Validation of the Elekta iBEAM Evo couchtop modeling in the Monaco treatment planning system.

Recently, carbon fiber (CF) has prevailed as the primary material used in radiotherapy couchtops. Modern couchtops incorporate the CF sandwich design, in which 2 thin CF plates sandwich an air-equivalent polymeric foam. Developments in radiotherapy necessitate irradiation from posterior angles through the couchtop. However, the presence of the couchtop needs proper modeling in the treatment planning system (TPS) due to attenuation; otherwise, the tumor dose is reduced. In the current study, an effort was made with the intent of finding the optimum electron density (ED) values for Elekta's iBEAM Evo couchtop components (CF and Foam Core (FC)) for its proper modeling in Monaco TPS. Also, the attenuation of the beam due to the couchtop's presence was investigated. A cylindrical phantom with an ionization chamber positioned at the isocenter was utilized for the measurements. The phantom was placed centrally on the iBEAM Evo couchtop and was irradiated with an Elekta Infinity linear accelerator's 6, 10, and 15 MV photon beams. The gantry angle was set at 0o and from 120o to 180o with an increment of 10o. The same procedure was designed and followed in Monaco TPS. Measured and calculated dose values were compared by calculating percentage deviation (PD). Attenuation has also been calculated using the measurements of the experimental setup and the Monaco calculations. The values of ED that provided the optimum agreement between measured and Monaco-calculated dose values while minimizing PD were 0.55 g/cm3 for CF, and 0.1 g/cm3 for FC. The maximum values of PD for the beams of 6, 10, and 15 MV were -0.62%, +1,78%, and +2.35%, respectively, for a 5 × 5 cm2 field size. Furthermore, Monaco predicted attenuation from 1.83% to 6.26% (calculated values), while from the measurements, an attenuation from 1.44% to 5.75% (measured values) regarding the posterior angles was found. Thus, good agreement was verified between the TPS calculations and experimental measurements. Elekta's iBEAM Evo couchtop modeling was successfully validated in Monaco TPS. The couchtop's presence alters the patient's dose regarding irradiation from the posterior angles. Due to the attenuation of the beam, proper incorporation, modeling, and validation of the couchtop are necessary to improve the radiotherapy outcome and ensure that each patient receives the optimal treatment.

Assessment of organ doses, peak skin doses and effective doses in patients undergoing anterior cervical discectomy and fusion utilising VirtualDose-IR software.

In this study, the effect of patient- and procedure-related parameters on organ doses (ODs), peak skin dose (PSD) and effective dose (E) during anterior cervical discectomy and fusion (ACDF) was evaluated. Patient- and procedure-related parameters, as well as fluoroscopy time, kerma-area product (KAP), cumulative air-kerma (Kair) and incident Kair, were analysed for 50 ACDF procedures performed with a mobile C-arm. These parameters were inserted in VirtualDose-IR software implementing sex-specific and body mass index (BMI)-adjustable anthropomorphic phantoms to calculate OD, PSD and E. The BMI, gender and type of implants did not significantly affect KAP, incident Kair, PSD and E. However, the type of fusion significantly affected the E. The single fusions in C5/C6 resulted in significantly higher KAP, incident Kair and E than C4/C5 levels, while those performed in C6/C7 resulted in significantly higher E and PSD than C4/C5 levels. The thyroid, oesophagus and salivary glands received the largest doses in all groups studied. The BMI did not significantly affect ODs. The salivary glands absorbed significantly higher doses in males than females, while the extrathoracic region's dose significantly increased for multi- than single-level fusions. The fusions in C6/C7 resulted in significantly higher oesophagus and thyroid doses than C3/C4 and C4/C5 levels, as well as fusions performed in C5/C6 compared with C4/C5 levels. The data presented here could be used by the neurosurgeons as a comparator for future studies in optimising radiation protection during ACDF procedures in the operating theatre by keeping the ODs, PSD and E as low as reasonably practicable.

Patient Dose Estimation in Computed Tomography-Guided Biopsy Procedures.

