Radiological Software Research Articles

Estimating Patient Eligibility And Benefit Of Intravenous Zolendronic Acid In Hip Fracture Patients: A Service Evaluation

Abstract Background Low trauma hip fractures are serious and carry an estimated re-fracture rate of 10.6%, leading increased morbidity, mortality and healthcare cost. Intravenous Zolendronic Acid (IVZ) administration following hip fracture reduces re-fracture risk by approximately 23% and is recommended yearly for three years by National Osteoporosis Guidelines Group (NOGG) 2021. However, a significant treatment gap remains with only one-fifth of patients receiving IVZ pre-discharge, due to implementation challenges, such as suboptimal Vitamin D levels and lack of resources for yearly infusions. Recently published consensus guidelines offer practical advice as to how to overcome these barriers. This service evaluation estimates the proportion of hip fracture patients eligible for IVZ; as well as the re-fracture rate, prior to the introduction of a local IVZ pathway. Methods Approval from local Quality and Patient Safety Department was received. Low trauma hip fracture patients were identified from the local Orthogeriatric database (October 2019 to January 2021). Hospital electronic laboratory and radiology software were used to identify renal function on discharge and evidence of further fractures (at six months, 1 year and 3 years). Subjects were deemed potentially eligible for IVZ if they had an estimated glomerular filtration rate (eGFR) of ≥50 mls/min (a proxy for calculated creatinine clearance ≥30mls/min in this patient cohort). Results Of 463 subjects, 384 (82.9%) had an eGFR ≥50. Re-fracture data was collected for 263 eligible subjects. Seventeen (6.5%) re-fractured within six months, 21 (8%) re-fractured within a year and 45 (17.1%) re-fractured at any stage post discharge. Conclusion IVZ treatment is the most efficacious secondary fracture prevention post-hip fracture, and most patients are eligible for this treatment. Implementing IVZ pathways for hip fracture patients may significantly reduce re-fracture rate, however expansion of resources allocated to Orthogeriatrics and Fracture Liaison teams is required to successfully implement inpatient pathways and ongoing care.

Leveraging the Apple Ecosystem: Easy Viewing and Sharing of Three-dimensional Perforator Visualizations via iPad/iPhone-based Augmented Reality

Summary: We introduce a novel technique using augmented reality (AR) on smartphones and tablets, making it possible for surgeons to review perforator anatomy in three dimensions on the go. Autologous breast reconstruction with abdominal flaps remains challenging due to the highly variable anatomy of the deep inferior epigastric artery. Computed tomography angiography has mitigated some but not all challenges. Previously, volume rendering and different headsets were used to enable better three-dimensional (3D) review for surgeons. However, surgeons have been dependent on others to provide 3D imaging data. Leveraging the ubiquity of Apple devices, our approach permits surgeons to review 3D models of deep inferior epigastric artery anatomy segmented from abdominal computed tomography angiography directly on their iPhone/iPad. Segmentation can be performed in common radiology software. The models are converted to the universal scene description zipped format, which allows immediate use on Apple devices without third-party software. They can be easily shared using secure, Health Insurance Portability and Accountability Act–compliant sharing services already provided by most hospitals. Surgeons can simply open the file on their mobile device to explore the images in 3D using “object mode” natively without additional applications or can switch to AR mode to pin the model in their real-world surroundings for intuitive exploration. We believe patient-specific 3D anatomy models are a powerful tool for intuitive understanding and communication of complex perforator anatomy and would be a valuable addition in routine clinical practice and education. Using this one-click solution on existing devices that is simple to implement, we hope to streamline the adoption of AR models by plastic surgeons.

Anatomical Parameters of Percutaneous, Minimally Invasive, Direct Intralaminar Pars Screw Fixation of Spondylolysis

