Automatic identification of hypertension and assessment of its secondary effects using artificial intelligence: A systematic review (2013-2023).

Artificial Intelligence (AI) techniques are increasingly used in computer-aided diagnostic tools in medicine. These techniques can also help to identify Hypertension (HTN) in its early stage, as it is a global health issue. Automated HTN detection uses socio-demographic, clinical data, and physiological signals. Additionally, signs of secondary HTN can also be identified using various imaging modalities. This systematic review examines related work on automated HTN detection. We identify datasets, techniques, and classifiers used to develop AI models from clinical data, physiological signals, and fused data (a combination of both). Image-based models for assessing secondary HTN are also reviewed. The majority of the studies have primarily utilized single-modality approaches, such as biological signals (e.g., electrocardiography, photoplethysmography), and medical imaging (e.g., magnetic resonance angiography, ultrasound). Surprisingly, only a small portion of the studies (22 out of 122) utilized a multi-modal fusion approach combining data from different sources. Even fewer investigated integrating clinical data, physiological signals, and medical imaging to understand the intricate relationships between these factors. Future research directions are discussed that could build better healthcare systems for early HTN detection through more integrated modeling of multi-modal data sources.

Patient-Specific 3D-Printed Low-Cost Models in Medical Education and Clinical Practice.

3D printing has been increasingly used for medical applications with studies reporting its value, ranging from medical education to pre-surgical planning and simulation, assisting doctor-patient communication or communication with clinicians, and the development of optimal computed tomography (CT) imaging protocols. This article presents our experience of utilising a 3D-printing facility to print a range of patient-specific low-cost models for medical applications. These models include personalized models in cardiovascular disease (from congenital heart disease to aortic aneurysm, aortic dissection and coronary artery disease) and tumours (lung cancer, pancreatic cancer and biliary disease) based on CT data. Furthermore, we designed and developed novel 3D-printed models, including a 3D-printed breast model for the simulation of breast cancer magnetic resonance imaging (MRI), and calcified coronary plaques for the simulation of extensive calcifications in the coronary arteries. Most of these 3D-printed models were scanned with CT (except for the breast model which was scanned using MRI) for investigation of their educational and clinical value, with promising results achieved. The models were confirmed to be highly accurate in replicating both anatomy and pathology in different body regions with affordable costs. Our experience of producing low-cost and affordable 3D-printed models highlights the feasibility of utilizing 3D-printing technology in medical education and clinical practice.

Utilizing 3D Slicer to incorporate tomographic images into GATE Monte Carlo simulation for personalized dosimetry in yttrium-90 radioembolization.

PURPOSE: Monte Carlo (MC) simulation is an important technique that can help design advanced and challenging experimental setups. GATE (Geant4 application for tomographic emission) is a useful simulation toolkit for applications in nuclear medicine. Transarterial radioembolization is a treatment for liver cancer, where microspheres embedded with yttrium-90 (90 Y) are administered intra-arterially to the tumor. Personalized dosimetry for this treatment may provide higher dosimetry accuracy compared to the conventional partition model (PM) calculation. However, incorporation of three-dimensional tomographic input data into MC simulation is an intricate process. In this article, 3D Slicer, free and open-source software, was utilized for the incorporation of patient tomographic images into GATE to demonstrate the feasibility of personalized dosimetry in hepatic radioembolization with 90 Y. METHODS: In this article, the steps involved in importing, segmenting, and registering tomographic images using 3D Slicer were thoroughly described, before importing them into GATE for MC simulation. The absorbed doses estimated using GATE were then compared with that of PM. SlicerRT, a 3D Slicer extension, was then used to visualize the isodose from the MC simulation. RESULTS: A workflow diagram consisting of all the steps taken in the utilization of 3D Slicer for personalized dosimetry in 90 Y radioembolization has been presented in this article. In comparison to the MC simulation, the absorbed doses to the tumor and normal liver were overestimated by PM by 105.55% and 20.23%, respectively, whereas for lungs, the absorbed dose estimated by PM was underestimated by 25.32%. These values were supported by the isodose distribution obtained via SlicerRT, suggesting the presence of beta particles outside the volumes of interest. These findings demonstrate the importance of personalized dosimetry for a more accurate absorbed dose estimation compared to PM. CONCLUSION: The methodology provided in this study can assist users (especially students or researchers who are new to MC simulation) in navigating intricate steps required in the importation of tomographic data for MC simulation. These steps can also be utilized for other radiation therapy related applications, not necessarily limited to internal dosimetry.