This study establishes typical Diagnostic Reference Levels (DRL) values and assesses patient doses in computed tomography (CT)-guided biopsy procedures. The Effective Dose (ED), Entrance Skin Dose (ESD), and Size-Specific Dose Estimate (SSDE) were calculated using the relevant literature-derived conversion factors. A retrospective analysis of 226 CT-guided biopsies across five categories (Iliac bone, liver, lung, mediastinum, and para-aortic lymph nodes) was conducted. Typical DRL values were computed as median distributions, following guidelines from the International Commission on Radiological Protection (ICRP) Publication 135. DRLs for helical mode CT acquisitions were set at 9.7 mGy for Iliac bone, 8.9 mGy for liver, 8.8 mGy for lung, 7.9 mGy for mediastinal mass, and 9 mGy for para-aortic lymph nodes biopsies. In contrast, DRLs for biopsy acquisitions were 7.3 mGy, 7.7 mGy, 5.6 mGy, 5.6 mGy, and 7.4 mGy, respectively. Median SSDE values varied from 7.6 mGy to 10 mGy for biopsy acquisitions and from 11.3 mGy to 12.6 mGy for helical scans. Median ED values ranged from 1.6 mSv to 5.7 mSv for biopsy scans and from 3.9 mSv to 9.3 mSv for helical scans. The study highlights the significance of using DRLs for optimizing CT-guided biopsy procedures, revealing notable variations in radiation exposure between helical scans covering entire anatomical regions and localized biopsy acquisitions.

A retrospective survey to establish institutional diagnostic reference levels for CT urography examinations based on clinical indications: preliminary results.

Objective. To establish institutional diagnostic reference levels (IDRLs) based on clinical indications (CIs) for three- and four-phase computed tomography urography (CTU).Methods. Volumetric computed tomography dose index (CTDIvol), dose-length product (DLP), patients' demographics, selected CIs like lithiasis, cancer, and other diseases, and protocols' parameters were retrospectively recorded for 198 CTUs conducted on a Toshiba Aquilion Prime 80 scanner. Patients were categorised based on CIs and number of phases. These groups' 75th percentiles of CTDIvoland DLP were proposed as IDRLs. The mean, median and IDRLs were compared with previously published values.Results. For the three-phase protocol, the CTDIvol(mGy) and DLP (mGy.cm) were 22.7/992 for the whole group, 23.4/992 for lithiasis, 22.8/1037 for cancer, and 21.2/981 for other diseases. The corresponding CTDIvol(mGy) and DLP (mGy.cm) values for the four-phase protocol were 28.6/1172, 30.6/1203, 27.3/1077, and 28.7/1252, respectively. A significant difference was found in CTDIvoland DLP between the two protocols, among the phases of three-phase (except cancer) and four-phase protocols (except DLP for other diseases), and in DLP between the second and third phases (except for cancer group). The results are comparable or lower than most studies published in the last decade.Conclusions. The CT technologist must be aware of the critical dose dependence on the scan length and the applied exposure parameters for each phase, according to the patient's clinical background and the corresponding imaging anatomy, which must have been properly targeted by the competent radiologist. When clinically feasible, restricting the number of phases to three instead of four could remarkably reduce the patient's radiation dose. CI-based IDRLs will serve as a baseline for comparison with CTU practice in other hospitals and could contribute to national DRL establishment. The awareness and knowledge of dose levels during CTU will prompt optimisation strategies in CT facilities.

Radiotherapy Infrastructure Shielding Calculations: software development for shielding calculations in a linear accelerator radiotherapy room.