ObjectiveTo investigate the anatomical parameters of the ideal screw trajectory for percutaneous intralaminar screw fixation of a pars defect in lumbar spondylolysis using computed tomography scans. MethodsUsing advanced radiological software, the ideal intralaminar screw trajectory was determined. The anatomical parameters of this trajectory were analyzed using a total of 80 single-level lumbar tomography scans in patients with spondylolysis at the L4 and L5 levels. The ideal intralaminar screw trajectory started from the inferolateral edge of the lamina and was between the intralaminar region, pars defect, and defective pars neck and pedicle. Along this trajectory, the skin–lamina distance, intralaminar screw length, isthmic lamina length and width, defective pars neck width, lateral entry distance of the screw to the center of the spinous process, and sagittal and coronal screw application angles were analyzed. ResultsWhen comparing the L4 and L5 parameters, the mean skin-to-lamina distances were 11-9 cm (p=0.000), intralaminar screw lengths 3.5-3.6 cm (p=0.067), isthmic lamina lengths 2-2 cm (p=0.698), mid-lamina widths 1-1 cm (p=0.941), defective pars neck widths 1-1 cm (p=0.674), screw lateral entry distances according to the spinous process 1-1.5 cm (p=0.000), sagittal screw angles 45°-45° (p=0.870), and coronal screw angles 10°-20° (p=0.000) respectively. There were no differences based on age and gender (p<0.05). ConclusionPercutaneous intralaminar rigid screw fixation of a pars defect in spondylolysis provides minimally invasive, low-profile instrumentation. In spondylolysis, a screw length of 3–4 cm and a screw diameter of 4–5 mm may be sufficient for pars fixation with intralaminar screws.

A novel radiological software prototype for automatically detecting the inner ear and classifying normal from malformed anatomy

BackgroundTo develop an effective radiological software prototype that could read Digital Imaging and Communications in Medicine (DICOM) files, crop the inner ear automatically based on head computed tomography (CT), and classify normal and inner ear malformation (IEM). MethodsA retrospective analysis was conducted on 2053 patients from 3 hospitals. We extracted 1200 inner ear CTs for importing, cropping, and training, testing, and validating an artificial intelligence (AI) model. Automated cropping algorithms based on CTs were developed to precisely isolate the inner ear volume. Additionally, a simple graphical user interface (GUI) was implemented for user interaction. Using cropped CTs as input, a deep learning convolutional neural network (DL CNN) with 5-fold cross-validation was used to classify inner ear anatomy as normal or abnormal. Five specific IEM types (cochlear hypoplasia, ossification, incomplete partition types I and III, and common cavity) were included, with data equally distributed between classes. Both the cropping tool and the AI model were extensively validated. ResultsThe newly developed DICOM viewer/software successfully achieved its objectives: reading CT files, automatically cropping inner ear volumes, and classifying them as normal or malformed. The cropping tool demonstrated an average accuracy of 92.25%. The DL CNN model achieved an area under the curve (AUC) of 0.86 (95% confidence interval: 0.81-0.91). Performance metrics for the AI model were: accuracy (0.812), precision (0.791), recall (0.8), and F1-score (0.766). ConclusionThis study successfully developed and validated a fully automated workflow for classifying normal versus abnormal inner ear anatomy using a combination of advanced image processing and deep learning techniques. The tool exhibited good diagnostic accuracy, suggesting its potential application in risk stratification. However, it is crucial to emphasize the need for supervision by qualified medical professionals when utilizing this tool for clinical decision-making.

DENSITY ANALYSIS OF HARD TISSUES OF CERVICAL REGION OF PERMANENT TEETH OF DIFFERENT GROUPS

Abstract. In the practice of clinical and experimental dentistry, numerous studies are devoted to the study of the dynamics of jaw bone tissue density in the age-related aspect and in various pathological conditions. At the same time, the determination of the mineral density of the hard tissues of the teeth is of practical use only in isolated cases.The aim of the study: fi nding out the features of the ratio of indicators of hard tissue density of permanent teeth of diff erent groups in the cervical region.Material and methods. In order to determine the density of the hard tissues of cervical region, radiographs of 320 intact permanent teeth (n=10 for each permanent dentition tooth), made on a Siemens dental radiovisiography device with Trophy Radiology software, were processed. The images were processed in the VixWin Pro program. The unit of measurement of tissue density is the conventional grayscale value (GSV). Tissue density in the cervical region was determined separately for enamel, cementum, and dentin, the diff erence between the established indicators was presented as a percentage.Results of the study. A signifi cant diff erence in the density of enamel, dentin and cementum of permanent teeth was established. It was found that in the cervical region of incisors, dentin has the highest density, cement has the lowest density; in canines, dentin has the highest density, enamel has the lowest density; in premolars, dentin has the highest density, cementum has the lowest density; in molars, enamel has the highest density, cementum has the lowest density. The enamel and dentin density indicators are the lowest in incisors, then gradually increase in canines and premolars, and reach the maximum value in molars. Cement density indicators are also the lowest in incisors, slightly higher in premolars, still increase in canines and reach the maximum value in molars.Conclusions. When using radiological methods to research the condition of the hard tissues of the teeth, it is the radiological biomarkers that can become an eff ective tool for studying the susceptibility or resistance of teeth to pathological lesions, in the cervical region in particular.