Experimental assessment on feasibility of computed tomography-based thermometry for radiofrequency ablation on tissue equivalent polyacrylamide phantom.

Purpose: This study aimed to evaluate the effects of various computed tomography (CT) acquisition parameters and metal artifacts on CT number measurement for CT thermometry during CT-guided thermal ablation. Methods: The effects of tube voltage (100-140 kVp), tube current (20-250 mAs), pitch (0.6-1.5) and gantry rotation time (0.5, 1.0 s) as well as metal artifacts from a radiofrequency ablation (RFA) needle on CT number were evaluated using liver tissue equivalent polyacrylamide (PAA) phantom. The correlation between CT number and temperature from 37 to 80 °C was studied on PAA phantom using optimum CT acquisition parameters. Results: No statistical significant difference (p > 0.05) was found on CT numbers under the variation of different acquisition parameters for the same temperature setting. On the other hand, the RFA needle has induced metal artifacts on the CT images of up to 8 mm. The CT numbers decreased linearly when the phantom temperature increased from 37 to 80 °C. A linear regression analysis on the CT numbers and temperature suggested that the CT thermal sensitivity was -0.521 ± 0.061 HU/°C (R2 = 0.998). Conclusion: CT thermometry is feasible for temperature assessment during RFA with the current CT technology, which produced a high CT number reproducibility and stable measurement at different CT acquisition parameters. Despite being affected by metal artifacts, the CT-based thermometry could be further developed as a tissue temperature monitoring tool during CT-guided thermal ablation.

Quantitative and qualitative comparison of low- and high-cost 3D-printed heart models.

Current visualization techniques of complex congenital heart disease (CHD) are unable to provide comprehensive visualization of the anomalous cardiac anatomy as the medical datasets can essentially only be viewed from a flat, two-dimensional (2D) screen. Three-dimensional (3D) printing has therefore been used to replicate patient-specific hearts in 3D views based on medical imaging datasets. This technique has been shown to have a positive impact on the preoperative planning of corrective surgery, patient-doctor communication, and the learning experience of medical students. However, 3D printing is often costly, and this impedes the routine application of this technology in clinical practice. This technical note aims to investigate whether reducing 3D printing costs can have any impact on the clinical value of the 3D-printed heart models. Low-cost and a high-cost 3D-printed models based on a selected case of CHD were generated with materials of differing cost. Quantitative assessment of dimensional accuracy of the cardiac anatomy and pathology was compared between the 3D-printed models and the original cardiac computed tomography (CT) images with excellent correlation (r=0.99). Qualitative evaluation of model usefulness showed no difference between the two models in medical applications.

Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images.

Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71% and 97.01% in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings.

Systematic investigation on the validity of partition model dosimetry for 90Y radioembolization using Monte Carlo simulation.

We aimed to investigate the validity of the partition model (PM) in estimating the absorbed doses to liver tumour ([Formula: see text]), normal liver tissue ([Formula: see text]) and lungs ([Formula: see text]), when cross-fire irradiations between these compartments are being considered. MIRD-5 phantom incorporated with various treatment parameters, i.e. tumour involvement (TI), tumour-to-normal liver uptake ratio (T/N) and lung shunting (LS), were simulated using the Geant4 Monte Carlo (MC) toolkit. 108 track histories were generated for each combination of the three parameters to obtain the absorbed dose per activity uptake in each compartment ([Formula: see text], [Formula: see text], and [Formula: see text]). The administered activities, A were estimated using PM, so as to achieve either limiting doses to normal liver, [Formula: see text] or lungs, [Formula: see text] (70 or 30 Gy, respectively). Using these administered activities, the activity uptake in each compartment ([Formula: see text], [Formula: see text], and [Formula: see text]) was estimated and multiplied with the absorbed dose per activity uptake attained using the MC simulations, to obtain the actual dose received by each compartment. PM overestimated [Formula: see text] by 11.7% in all cases, due to the escaped particles from the lungs. [Formula: see text] and [Formula: see text] by MC were largely affected by T/N, which were not considered by PM due to cross-fire exclusion at the tumour-normal liver boundary. These have resulted in the overestimation of [Formula: see text] by up to 8% and underestimation of [Formula: see text] by as high as -78%, by PM. When [Formula: see text] was estimated via PM, the MC simulations showed significantly higher [Formula: see text] for cases with higher T/N, and LS ⩽ 10%. All [Formula: see text] and [Formula: see text] by MC were overestimated by PM, thus [Formula: see text] were never exceeded. PM leads to inaccurate dose estimations due to the exclusion of cross-fire irradiation, i.e. between the tumour and normal liver tissue. Caution should be taken for cases with higher TI and T/N, and lower LS, as they contribute to major underestimation of [Formula: see text]. For [Formula: see text], a different correction factor for dose calculation may be used for improved accuracy.