This work aimed to develop and validate software that calculates the shielding thickness required for a radiotherapy room with a linear accelerator utilising geometric and dosimetric data. The software "Radiotherapy Infrastructure Shielding Calculations" (RISC) was developed using MATLAB programming. It does not require the installation of the MATLAB platform, and the user only needs to download and install the application, which displays a graphical user interface (GUI). The GUI includes empty cells to insert numerical values for several parameters to calculate the proper shielding thickness. The GUI comprises two main interfaces, one for the primary and one for the secondary barrier calculation. The interface of the primary barrier is divided into four tabs: (a) primary radiation, (b) patient scattered and leakage radiation, (c) IMRT techniques and (d) the shielding cost calculations. The interface of the secondary barrier includes three tabs: (a) patient scattered and leakage radiation, (b) IMRT techniques and (c) the shielding cost calculations. Each tab consists of two sections: one for input and one for output of the necessary data. The RISC is based on the methods and formulae of the NCRP 151 and calculates the primary and secondary barrier thickness for ordinary concrete with a density of 2.35 g/cm3 and the cost for a radiotherapy room with a linear accelerator that performs conventional or IMRT techniques. Calculations can be performed for photon energies of 4, 6, 10, 15, 18, 20, 25 and 30 MV of a dual-energy linear accelerator, while instantaneous dose rate (IDR) calculations are also performed. The RISC has been validated using all comparative examples of NCRP 151 and the calculations from shielding reports of the Varian IX linear accelerator at Methodist Hospital of Willowbrook and Elekta Infinity at the University Hospital of Patras. The RISC is accompanied by two text files: (a) "Terminology," extensively describing all parameters, and (b) "User's Manual," providing useful instructions to the user. The RISC is user-friendly, simple, fast and precise, providing accurate shielding calculations and quickly and easily reproducing different shielding scenarios for a radiotherapy room with a linear accelerator. Additionally, it could be used during the educational process of shielding calculations by graduate students or trainee medical physicists. As a future work, the RISC will be updated with new features such as skyshine radiation, door shielding, and other types of machines and shielding materials.

Current Clinical Knowledge on GORE EXCLUDER Conformable Abdominal Aortic Aneurysm Repair Endoprosthesis: A Case Series and Literature Review.

The GORE EXCLUDER Conformable abdominal aortic aneurysm (AAA) Endoprosthesis (CEXC), is currently the newest stent-graft system for treating patients with AAA. CEXC is approved for patients with proximal aortic neck angles ≤90° with a ≥15 mm aortic neck length or proximal aortic neck angles ≤60° with ≥10 mm aortic neck length. The present study describes a clinical series of 5 males with AAA, one of whom had a ruptured infrarenal AAA and a 90° proximal aortic neck angle. All patients were treated with 100% technical success using the CEXC device. Dosimetric data were recorded regarding the total kerma-area product and total fluoroscopy time. During the 30-day follow-up, no device migration or failure was detected, whereas type Ib and II endoleaks were observed in two patients. The type Ib endoleak required re-intervention with limb extension placement, and the type II endoleak was treated with lumbar artery embolization. This clinical series showed that CEXC has no technical defects or AAA-related mortality. We also reviewed the current knowledge on CEXC's clinical outcomes, showing promising technical and clinical results in some studies, even outside the instructions for use. CEXC expands the vascular surgeons' armamentarium against hostile neck anatomy, as it is the only repositionable endovascular aneurysm repair device available. Multicenter, long-term outcome studies should confirm the promising preliminary results of our case series and the literature review.

Lumbar discectomy and fusion: Organs' dose and effective dose estimation using Monte Carlo simulation.

In this study, the effect of patient- and procedure-related parameters on organs' dose (OD), peak skin dose (PSD) and effective dose (ED) during lumbar discectomy and fusion (LDF) was assessed. Intra-operative parameters obtained from 102 LDFs were inserted into VirtualDose-IR software implementing sex-specific and BMI-adjustable anthropomorphic phantoms for dosimetric calculations. Fluoroscopy time (FT), kerma-area product (KAP), cumulative and incident air-kerma (Kair) were also recorded from the dosimetric report of the mobile C-arm. An increase in KAP, Kair, PSD and ED was found for male or higher BMI patients, multi-level or fusion or L5/S1 procedures. However, a significant difference was found only for PSD and incident Kair between normal and obese patients and for FT between discectomy and discectomy and fusion procedures. The spleen, kidneys and colon received the highest doses. The BMI have a significant impact only for kidneys, pancreas, and spleen doses when comparing obese to overweight and for urinary bladder when comparing overweight to normal patients. Multi-level and fusion procedures resulted in significantly higher doses for lungs, heart, stomach, adrenals, gallbladder and kidneys, while pancreas and spleen doses significantly increased only for multi-level procedures. Additionally, a significant increase was found only for urinary bladder, adrenals, kidneys, and spleen ODs when comparing L5/S1 and L3/L4 levels. The mean ODs were lower compared to the literature. These data may aid neurosurgeons in optimising exposure techniques during LDF to keep patients' dose as low as is practicably possible.