Measurement of Thickness at the Inferior Border of the Mandible Using Computed Tomography Images: A Retrospective Study including 300 Japanese Cases.

Vascularised fibular free flaps are integral to reconstructive surgery for head and neck tumours. We investigated the morphological characteristics of the mandible to improve the incidence of plate-related complications after surgery. Using standard radiological software, thickness measurements of the inferior or posterior margin of the mandible were obtained from computed tomography images of 300 patients at seven sites: (1) mandibular symphysis, (2) midpoint between the mandibular symphysis and mental foramen, (3) mental foramen, (4) midpoint between the mental foramen and antegonial notch, (5) antegonial notch, (6) mandibular angular apex (gonion), and (7) neck lateral border of the dentate cartilage. Relationships between age, sex, height, weight, the number of remaining teeth in the mandible, and the thickness of each mandible were also investigated. Measurement point 1 had the largest median mandibular thickness (11.2 mm), and measurement point 6 had the smallest (5.4 mm). Females had thinner measurements than males at all points, with significant differences at points 1, 2, 3, 4, and 7 (p < 0.001). Age and number of remaining teeth in the mandible did not correlate with mandibular thickness; however, height and weight correlated at all points except point 6. Thickness measurements obtained at the sites provide a practical reference for mandibular reconstruction. Choosing the fixation method based on the measured thickness of the mandible at each site allows for sound plating.

CT-derived psoas muscle area and density are associated with length of stay and discharge disposition after liver transplantation

Prolonged length of stay (LOS) and discharge disposition following liver transplantation are associated with postoperative complications and increased healthcare utilization. This study evaluated the relationship between CT-derived psoas muscle measurements and hospital LOS, intensive care unit (ICU) LOS, and discharge disposition after liver transplant. The psoas muscle was chosen given its ease of measurement with any radiological software. A secondary analysis assessed the relationship between the American Society for Parenteral and Enteral Nutrition and the Academy of Nutrition and Dietetics (ASPEN/AND) malnutrition diagnosis criteria and CT-derived psoas muscle measures. CT-derived measures of psoas muscle density (mHU) and cross-sectional area at the level of the third lumbar vertebrae were obtained from preoperative CT scans of liver transplant recipients. Cross-sectional area measures were corrected for body size to generate a psoas area index variable (cm2/m2; PAI). Each 1-unit increase in PAI was associated with a reduced hospital LOS of 4 days (R2=0.07). Each 5-unit increase in mean Hounsfield units (mHU) was associated with a reduced hospital and ICU LOS of 5 and 1.6 days, respectively (R2=0.22 and 0.14, respectively). Mean PAI and mHU were higher in patients who discharged to home. PAI was reasonably identified through ASPEN/AND malnutrition criteria, but there was no difference in mHU between those with and without malnutrition. Measures of psoas density were associated with both hospital and ICU LOS and discharge disposition. PAI was associated with hospital LOS and discharge disposition. CT-derived measures of psoas density may be a valuable complement to preoperative liver transplant nutrition assessment using traditional ASPEN/AND malnutrition criteria.

Intraoperative MRI-derived volumetric ablation margins and initial correlation with local outcome after MRI-guided cryoablation of renal tumors

