Search

Detecting lung pathologies is critical for precise medical diagnosis. In the realm of diagnostic methods, various approaches, including imaging tests, physical examinations, and laboratory tests, contribute to this process. Of particular note, imaging techniques like X-rays, CT scans, and MRI scans play a pivotal role in identifying lung pathologies with their non-invasive insights. Deep learning, a subset of artificial intelligence, holds significant promise in revolutionizing the detection and diagnosis of lung pathologies. By leveraging expansive datasets, deep learning algorithms autonomously discern intricate patterns and features within medical images, such as chest X-rays and CT scans. These algorithms exhibit an exceptional capacity to recognize subtle markers indicative of lung diseases. Yet, while their potential is evident, inherent limitations persist. The demand for abundant labeled data during training and the susceptibility to data biases challenge their accuracy. To address these formidable challenges, this research introduces a tailored computer-assisted system designed for the automatic retrieval of annotated medical images that share similar content. At its core lies an intelligent deep learning-based features extractor, adept at simplifying the retrieval of analogous images from an extensive chest radiograph database. The crux of our innovation rests upon the fusion of YOLOv5 and EfficientNet within the features extractor module. This strategic fusion synergizes YOLOv5's rapid and efficient object detection capabilities with EfficientNet's proficiency in combating noisy predictions. The result is a distinctive amalgamation that redefines the efficiency and accuracy of features extraction. Through rigorous experimentation conducted on an extensive and diverse dataset, our proposed solution decisively surpasses conventional methodologies. The model's achievement of a mean average precision of 0.488 with a threshold of 0.9 stands as a testament to its effectiveness, overshadowing the results of YOLOv5 + ResNet and EfficientDet, which achieved 0.234 and 0.257 respectively. Furthermore, our model demonstrates a marked precision improvement, attaining a value of 0.864 across all pathologies—a noteworthy leap of approximately 0.352 compared to YOLOv5 + ResNet and EfficientDet. This research presents a significant stride toward enhancing radiologists' workflow efficiency, offering a refined and proficient tool for retrieving analogous annotated medical images. [ABSTRACT FROM AUTHOR]

Renal diseases and urinary tract disorders are causing a global burden, with an estimated prevalence of around 13%. Contrast-enhanced computed tomography urography (CE-CTU) is a well-known diagnostic technique for urinary system diseases for initial diagnosis and, very often, for follow-up. CE-CTU procedure exposes patients to high doses of ionizing radiation; hence, justification and optimization of doses are necessary to maximize the benefits and minimize the patients' risks. This study aims to evaluate radiation doses to patients during CE-CTU procedures and estimate the subsequent radiogenic risk. The study included twenty-seven patients who underwent CE-CTU examination in two different hospitals (National Ribat Hospital (NRH) and National Security Fource Hospital (NSFH)), where 16-slice CT machines from different vendors are used. The variables and significance were analyzed using SPSS and Scheffe's statistical tool. Data collected included the age of patients (19–70 years), the radiation dose received by patients: dose length product (DLP, mGy.cm) and volume CT dose index (CTDIvol (mGy)), and tube current-time product (mAs). Patients' dose measurements per CE-CTU procedure given as (mean and range) was: DLP 3098 (647–5301) (mGy.cm) and CTDIvol 44.11 (15–136) (mGy). The results revealed statistically significant differences in DLP (mGy.cm), CTDIvol (mGy), and mAs, and this could be attributed to discrepancies in protocols, machines, and operators among the hospitals and within each hospital. Considering gender, the variables (age, tube current-time product (mAs), and CTDIvol) showed no statistically significant differences. The radiogenic risks from the CE-CTU procedure were ≈1 per 400. Comparison between the two hospitals showed that the variables varied significantly between the hospitals studied, but no significant differences were found based on gender. CE-CTU with contrast medium exposes patients to high doses. Therefore, proper dose optimization is crucial. • The radiation doses during IVU and the subsequent risks from exposure are studied. • The entrance-surface air kerma (ESAK) and effective dose were quantified. • Calculation of the overall cancer risk yielded 5.85 per million procedures. • The effective and cancer risk are around ten times lower during IVU procedures compared to CTU. [ABSTRACT FROM AUTHOR]