BMI-Based organ doses in endovascular aneurysm repair interventions utilising Monte Carlo simulation.

In this study, the effect of body-mass-index (BMI) on organ doses (ODs) during infrarenal endovascular-aneurysm-repair (EVAR) procedures was evaluated. Patient- and intra-operative data from fifty-nine EVAR procedures were inserted into VirtualDose-IR software to calculate ODs. For overweight, obesity class-I and obesity class-II, ODs were up to 147%, 412% and 775% higher than those for normal weight-patients, respectively. A large variation was observed in ODs published in literature mainly due to the differences in the software and the technical parameters used for the calculations.

FACTORS INFLUENCING FLUOROSCOPY TIME IN ENDOVASCULAR TREATMENT OF ABDOMINAL ANEURYSMS: A RETROSPECTIVE STUDY.

Patients who undergo endovascular aortic aneurysm repair (EVAR) may require prolonged radiation exposure affected by several factors. The objectives of this study were to document fluoroscopy time (FT) during EVAR and identify possible factors that influence it. A retrospective analysis of a 180 patients' database with abdominal infrarenal aortic aneurysms submitted to EVAR during a 7-y period was performed. The FT is evaluated regarding risk factors and comorbidities, graft type and patient-related, clinical and technical parameters. FT's median (interquartile range) was 1011 (698-1500) s. Excluder and C3 Excluder were associated with significantly lower FT values when compared with other grafts. Hypertension, dyslipidemia, age ≥ 70 y, maximum aneurysm diameter ≥ 6 cm and procedure duration ≥2 h resulted in higher FT values. A significantly lower FT was found for the operations performed in the 7th y of the study's period compared with the previous 6 y, mainly because of the use of Excluder or C3 Excluder grafts. However, these grafts did not show any significant difference in FT values during the 7 y. A significant correlation between FT with age and procedure duration was found. Nevertheless, procedure duration is a poor FT predictor in linear and logistic regressions, although is significantly correlated with FT. Dyslipidemia, procedure duration and graft type are independent predictors of FT larger than the median, whereas only the procedure duration is a predictor for FT larger than the 75th percentile value. The identified factors regarding radiation protection issues should be considered when contemplating abdominal aortic aneurysm repair, however, without compromising the procedure's efficacy. Further work is necessary to identify more potential anatomical, clinical and technical factors affecting procedures' complexity and FT and patient radiation dose during EVAR interventions.

Muscle Cross-Sectional Area Segmentation in Transverse Ultrasound Images Using Vision Transformers.

Automatically measuring a muscle's cross-sectional area is an important application in clinical practice that has been studied extensively in recent years for its ability to assess muscle architecture. Additionally, an adequately segmented cross-sectional area can be used to estimate the echogenicity of the muscle, another valuable parameter correlated with muscle quality. This study assesses state-of-the-art convolutional neural networks and vision transformers for automating this task in a new, large, and diverse database. This database consists of 2005 transverse ultrasound images from four informative muscles for neuromuscular disorders, recorded from 210 subjects of different ages, pathological conditions, and sexes. Regarding the reported results, all of the evaluated deep learning models have achieved near-to-human-level performance. In particular, the manual vs. the automatic measurements of the cross-sectional area exhibit an average discrepancy of less than 38.15 mm2, a significant result demonstrating the feasibility of automating this task. Moreover, the difference in muscle echogenicity estimated from these two readings is only 0.88, another indicator of the proposed method's success. Furthermore, Bland−Altman analysis of the measurements exhibits no systematic errors since most differences fall between the 95% limits of agreements and the two readings have a 0.97 Pearson's correlation coefficient (p < 0.001, validation set) with ICC (2, 1) surpassing 0.97, showing the reliability of this approach. Finally, as a supplementary analysis, the texture of the muscle's visible cross-sectional area was examined using deep learning to investigate whether a classification between healthy subjects and patients with pathological conditions solely from the muscle texture is possible. Our preliminary results indicate that such a task is feasible, but further and more extensive studies are required for more conclusive results.