PurposeTo assess volumetric ablation margins derived from intraoperative pre- and post-ablation MRI after magnetic resonance imaging (MRI)-guided percutaneous cryoablation of renal tumors and explore its correlation with local treatment success.MethodsRetrospective analysis was performed on 30 patients (mean age 69y) who underwent percutaneous MRI-guided cryoablation between May 2014 and May 2020 for 32 renal tumors (size: 1.6–5.1 cm). Tumor and ice-ball volumes were segmented on intraprocedural pre- and post-ablation MR images using Software Assistant for Interventional Radiology (SAFIR) software. After MRI-MRI co-registration, the software automatically quantified the minimal treatment margin (MTM),defined as the smallest 3D distance between the tumor and ice-ball surface. Local tumor progression (LTP) after cryoablation was assessed on follow-up imaging.ResultsMedian follow-up was 16 months (range: 1–58). Local control after cryoablation was achieved in 26 cases (81%) while LTP occurred in 6 (19%). The intended MTM of ≥5 mm was achieved in 3/32 (9%) cases. Median MTM was significantly smaller for cases with (− 7 mm; IQR:-10 to − 5) vs. without LTP (3 mm; IQR:2 to 4) (P < .001). All cases of LTP had a negative MTM. All negative treatment margins occurred in tumors > 3 cm.ConclusionsDetermination of volumetric ablation margins from intraoperative MRI was feasible and may be useful in predicting local outcome after MRI-guided renal cryoablation. In our preliminary data, an intraoperative MRI-derived minimal margin extending at least 1 mm beyond the MRI-visible tumor led to local control and this was more difficult to achieve in tumors > 3 cm. Ultimately, online margin analysis may be a valuable tool to intraoperatively assess therapy success, but larger prospective studies are needed to establish a reliable threshold for clinical use.

Variance in 3D anatomic localization of surgical margins based on conventional margin labeling in head and neck squamous cell carcinoma

ObjectiveIn head and neck cancer (HNC), positive margins are strongly predictive of treatment failure. We sought to measure the accuracy of localization of margin sampling sites based on conventional anatomic labels using a digital 3D-model. MethodsPreoperative CT scans for 9 patients with HNC treated operatively at our institution were imported into a multiplanar radiology software, which was used to render a digital 3D model of each tumor intended to represent the resection specimen. Surgical margin labels recorded during the operative case were collected from pathology records. Margin labels (N = 64) were presented to participating physicians.Participants were asked to mark the anatomic location of each surgical margin using the 3D-model and corresponding radiographic planes for reference.For each individual margin, the 3D coordinates of each participant’s marker were used to calculate a mean localization point called the geometric centroid. Mean distance from individual markers to the centroid was compared between participantsand margin types. ResultsAmongst 7 surgeons, markers were placed a mean distance of 12.6 mm ([SD] = 7.5) from the centroid.Deep margins were marked with a greater mean distance than mucosal/skin margins (19.6 [24.8] mm vs. 15.3 [14.9] mm, p = 0.034). When asked to relocate a margin following re-resection, surgeons marked a point an average of 20.6 [12.4] mm from their first marker with a range of 3.9– 45.1 mm. ConclusionsRetrospective localization of conventionally labeled margins is an imprecise process with variability across the care team. Future interventions targeting margin documentation and communication may improve sampling precision.

Management of lower limb ischaemia using hybrid techniques: a single-centre experience

Introduction: Modern vascular surgery combines procedures with both open and endovascular techniques, with these hybrid procedures becoming part of routine arterial surgery. Hybrid procedures have been established in this centre with access to a hybrid suite since 2014. The aim of this study was to characterise patients undergoing hybrid procedures including an open groin dissection plus an endovascular component. Methods: A retrospective review of operation notes, electronic health records and radiology software for patients undergoing hybrid revascularisation for critical limb threatening ischaemia (CLTI) or intermittent claudication (IC) between January 2017 and December 2021 was performed. Any open groin surgical procedure including common femoral endarterectomy and/or lower limb bypass plus any endovascular procedure were recorded. Primary outcomes were recorded as stent patency, a composite of tissue healing or symptom resolution, and wound complications including surgical site infections. Secondary outcomes were length of stay, rate of readmission and mortality at 30 days. Results: A total of 98 patients (77 men) of median age 73 years (IQR 68–78) underwent a hybrid procedure during this period. Treatment was for CLTI in 66% of the patients and for IC in 34%. The median length of stay was 5 days. Overall graft and stent patency was 85%. The overall rate of tissue healing and symptom resolution was 92%. The surgical site infection rate was 14% (14/98) and mortality at 30 days was 2%. Conclusion: Hybrid revascularisation is safe and effective in treating CLTI and IC with an acceptable risk of surgical site infections. Our short-term results suggest that hybrid revascularisation should be considered in patients with multilevel disease.

