فهرست مطالب f. ansari

We introduced Mask R-CNN+CNN as a deep learning model to classify COVID-19 and non-COVID-19 cases. Radiomic features relevant to COVID-19 was presented for Iranian and other nationalities.

Chest CT images from 800 COVID-19 positive and negative patients were studied. The automated volume of the lung and segmentation of COVID-19 lung lesions were implemented using 3D U-net, Capsule network, and Mask R-CNN on annotated CT images. Deep learning models designed were based on Mask R-CNN, CNN, and Mask R-CNN+CNN algorithms to classify COVID-19 cases. We also explored radiomic features relevant to the COVID-19 pandemic in the lungs for chest CT images and implemented random forest (RF), decision tree (DT), and gradient boosting decision tree (GBDT) algorithms on two datasets.

The Mask R-CNN+CNN model demonstrated a higher classification accuracy (96.39 ± 2.94) compared to the Mask R-CNN and CNN models. The RF algorithm had greater power in differentiating relevant COVID-19 radiomic features compared to DT and GBDT, with an accuracy of at least 91 and an AUC of at least 985 in both datasets. We identified six radiomic features that were relevant to the pathological characteristics of COVID-19 positive/negative patients and were common across all datasets.

This study emphasizes the power of Mask R-CNN+CNN with a ResNet-101 backbone as a CNN algorithm that utilizes bounding box offsets output from Mask R-CNN as the input for classifying COVID-19 cases. Radiomic features extracted from lung CT images might aid the diagnosis of COVID-19 in patients at various stages of the disease.

Although it has some benefits, short-term farmland rental transactions have had negative consequences such as excessive use of water, overuse of chemical fertilizers and pesticides, and farmland degradation. Why are landowners more engaged in short-term land rental contracts and less involved in longer rental contracts, that are more associated with incentives to invest and sustainably use farmland? Based on a post positivist worldview, the present study has chosen a quantitative approach and used a survey strategy to explore factors affecting the participation of landholders in longer farmland rental markets. Using multi-stage sampling, 250 landholders in Razan County who had rented their land, at least once in the past five years, were selected. The study indicated that the landholders' motivations to rent out their farmlands changed by their place of residence (rural/urban). The identified barriers and drivers that require policy attention broadly focus on the security of farmland property rights, competence of tenants and kinship contracts, high risk and profitability of farming activities, and capital constraints in rural areas.