Recent Update on Radiation Dose Assessment for the State-of-the-Art Coronary Computed Tomography Angiography Protocols.

OBJECTIVES: This study aimed to measure the absorbed doses in selected organs for prospectively ECG-triggered coronary computed tomography angiography (CCTA) using five different generations CT scanners in a female adult anthropomorphic phantom and to estimate the effective dose (HE). MATERIALS AND METHODS: Prospectively ECG-triggered CCTA was performed using five commercially available CT scanners: 64-detector-row single source CT (SSCT), 2 × 32-detector-row-dual source CT (DSCT), 2 × 64-detector-row DSCT and 320-detector-row SSCT scanners. Absorbed doses were measured in 34 organs using pre-calibrated optically stimulated luminescence dosimeters (OSLDs) placed inside a standard female adult anthropomorphic phantom. HE was calculated from the measured organ doses and compared to the HE derived from the air kerma-length product (PKL) using the conversion coefficient of 0.014 mSv∙mGy-1∙cm-1 for the chest region. RESULTS: Both breasts and lungs received the highest radiation dose during CCTA examination. The highest HE was received from 2 × 32-detector-row DSCT scanner (6.06 ± 0.72 mSv), followed by 64-detector-row SSCT (5.60 ± 0.68 and 5.02 ± 0.73 mSv), 2 × 64-detector-row DSCT (1.88 ± 0.25 mSv) and 320-detector-row SSCT (1.34 ± 0.48 mSv) scanners. HE calculated from the measured organ doses were about 38 to 53% higher than the HE derived from the PKL-to-HE conversion factor. CONCLUSION: The radiation doses received from a prospectively ECG-triggered CCTA are relatively small and are depending on the scanner technology and imaging protocols. HE as low as 1.34 and 1.88 mSv can be achieved in prospectively ECG-triggered CCTA using 320-detector-row SSCT and 2 × 64-detector-row DSCT scanners.

Internal radiation dosimetry of orally administered radiotracers for the assessment of gastrointestinal motility.

Radionuclide imaging using (111)In, (99m)Tc and (153)Sm is commonly undertaken for the clinical investigation of gastric emptying, intestinal motility and whole gut transit. However the documented evidence concerning internal radiation dosimetry for such studies is not readily available. This communication documents the internal radiation dosimetry for whole gastrointestinal transit studies using (111)In, (99m)Tc and (153)Sm labeled formulations. The findings were compared to the diagnostic reference levels recommended by the United Kingdom Administration of Radioactive Substances Advisory Committee, for gastrointestinal transit studies.

Fusion of gamma scintigraphic and magnetic resonance images improves the anatomical delineation of radiotracer for the assessment of gastrointestinal transit.

OBJECTIVES: This paper describes the use of gamma scintigraphic and magnetic resonance (MR) fusion images for improving the anatomical delineation of orally administered radiotracers used in gastrointestinal (GI) transit investigations. METHODS: Ten healthy volunteers ingested enteric-coated gelatin capsules containing 4.4 ± 1.1 MBq SmCl3-labelled resin. Four external body markers containing Sm and Gd-DTPA were placed on the left and right lower costal margins and iliac crests of each volunteer. Anterior and posterior planar images were acquired hourly for 9 h, followed by a final single photon emission computed tomography (SPECT) image and subsequent T1-weighted images using a 1.5 T MR system. Coronal scintigraphic images were fused with MR images and assessed for diagnostic information. RESULTS: The fused images revealed a combination of the tissue and organ anatomy with an overlay of the distribution of the tracer. Compared with conventional scintigraphic imaging alone, SPECT-MR fused images improved the localization of spatial and temporal movements of the radiotracer throughout the GI tract. CONCLUSION: Fusion of SPECT and MR images in conjunction with sequential scintigraphic images improved the assessment of segmental GI transit. These have the potential to provide more accurate diagnostic results and are visually powerful images that would have more widespread acceptance by nonspecialists.