Serum D-Dimer Level and Chest CT Scoring in SARS-Cov-2 Virus Patients - It’s Relevance in Prognostication and Severity of the Disease

Background: COVID -19 has wide range of presentation, from asymptomatic infection to severe viral pneumonia and death. D-dimer &gt;1μg/ml is one of the risk factors for mortality. CT chest plays an important role in early detection and monitoring of disease. Objectives: 1. To compare D-dimer value and CT chest findings in Covid-19 patients. 2. To study platelet count, PT, aPTT and CRP in Covid-19 patients. Methodology: RT-PCR confirmed Covid- 19 patients admitted in hospital investigated with D-dimer and CT chest were included in the study. Case details retrieved from medical records. Venous blood collected and plasma processed in coagulation analyser for PT, aPTT, INR and D-dimer. Platelet count was performed using auto analyser. CT findings were retrieved from radiology software (PACS). Statistical tests used were mean, percentage and Fisher’s exact test (SPSS Version 20). Results: During study period of January-June 2021, 38 patients were included. Mean age was 51.1±15.6 years and M:F ratio 2.8:1. 65.8% patients had comorbidities (25/38). D-dimer elevated in 60.5% (23/38) patients. CT showed 10.53%, 28.94%, 60.53% of patients had affected lungs of &lt;15%, 15%-49% and ≥50% of the total area and showed significant association with D- dimer (P=0.018). 17.4% (4/23) patients with elevated D-dimer did not survive. 15.8% (6/38) patients had low platelet, 23.7% (9/38) had abnormal PT, 70.3% had abnormal aPTT and 89.5% (34/38) had elevated CRP. There was no significant correlation between platelet, PT, aPTT, CRP and D-dimer. Conclusion: D-Dimer is elevated in COVID -19 patients and shows significant association with lung involvement and can be used as prognostic marker.

Iron deposition in multiple sclerosis: overall load or distribution alteration?

BackgroundThough abnormal iron deposition has been reported in specific brain regions in multiple sclerosis (MS), no data exist about whether the overall quantity of iron in the brain is altered or not. We aimed to determine whether the noted aberrant iron deposition in MS brains was a problem of overall load or regional distribution in a cohort of MS patients.MethodsAn experienced neuroradiologist, a radiology software engineer, and four neurologists analysed data from quantitative susceptibility maps reconstructed from 3-T magnetic resonance brain images of 30 MS patients and 15 age- and sex-matched healthy controls. Global brain iron load was calculated, and the regional iron concentrations were assessed in 1,000 regions of interest placed in MS lesions in different locations, normal appearing white matter, thalami, and basal ganglia.ResultsGlobal brain iron load was comparable between patients and controls after adjustment for volume (p = 0.660), whereas the regional iron concentrations were significantly different in patients than in control (p ≤ 0.031). There was no significant correlation between global iron load and clinical parameters, whereas regional iron concentrations correlated with patients’ age, disease duration, and disability grade (p ≤ 0.039).ConclusionsThe aberrant iron deposition noted in MS seems to be a problem of regional distribution rather than an altered global brain iron load.

Radiological risk assessment to marine biota from exposure to NORM from a decommissioned offshore oil and gas pipeline

Scale residues can accumulate on the interior surfaces of subsea petroleum pipes and may incorporate naturally occurring radioactive materials (NORM). The persistent nature of ‘NORM scale’ may result in a radiological dose to the organisms living on or near intact pipelines. Following a scenario of in-situ decommissioning of a subsea pipeline, marine organisms occupying the exteriors or interiors of petroleum structures may have close contact with the scale or other NORM-associated contaminated substances and suffer subsequent radiological effects. This case study used radiological dose modelling software, including the ERICA Tool (v2.0), MicroShield® Pro and mathematical equations, to estimate the likely radiological doses and risks of effects from NORM-contaminated scale to marine biota from a decommissioned offshore oil and gas pipeline. Using activity concentrations of NORM (226Ra, 210Po, 210Pb, 228Ra, 228Th) from a subsea pipeline from Australia, environmental realistic exposure scenarios including radiological exposures from both an intact pipe (external only; accounting for radiation shielding by a cylindrical carbon steel pipe) and a decommissioned pipeline with corrosive breakthrough (resulting in both internal and external radiological exposure) were simulated to estimate doses to model marine organisms. Predicted dose rates for both the external only exposure (ranging from 26 μGy/h to 33 μGy/h) and a corroded pipeline (ranging from 300 μGy/h to 16,000 μGy/h) exceeded screening levels for radiological doses to environmental receptors. The study highlighted the importance of using scale-specific solubility data (i.e., Kd) values for individual NORM radionuclides for ERICA assessments. This study provides an approach for conducting marine organism dose assessments for NORM-contaminated subsea pipelines and highlights scientific gaps required to undertake risk assessments necessary to inform infrastructure decommissioning planning.