Non-dynamic and multiphase CT protocols for parathyroid glands imaging: a review of technical parameters, radiation dose and diagnostic accuracy.

INTRODUCTION: Our purpose was to review the scientific literature and collect information regarding clinical and technical parameters of different single- or multiphase CT protocols, their diagnostic performance and patient dose during parathyroid imaging. EVIDENCE ACQUISITION: PubMed and Scopus databases were searched for studies investigating the diagnostic performance of CT in detecting parathyroid lesions and the corresponding patients' dose. The following information was retrieved for each article: CT system, number, combination and time interval between phases, scanning length, sensitivity, specificity, accuracy, positive and negative predictive values, contrast enhancement in Hounsfield Units (HUs), technical and exposure parameters, and dose indices. Fifty studies published during the last sixteen years (2005-2021) were reviewed. EVIDENCE SYNTHESIS: A large discrepancy in the number and combination of phases, as well as clinical and technical parameters of the CT protocols was indicated. The variations in patients' doses are mainly due to scanners' technology, number and combination of phases, the extent of scanning length, technical parameters (tube voltage, tube current modulation, pitch, reconstruction algorithms), and patient-related parameters. Technical parameters are not always adjusted appropriately to the clinical question or patient size. These variations indicate a large potential to optimize dose during parathyroid imaging without compromising diagnostic performance. The potential is to decrease the number of phases or use low tube voltage protocols, tube current modulation, iterative reconstruction, and reduce the scanning length during some phases. CONCLUSIONS: The reporting results could inform researchers about the current status of CT parathyroid imaging and guide their future efforts to optimize both patients' dose and corresponding image quality.

Deep Learning Assessment for Mining Important Medical Image Features of Various Modalities.

Deep learning (DL) is a well-established pipeline for feature extraction in medical and nonmedical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. This study evaluates DL methods for their efficiency in revealing and suggesting potential image biomarkers. Eleven biomedical image datasets of various modalities are utilised, including SPECT, CT, photographs, microscopy, and X-ray. Seven state-of-the-art CNNs are employed and tuned to perform image classification in tasks. The main conclusion of the research is that DL reveals potential biomarkers in several cases, especially when the models are trained from scratch in domains where low-level features such as shapes and edges are not enough to make decisions. Furthermore, in some cases, device acquisition variations slightly affect the performance of DL models.

Automatic Extraction of Muscle Parameters with Attention UNet in Ultrasonography.

