Improving deep learning U-Net++ by discrete wavelet and attention gate mechanisms for effective pathological lung segmentation in chest X-ray imaging.

Since its introduction in 2015, the U-Net architecture used in Deep Learning has played a crucial role in medical imaging. Recognized for its ability to accurately discriminate small structures, the U-Net has received more than 2600 citations in academic literature, which motivated continuous enhancements to its architecture. In hospitals, chest radiography is the primary diagnostic method for pulmonary disorders, however, accurate lung segmentation in chest X-ray images remains a challenging task, primarily due to the significant variations in lung shapes and the presence of intense opacities caused by various diseases.

High Tyrosol and Hydroxytyrosol Intake Reduces Arterial Inflammation and Atherosclerotic Lesion Microcalcification in Healthy Older Populations.

Aging is an important risk factor for cardiovascular diseases and convincing data have shown that chronic low-grade inflammation, which develops with advanced age, contributes significantly to cardiovascular risk. The present study aimed to use F-FDG/F-NaF-PET/CT imaging to, respectively, gauge arterial inflammation and microcalcification in a healthy elderly population and to assess the potential benefits of a tyrosol- and hydroxytyrosol-rich diet on these two markers of atherosclerotic plaque fragility. Eleven healthy participants (mean age 75 ± 5.

Non-calcified active atherosclerosis plaque detection with 18F-NaF and 18F-FDG PET/CT dynamic imaging.

Arterial inflammation is an indicator of atheromatous plaque vulnerability to detach and to obstruct blood vessels in the heart or in the brain thus causing heart attack or stroke. To date, it is difficult to predict the plaque vulnerability. This study was aimed to assess the behavior of 18F-sodium fluoride (18F-NaF) and 18F-fluorodeoxyglucose (18F-FDG) uptake in the aorta and iliac arteries as a function of plaque density on CT images.

DNA damage by radiation as a function of electron energy and interaction at the atomic level with Monte Carlo simulation.

In radiotherapy, X-ray or heavy ion beams target tumors to cause damage to their cell DNA. This damage is mainly induced by secondary low energy electrons. In this paper, we report the DNA molecular breaks at the atomic level as a function of electron energy and types of electron interactions using of Monte Carlo simulation.

Quantification of Hypoxia in Human Glioblastoma using PET with 18F-FMISO.

Purpose: This study aimed to investigate the results of compartmental modeling (CM) and spectral analysis (SA) generated with dynamic 18F-FMISO tumor images. Besides, the regular tissue-to-blood ratio (TBR) images were derived and compared with the dynamic models.

Methods: Nine subjects with glioblastoma underwent PET/CT imaging with the 18F-FMISO tracer.