Modeling Epidemiology Data with Machine Learning Technique to Detect Risk Factors for Gastric Cancer.

PURPOSE: Gastric cancer (GC) ranks as the 7th most common cancer worldwide and a leading cause of cancer mortality. In Iran, stomach malignancies are the most common fatal cancers with higher than world average incidence. In recent years, methods like machine learning that provide the opportunity of merging health issues with computational power and learning capacity have caught considerable attention for prediction and diagnosis of diseases. In this study, we aimed to model GC data to find risk factors and identify GC cases in Golestan Cohort Study (GCS), using gradient boosting as a machine learning technique. METHODS: Since the GC class (280) was smaller than not-GC (49,467), "Synthetic Minority Oversampling Technique" was used to balance the dataset. Seventy percent of the data was used to train the gradient boosting algorithm and find effective factors on gastric cancer, and the remaining 30% was used for accuracy assessment. RESULTS: Our results indicated that out of 19 factors, age, social economical status, tea temperature, body mass index, gender, and education were the top six effective factors with impact rates of 0.24, 0.16, 0.13, 0.13, and 0.07, respectively. The trained model classified 70 out of 72 GC patients in the test set, correctly. CONCLUSION: The results indicate that this model can effectively detect gastric cancer (GC) by utilizing important risk factors, thus avoiding the need for invasive procedures. The model's performance is reliable when provided with an adequate amount of input data, and as the dataset expands, its accuracy and generalization improve significantly. Overall, the trained system's success stems from its ability to identify risk factors and identify cancer patients.

Investigating heavy-metal soil contamination state on the rate of stomach cancer using remote sensing spectral features.

Heavy metal (HM) contamination in agricultural soils has been a serious environmental and health problem in the past decades. High concentration of HM threatens human health and can be a risk factor for many diseases such as stomach cancer. In order to investigate the relationship between HM content and stomach cancer, the under-study area should be adequately large so that the possible relationship between soil contamination and the patients' distribution can be studied. Examining soil content in a vast area with traditional techniques like field sampling is neither practical nor possible. However, integrating remote sensing imagery and spectrometry can provide an unexpensive and effective substitute for detecting HM in soil. To estimate the concentration of arsenic (As), chrome (Cr), lead (Pb), nickel (Ni), and iron (Fe) in agricultural soil in parts of Golestan province with Hyperion image and soil samples, spectral transformations were used to preprocess and highlight spectral features, and Spearman's correlation was calculated to select the best features for detecting each metal. The generalized regression neural network (GRNN) was trained with the chosen spectral features and metal containment, and the trained GRNN generated the pollution maps from the Hyperion image. Mean concentration of Cr, As, Fe, Ni, and Pb was estimated at 40.22, 11.8, 21,530.565, 39.86, and 0.5 mg/kg, respectively. Concentrations of As and Fe were near the standard limit and overlying the pollution maps, and patients' distribution showed high concentrations of these metals can be considered as stomach cancer risk factors.

Estimation of trees height and vertical structure using SAR interferometry in uneven-aged and mixed forests.

Estimation of forest height is an important parameter of stands structure that aids in the determination of forest biomass, successional stage dynamics, and the decision of the type of forest management. In addition, estimating the height of trees especially in uneven-aged, massive, and multi-storied forest stands always faces challenges in kind of inventory and accuracy of the assessment. In this research, the synthetic aperture radar (SAR) interferometry technique was used to estimate the height of trees for determining the vertical structure of forest. For this purpose, we focused on an area at the mixed and uneven-aged forest in Iran and evaluated the potential of Envisat ASAR data to characterize the tree height in the forest patches and the digital surface model (DSM) was produced via SAR interferometry. The height of trees and the vertical structure of the forest stands were estimated using produced DSM and Digital elevation Model (DEM). Furthermore, the accuracy of estimated parameters was evaluated with real ground data (11 × 1 ha (100 × 100 m) sample plots). The results indicated that the estimated height of trees was meanly 7.69 m with a 22 m STDV over the reality. Furthermore, the vertical structure in all the plots was three-storied that they are the same as ground truth, but the percentage of the share of trees in the under and middle story was different from the ground truth. In conclusion, the tree height and vertical structure of forest stands can be determined with acceptable accuracy via SAR interferometry and Envisat ASAR data.

Forest structure parameter extraction using SPOT-7 satellite data by object- and pixel-based classification methods.

Using satellite data to extract forest structure mapping parameters assists forest management. In this research, structural parameters including species, density, canopy, and gaps were extracted from SPOT-7 satellite data over Hyrcanian forests (Iran). A detailed ground inventory was initially conducted, over 12 × 1 ha (100 m × 100 m) plots, in which tree coordinates were plotted, using a differential global positioning system (DGPS), along with data on tree species, diameter-at-breast-height and height, as well as canopy dimensions, and canopy gap shapes, sizes, and positions, for each plot. Then, spectral transformations, vegetation indices, and simple spectral ratios were extracted from SPOT-7 data, and a supervised, pixel-based classification method and a support-vector machine algorithm were used to classify and determine tree species types. In addition, canopy tree borders and gaps were classified, using an object-based method, and tree densities per unit area were determined, using the canopy gravity center. Finally, the original ground data was used to perform an accuracy assessment on the extracted information, with the results showing that forest type could be determined with 95% accuracy and a Kappa coefficient of 0.8. Canopy and gap coverage achieved an overall accuracy of 91% (Kappa coefficient: 0.7), and tree densities per hectare were determined, on average, to be 47 trees fewer than reality. In conclusion, we have shown that forest structural parameters could be extracted, with good accuracy, using a combination of pixel- and object-based methods applied to SPOT-7 imaging.

Bare Soil Surface Moisture Retrieval from Sentinel-1 SAR Data Based on the Calibrated IEM and Dubois Models Using Neural Networks.

The main purpose of this study is to investigate the performance of two radar backscattering models; the calibrated integral equation model (CIEM) and the modified Dubois model (MDB) over an agricultural area in Karaj, Iran. In the first part, the performance of the models is evaluated based on the field measurement and the mentioned backscattering models, CIEM and MDB performed with root mean square error (RMSE) of 0.78 dB and 1.45 dB, respectively. In the second step, based on the neural networks (NNS), soil surface moisture is estimated using the two backscattering models, based on neural networks (NNs), from single polarization Sentinel-1 images over bare soils. The inversion results show the efficiency of the single polarized data for retrieving soil surface moisture, especially for VV polarization.