Automatically delineating the deep and superficial aponeurosis of the skeletal muscles from ultrasound images is important in many aspects of the clinical routine. In particular, finding muscle parameters, such as thickness, fascicle length or pennation angle, is a time-consuming clinical task requiring both human labour and specialised knowledge. In this study, a multi-step solution for automating these tasks is presented. A process to effortlessly extract the aponeurosis for automatically measuring the muscle thickness has been introduced as a first step. This process consists mainly of three parts. In the first part, the Attention UNet has been incorporated to automatically delineate the boundaries of the studied muscles. Afterwards, a specialised post-processing algorithm was utilised to improve (and correct) the segmentation results. Lastly, the calculation of the muscle thickness was performed. The proposed method has achieved similar to a human-level performance. In particular, the overall discrepancy between the automatic and the manual muscle thickness measurements was equal to 0.4 mm, a significant result that demonstrates the feasibility of automating this task. In the second step of the proposed methodology, the fascicle's length and pennation angle are extracted through an unsupervised pipeline. Initially, filtering is applied to the ultrasound images to further distinguish the tissues from the other muscle structures. Later, the well-known K-Means algorithm is used to isolate them successfully. As the last step, the dominant angle of the segmented muscle tissues is reported and compared with manual measurements. The proposed pipeline is showing very promising results in the evaluated dataset. Specifically, in the calculation of the pennation angle, the overall discrepancy between the automatic and the manual measurements was less than 2.22° (degrees), once more comparable with the human-level performance. Finally, regarding the fascicle length measurements, the results were divided based on the muscle properties. In the muscles where a large portion (or all) of the fascicles are located between the upper and lower aponeuroses, the proposed pipeline exhibits superb performance; otherwise, overall accuracy deteriorates due to errors caused by the trigonometric approximations needed for the length calculation.

Organs' absorbed dose and comparison of different methods for effective dose calculation in computed tomography of parathyroid glands.

OBJECTIVE: To estimate organs' absorbed dose from the two-phase CT of parathyroid glands, effective dose (ED) based on three different methods, and compare the dose values with those reported by other published protocols. METHODS: Volumetric-computed-tomography-dose-index (CTDIvol), dose-length-product (DLP), and the corresponding scan length during each phase of a parathyroid protocol were recorded, for seventy-six patients. One k-factor, and two different k-factors for the neck and chest area were used to estimate the ED from DLP. A Monte Carlo software, VirtualDoseCT, was also used for the estimation of organs' absorbed dose and ED. RESULTS: Two-phase parathyroid CT resulted in a mean ED of 3.93 mSv, 4.29 mSv and 4.21 mSv according to the one k-factor, two k-factors, and VirtualDoseCT methods, respectively. The two k-factors method resulted in a slight overestimation of 1.9% in total ED compared to VirtualDoseCT. No statistically significant difference was found in ED values between these methods (Wilcoxon test, p > 0.05), except for female patients in the pre-contrast phase. The organs inside the scanning field of view (SFOV) received the following doses: thymus 23.3 mGy, lungs 11.5 mGy, oesophagus 9.2 mGy, thyroid 6.9 mGy, and breast 6.3 mGy. The ED and organs' dose (OD) values were significantly lower in the pre-contrast than in the arterial phase (Wilcoxon test, p < 0.001). A statistically significant difference was observed between male and female patients for the pre-contrast phase (Mann-Whitney test, p < 0.05), regarding the ED values obtained with the two k-factors method and VirtualDoseCT software. CONCLUSIONS: The two k-factors method could be applied for the ED estimation in clinical practice, if appropriate software is not available. An extensive range of ED values derived from the literature, mainly depending on the acquisition protocol parameters and the estimation method.

Applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging: A review.

PURPOSE: This paper reviews recent applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging. Recent advances in Deep Learning (DL) and GANs catalysed the research of their applications in medical imaging modalities. As a result, several unique GAN topologies have emerged and been assessed in an experimental environment over the last two years. METHODS: The present work extensively describes GAN architectures and their applications in PET imaging. The identification of relevant publications was performed via approved publication indexing websites and repositories. Web of Science, Scopus, and Google Scholar were the major sources of information. RESULTS: The research identified a hundred articles that address PET imaging applications such as attenuation correction, de-noising, scatter correction, removal of artefacts, image fusion, high-dose image estimation, super-resolution, segmentation, and cross-modality synthesis. These applications are presented and accompanied by the corresponding research works. CONCLUSION: GANs are rapidly employed in PET imaging tasks. However, specific limitations must be eliminated to reach their full potential and gain the medical community's trust in everyday clinical practice.

DOSIMETRIC EVALUATION OF THE TWO-PHASE COMPUTED TOMOGRAPHY IN PARATHYROID GLANDS IMAGING.

