrical properties were also measured at a constant frequency of 1 MHz in the temperature range from 400 to 600 °C. Gd-substituted lithium ferrite showed high AC conductivity, high DC resistivity and constant dielectric values, but low dielectric loss values as compared to pure lithium ferrite.
Lung cancer is the leading cause of cancer death and morbidity worldwide. Many studies have shown machine learning models to be effective in detecting lung nodules from chest X-ray images. However, these techniques have yet to be embraced by the medical community due to several practical, ethical, and regulatory constraints stemming from the "black-box" nature of deep learning models. Additionally, most lung nodules visible on chest X-rays are benign; therefore, the narrow task of computer vision-based lung nodule detection cannot be equated to automated lung cancer detection. Addressing both concerns, this study introduces a novel hybrid deep learning and decision tree-based computer vision model, which presents lung cancer malignancy predictions as interpretable decision trees. The deep learning component of this process is trained using a large publicly available dataset on pathological biomarkers associated with lung cancer. These models are then used to inference biomarker scores for chest X-ray images from two independent data sets, for which malignancy metadata is available. Next, multi-variate predictive models were mined by fitting shallow decision trees to the malignancy stratified datasets and interrogating a range of metrics to determine the best model. The best decision tree model achieved sensitivity and specificity of 86.7% and 80.0%, respectively, with a positive predictive value of 92.9%. Decision trees mined using this method may be considered as a starting point for refinement into clinically useful multi-variate lung cancer malignancy models for implementation as a workflow augmentation tool to improve the efficiency of human radiologists.