Detection of exhaled methane levels for monitoring trauma-related haemorrhage following blunt trauma: study protocol for a prospective observational study

IntroductionEarly recognition and effective treatment of internal bleeding impose a cardinal challenge for trauma teams. The reduction of the superior mesenteric artery (SMA) blood flow is among the first compensatory...

Position statement on endoscopic lung volume reduction in South Africa: 2022 update.

Chronic obstructive pulmonary disease (COPD) remains one of the most common causes of morbidity and mortality in South Africa. Endoscopic lung volume reduction (ELVR) was first proposed by the South African Thoracic Society (SATS) for the treatment of advanced emphysema in 2015. Since the original statement was published, there has been a growing body of evidence that a certain well-defined sub-group of patients with advanced emphysema may benefit from ELVR, to the point where the current Global Initiative for Chronic Obstructive Lung Disease (GOLD) Guidelines and the United Kingdom National Institute for Health and Care Excellence (NICE) advocate the use of endoscopic valves based on level A evidence. Patients aged 40 - 75 years with severe dyspnoea (COPD Assessment Test score ≥10) despite maximal medical therapy and pulmonary rehabilitation, with forced expiratory volume in one second (FEV1) 20 - 50%, hyperinflation with residual volume (RV) >175% or RV/total lung capacity (TLC) >55% and a six-minute walking distance (6MWD) of 100 - 450 m (post-rehabilitation) should be referred for evaluation for ELVR, provided no contraindications (e.g. severe pulmonary hypertension) are present. Further evaluation should focus on the extent of parenchymal tissue destruction on high-resolution computed tomography (HRCT) of the lungs and interlobar collateral ventilation (CV) to identify a potential target lobe. Commercially available radiology software packages and/or an endobronchial catheter system can aid in this assessment. The aim of this statement is to provide the South African medical practitioner and healthcare funders with an overview of the practical aspects and current evidence for the judicious use of the valves and other ELVR modalities which may become available in the country.

A novel clinical trials imaging network platform for RECIST 1.1, and related protocols run on standard radiology software: A pilot at multiple oncology centers.

e13552 Background: Oncologists face the following challenges with clinical trials imaging analysis: non-structured radiology reports, inconsistent lesion measurement between time points, time-consuming and error-prone manual calculations for clinical trials protocols, and lack of dedicated storage and auditable signoff. Clinical Trials Imaging Network (CTIN) is a novel clinical trials imaging platform that allows radiologists to provide oncologists with dedicated clinical trials imaging reads and calculations from non-proprietary standard radiology dictation and PACS software, using RECIST 1.1 and other tumor response criteria. It was piloted at several cancer centers between 2019 and 2021. Methods: An anonymous survey was sent out to the oncologist and research coordinators who have experience using the CTIN program. The survey was designed to gauge the effectiveness of the software. Questions asked included the decrease in turnaround time between initiation of scan and completion of research protocol calculations, and regarding the decrease in time the oncologists personally need to make calculations. Additionally, respondents were inquired regarding the accuracy of the data, and how much time they had to spend verifying the integrity of the data. Results: The survey was sent to approximately 150 recipients, with 32 respondents. 84.4% of respondents said they strongly agreed or agreed that there was a decreased turnaround time between scan initiation, and completion of research protocol calculations, and 15.6% neither agreed nor disagreed. 80% strongly agreed or agreed that there was a decreased time they personally performed the calculations. 25.0% said they saved less than 5 minutes per time point personally performing the calculations, 28.6% said 5-15 minutes, 23.4% 15 to 30 minutes, and 17.8% 30-60 minutes. Users were also asked regarding their time spend verifying the data. 64.5% of people spent less than 5 minutes per time point verifying the integrity and quality of the data. 19.4% spent 5-15 minutes, 12.9% spent 15-30 minutes, and 3.2% 30-60 minutes. No one spent greater than 60 minutes verifying the data. 65.6% of people strongly agreed that they were confident in the accuracy of the data, 25.0% agreed, and 9.4% neither agreed or disagreed. 90.6% of people said that they were very satisfied or satisfied with CTIN. Conclusions: We have piloted an approach to provide clinical trials imaging metrics to oncologists using non-proprietary technology that runs from any standard radiology voice recognition system and PACS. The majority of respondents agreed that they would recommend this system for its time-saving, automated calculation and ease of use, user features. The CTIN platform bridges the gap between general radiology reads and clinical trials imaging reads without the need for dedicated radiology software.