This study evaluates the patient radiation dose from the two-phase protocols of two different computed tomography (CT) systems and compares this with that delivered by the other similar protocols previously published. Two hundred and fourteen patients with primary hyperparathyroidism were included in the study with a two-phase CT scan between 2008 and 2020 by using a Toshiba Aquilion Prime 80 and a GE Light Speed 16. The standard 'neck' or a modified 'parathyroid' protocol was used. The patient dose was evaluated in terms of volumetric computed tomography dose index (CTDIvol), dose length product (DLP) and effective dose (ED) per acquisition protocol and CT system. CTDIvol and DLP were recorded retrospectively, while the ED was calculated based on DLP and an appropriate conversion coefficient. Comparisons of patient dose between the two protocols and two CT systems and the corresponding published values were established. A significantly lower patient dose (40.2-43.2%) than the GE system (p < 0.0001) resulted from the Toshiba system. The 'parathyroid' protocol resulted in a 6.5-9.6% lower patient dose than the standard 'neck' protocol. Compared with the literature, the lowest ED value (3.6 mSv) was observed since this protocol consists of a lowered tube voltage of 100 kVp, a reduced scan length for the pre-contrast phase and implementation of an iterative reconstruction algorithm.

KERMA-AREA PRODUCT, ENTRANCE SURFACE DOSE AND EFFECTIVE DOSE IN ABDOMINAL ENDOVASCULAR ANEURYSM REPAIR.

This study aims to evaluate patient radiation dose during fluoroscopically guided endovascular aneurysm repair (EVAR) procedures. Fluoroscopy time (FT) and kerma-area product (KAP) were recorded from 87 patients that underwent EVAR procedures with a mobile C-arm fluoroscopy system. Effective dose (ED) and organs' doses were calculated utilising appropriate conversion coefficients based on the recorded KAP values. Entrance surface dose (ESD) was calculated based on KAP values and technical parameters. The mean FT was 22.7 min (range 6.4-76.8 min), resulting in a mean KAP of 36.6 Gy cm2 (range 2.0-167.8 Gy cm2), a mean ED of 6.2 mSv (range 0.3-28.5 mSv) and a mean ESD of 458 mGy (range 26-2098 mGy). The corresponding median values were 17.4 min, 25.6 Gy cm2, 4.4 mSv and 320 mGy. The threshold of 2 Gy for skin erythema was exceeded in two procedures for a focus-to-skin distance (FSD) of 40 cm and six procedures when an FSD of 30 cm was considered. The highest doses absorbed by the adrenals, kidneys, spleen and pancreas and ranged between 3.7 and 313.3 mGy (average 66.8 mGy), 3.3 and 285.1 mGy (average 60.8 mGy), 1.3 and 111.1 mGy (average 23.7 mGy), 1.1 and 92.1 mGy (average 19.6 mGy), respectively. A wide range of patient doses was reported in the literature. The radiation dose received by the patients was comparative or lower than most of the previously reported values. However, higher doses can be revealed due to the X-ray system's non-optimum use and extended FTs, mainly affected by complex clinical conditions, patients' body habitus and vascular surgeon experience. The large variation of patient doses highlights the potential to optimise the EVAR procedure by considering the balance between the radiation dose and the required image quality. Additional studies need to be conducted in increasing the vascular surgeons' awareness regarding patient dose and radiation protection issues during EVAR procedures.

Automatic classification of solitary pulmonary nodules in PET/CT imaging employing transfer learning techniques.