Mammary glands or breasts are radiosensitive organs that makeup 12% of the body's overall radiation sensitivity. According to estimates, Saudi Arabia has a 27.3% overall cancer incidence rate for breast cancer. Recent studies reported that breasts get significant organ equivalent doses during diagnostic procedures with ionizing radiation, even though the breast is not the target organ. The objective of this work is to assess the effective and breast equivalent doses during positron emission tomography (PET)/Computed tomography (CT) imaging examinations. The effective and breast equivalent doses per PET/CT (GE PET/CT 710) examination were quantified using the amount of the injected radiopharmaceutical (MBq) (18F- fluorodeoxyglucose (FDG)), and external doses from CT examinations. The average, standard deviation (SD) and range of examined patients' age (years) and body mass index ((BMI), kg/m2) were 58 ± 11 (39–76) and 30 ± 5 (20.7–43.1), respectively. Constant administered activity (AA, 185 MBq) and tube potential (120 kVp) were used for all patients. The average, SD, and range of the patients effective dose (mSv) from PET/CT (18F- FDG) examination was 8.0 ± 0.93 (7.0–10.0) and 2.075 ± 0.11 (1.91–2.29) in that order. Breast doses are comparable with previous studies during the PET/CT and mammographic examination. Proper justification criteria and dose optimization are essential to lowering excessive exposure while preserving image quality, especially for young females because they have a higher risk of radiation-induced cancer. • Breast doses during PET/CT imaging procedures were evaluated. • Breast absorbed dose depends on CT protocol and administered activity. • The organ equivalent dose ranged from 1.91 to 2.29 mGy per procedure. • Breast doses are comparable with previous studies PET/CT procedures. • Young females have a higher risk of breast cancer due to PET/CT procedure. [ABSTRACT FROM AUTHOR]

The pathology of the urinary system is usually investigated using Intravenous Urography (IVU). The study objectives are to quantify patients' radiation dose and radiation induced malignant tumors risk during IVU examination. The radiation doses during IVU and the subsequent risks from exposure are studied, using data from 50 patients imaged in one hospital. The demographic data given as (mean ± std) was as follows:The age of patients was 39 ± 14 years; height of patients was 1.7 ± 0.1 m, the mass was 69 ± 10 kg and the body-mass-index was 24.3 ± 4.1 kg m−2. The physical exposure parameters recorded were: kVp: 74.04 ± 3.1, mAs: 33.64 ± 4. Moreover, the average number of films per procedure was 5.72 ± 1.49. The entrance-surface air kerma (ESAK) was 2.1 ± 0.64 mGy, and the mean effective dose was 0.131 ± 0.04 mSv. Calculation of the overall cancer risk yielded 5.9 × 10−6 procedures. ESAK (mGy) and effective dose values obtained in this study were comparable with reported studies as shown in the text. The effective and cancer risk are around ten times lower during IVU procedures than for example, contrast enhanced computed tomography urography (CTU) examination. Reduction of doses received by patients to meet the values of the diagnostic reference levels without compromising the quality and clarity of the images is highly recommended. Radiation dosimetry; IVU; Radiology; Cancer risk; medical imaging. • The radiation doses during IVU and the subsequent risks from exposure are studied. • The entrance-surface air kerma (ESAK) and effective dose were quantified. • Calculation of the overall cancer risk yielded 5.85 per million procedures. • Patients received higher doses due to unoptimized imaging protocol. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) frequency is approximately 11% of medical radiological procedures. Nevertheless, CT examinations contribute up to 70% collective doses. CT procedures carried out in pediatric patients represent 33% of CT procedures. This study aimed to assess pediatric doses during chest and abdomen procedures and estimated the projected radiogenic risk. In total, 83 pediatric were divided into four groups, according to their age (years). The patients were ≤six months, six months - ≤3 years, 4 - ≤ 6 years and, 7 - ≤ 15 years. The mean and range of DLP (mGy.cm) and CTDIvol (mGy) for pediatric CT chest were 42 (33–52) and 2 (1.9–2.2), respectively. The mean and range of DLP (mGy.cm) and CTDIvol (mGy) for pediatric CT abdomen pelvic region were 116 (105–129) and 3.8 (3.7–3.9), in that order. Even though pediatric' radiation doses are below the published diagnostic reference levels (DRL), additional dose reduction is required and achievable if the imaging protocol is adjusted according to the child size. • Pediatric doses during CT chest and abdomen procedures were assessed. • The variation in patients' doses was due to the scan length and child weight. • The Patients' radiation doses were lower than available published values. • The study has revealed an indispensable need for justified referring criteria. • Establishing an imaging protocol based on a pediatric subgroup is recommended. [ABSTRACT FROM AUTHOR]