Deep learning prediction of quantitative coronary angiography values using myocardial perfusion images with a CZT camera

PurposeEvaluate the prediction of quantitative coronary angiography (QCA) values from MPI, by means of deep learning. Methods546 patients (67% men) undergoing stress 99mTc-tetrofosmin MPI in a CZT camera in the upright and supine position were included (1092 MPIs). Patients were divided into two groups: ICA group included 271 patients who performed an ICA within 6 months of MPI and a control group with 275 patients with low pre-test probability for CAD and a normal MPI. QCA analyses were performed using radiologic software and verified by an expert reader. Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. A deep learning model was trained using a double cross-validation scheme such that all data could be used as test data as well. ResultsArea under the receiver-operating characteristic curve for the prediction of QCA, with > 50% narrowing of the artery, by deep learning for the external test cohort: per patient 85% [95% confidence interval (CI) 84%-87%] and per vessel; LAD 74% (CI 72%-76%), RCA 85% (CI 83%-86%), LCx 81% (CI 78%-84%), and average 80% (CI 77%-83%). ConclusionDeep learning can predict the presence of different QCA percentages of coronary artery stenosis from MPIs.

Retrospective audit of CT scans performed at a hospital for surgical patients

IntroductionEasy accessibility, high sensitivity and specificity of CT scans have markedly increased its usage in developed countries. Its importance is undeniably considered integral for the diagnosis of various pathologies. However, sometimes this costly resource is wasted when used unnecessary. This paper is an audit on CT scans performed to look for surgical pathologies between July 2018 and April 2019 recapitulating the numbers of CT scan's abnormal and normal findings. MethodologyAnonymized record of all the patients seen by the surgical team in the emergency department was reviewed. Retrospective data of every patient who had the CT scan was taken through Mckesson Radiology software of an Irish Hospital. Analysis was done using SPSS. Findings of 102 CT scans was broken down in to three different groups depending at which departmental level CT was performed, namely:Emergency department, Inpatient and Outpatient. Results102 CT Scans were performed of which 51 (50%) patients out of all the three groups had unremarkable. ConclusionsAdequate history, proper clinical examination and strong clinical knowledge may bring down the number of unnecessary CT scans.

Transgender health and medicine – Are radiological devices prepared?

Background & AimsTo determine if radiological hard- and software offers options beyond the binary female / male classification. MethodsWe surveyed thirteen radiological hardware and six radiological software vendors about the options to enter patient gender. ResultsSix of thirteen hardware and five of six software vendors replied to our inquiry. All vendors except one offered a third option in addition to male / female. ConclusionWe found that most hard- and software systems provide with a third option for patient gender. These systems allow radiology personnel to accurately document patient gender in the medical record and contribute to an inclusive patient experience in the radiology department. Registering the biological sex in addition to gender may further improve medical care.

Deep learning model for measurement of shoulder critical angle and acromion index on shoulder radiographs

Several bone morphological parameters, including the anterior acromion morphology, the lateral acromial angle, the coracohumeral interval, the glenoid inclination, the acromion index (AI), and the shoulder critical angle (CSA), have been proposed to impact the development of rotator cuff tears and glenohumeral osteoarthritis. This study aimed to develop a deep learning tool to automate the measurement of CSA and AI on anteroposterior shoulder radiographs. We used MURA Dataset v1.1, which is a large publicly available musculoskeletal radiograph dataset from the Stanford University School of Medicine. All normal shoulder anteroposterior radiographs were extracted and annotated by an experienced orthopedic surgeon. The annotated images were divided into train (1004), validation (174), and test (93) sets. We use pytorch_segmentation_models for U-Net implementation and PyTorch framework for training the model. The test set was used for final evaluation of the model. The mean absolute error for CSA and AI between human-performed and machine-performed measurements on the test set with 93 images was 1.68° (95% CI 1.406°-1.979°) and 0.03 (95% CI 0.02 - 0.03), respectively. A deep learning model can precisely and accurately measure CSA and AI in shoulder anteroposterior radiographs. A tool of this nature makes large-scale research projects feasible and holds promise as a clinical application if integrated with a radiology software program.