Early and automatic diagnosis of Solitary Pulmonary Nodules (SPN) in Computed Tomography (CT) chest scans can provide early treatment for patients with lung cancer, as well as doctor liberation from time-consuming procedures. The purpose of this study is the automatic and reliable characterization of SPNs in CT scans extracted from Positron Emission Tomography and Computer Tomography (PET/CT) system. To achieve the aforementioned task, Deep Learning with Convolutional Neural Networks (CNN) is applied. The strategy of training specific CNN architectures from scratch and the strategy of transfer learning, by utilizing state-of-the-art pre-trained CNNs, are compared and evaluated. To enhance the training sets, data augmentation is performed. The publicly available database of CT scans, named as Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), is also utilized to further expand the training set and is added to the PET/CT dataset. The results highlight the effectiveness of transfer learning and data augmentation for the classification task of small datasets. The best accuracy obtained on the PET/CT dataset reached 94%, utilizing a modification proposal of a state-of-the-art CNN, called VGG16, and enhancing the training set with LIDC-IDRI dataset. Besides, the proposed modification outperforms in terms of sensitivity several similar researches, which exploit the benefits of transfer learning. Overview of the experiment setup. The two datasets containing nodule representations are combined to evaluate the effectiveness of transfer learning over the traditional approach of training Convolutional Neural Networks from scratch.

Multi-input deep learning approach for Cardiovascular Disease diagnosis using Myocardial Perfusion Imaging and clinical data.

PURPOSE: Accurate detection and treatment of Coronary Artery Disease is mainly based on invasive Coronary Angiography, which could be avoided provided that a robust, non-invasive detection methodology emerged. Despite the progress of computational systems, this remains a challenging issue. The present research investigates Machine Learning and Deep Learning methods in competing with the medical experts' diagnostic yield. Although the highly accurate detection of Coronary Artery Disease, even from the experts, is presently implausible, developing Artificial Intelligence models to compete with the human eye and expertise is the first step towards a state-of-the-art Computer-Aided Diagnostic system. METHODS: A set of 566 patient samples is analysed. The dataset contains Polar Maps derived from scintigraphic Myocardial Perfusion Imaging studies, clinical data, and Coronary Angiography results. The latter is considered as reference standard. For the classification of the medical images, the InceptionV3 Convolutional Neural Network is employed, while, for the categorical and continuous features, Neural Networks and Random Forest classifier are proposed. RESULTS: The research suggests that an optimal strategy competing with the medical expert's accuracy involves a hybrid multi-input network composed of InceptionV3 and a Random Forest. This method matches the expert's accuracy, which is 79.15% in the particular dataset. CONCLUSION: Image classification using deep learning methods can cooperate with clinical data classification methods to enhance the robustness of the predicting model, aiming to compete with the medical expert's ability to identify Coronary Artery Disease subjects, from a large scale patient dataset.

Factors affecting radiation exposure in endovascular repair of abdominal aortic aneurysms: a pilot study.

BACKGROUND: Radiation exposure during endovascular repair (EVAR) of abdominal aortic aneurysms (AAAs) is a potential issue. Several studies have identified factors affecting radiation exposure, although they are limited. The aim of this study was to identify independent factors affecting radiation exposure in patients with AAA undergoing standard EVAR. METHODS: Forty-eight consecutive patients underwent elective EVAR for infrarenal AAA managed between April 2019 and April 2020. Fluoroscopy time (FT) and kerma area product (KAP) were the main outcome measures. RESULTS: Median (interquartile range) FT and KAP values were 1018 (653-1619) s and 2.68 (2.08-3.81) mGy·m2, respectively. C3 Excluder graft use and main body insertion site from the right femoral were associated with significantly lower FT. Coronary artery disease, endografts with two docking limbs, AAA diameter, neck angle and length, procedure duration, contrast amount, and hospitalization were associated with significantly higher FT. Neck angle was the single independent perioperative factor related to FT higher than the median value observed in the study (P=0.004, odds ratio: 1.073, 95% confidence interval: 1.023-1.126). The use of the C3 Excluder device was associated with lower KAP. AAA diameter, neck angle, procedure duration, contrast medium amount and postoperative hospitalization were associated with higher KAP. AAA diameter was the single independent factor related to KAP higher than the median value observed in the study (P=0.013, odds ratio: 3.73, 95% confidence interval: 1.32-10.56). CONCLUSIONS: This study has identified factors affecting radiation exposure during standard EVAR for infrarenal AAAs. These factors should be taken into account when contemplating AAA repair.