An NHS Trust comparison of reporting radiographers and consultant radiologists ability to identify cancer on chest radiographs with confirmation through a Fast track CT thorax referral system.

INTRODUCTION: The National Institute for Health and Care Excellence (NICE) recommends that GPs initially refer patients with suspected lung cancer for a chest X-ray (CXR). The Radiology department has a 'fast track system' to identify those patients who may have lung cancer on CXR and are referred for a CT thorax with contrast to help determine a cancer diagnosis. This fast track system was put in place to ensure the NICE guidelines and NHS England's standards on a faster cancer diagnosis are being met. This audit studied the ability of radiologists and reporting radiographers to identify lung cancer on CXRs and the accuracy of the fast-track system. METHODS: 846 cases with lung alerts were analysed and 545 CXRs were audited. The CXRs were split into images reported by radiologists (168) and those reported by reporting radiographers (377). CT thorax results were collected through PACS and Cerner computer systems to identify if the 'fast track' system had yielded a "positive", "negative", or "other findings" result for lung cancer. RESULTS: 32.8% (179) of CXRs flagged for lung cancer were positive, 40.6% (221) were negative, and 26.6% (145) had other findings. Chi square statistical test showed no significant difference (p = 0.14) between the two reporting groups in their ability to identify lung cancer on CXRs. 27% (38) of CXRs flagged by radiologists and 35% (125) by reporting radiographers were positive for lung cancer. CONCLUSION: This clinical audit indicates, reporting radiographers and radiologists are not statistically significantly different regarding their ability to identify lung cancer on CXRs, when supported by the fast track system. The fast-track system had a 59.4 % accuracy rate, detected by the number of imaging of reports that identified a serious pathology. This concludes that the system is performing well, yet could still be improved. IMPLICATIONS FOR PRACTICE: This audit provides further evidence for the value of developing and deploying reporting radiographers for projection radiography reporting.

Multicentre external validation of a commercial artificial intelligence software to analyse chest radiographs in health screening environments with low disease prevalence.

OBJECTIVES: To externally validate the performance of a commercial AI software program for interpreting CXRs in a large, consecutive, real-world cohort from primary healthcare centres. METHODS: A total of 3047 CXRs were collected from two primary healthcare centres, characterised by low disease prevalence, between January and December 2018. All CXRs were labelled as normal or abnormal according to CT findings. Four radiology residents read all CXRs twice with and without AI assistance. The performances of the AI and readers with and without AI assistance were measured in terms of area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. RESULTS: The prevalence of clinically significant lesions was 2.2% (68 of 3047). The AUROC, sensitivity, and specificity of the AI were 0.648 (95% confidence interval [CI] 0.630-0.665), 35.3% (CI, 24.7-47.8), and 94.2% (CI, 93.3-95.0), respectively. AI detected 12 of 41 pneumonia, 3 of 5 tuberculosis, and 9 of 22 tumours. AI-undetected lesions tended to be smaller than true-positive lesions. The readers' AUROCs ranged from 0.534-0.676 without AI and 0.571-0.688 with AI (all p values < 0.05). For all readers, the mean reading time was 2.96-10.27 s longer with AI assistance (all p values < 0.05). CONCLUSIONS: The performance of commercial AI in these high-volume, low-prevalence settings was poorer than expected, although it modestly boosted the performance of less-experienced readers. The technical prowess of AI demonstrated in experimental settings and approved by regulatory bodies may not directly translate to real-world practice, especially where the demand for AI assistance is highest. KEY POINTS: • This study shows the limited applicability of commercial AI software for detecting abnormalities in CXRs in a health screening population. • When using AI software in a specific clinical setting that differs from the training setting, it is necessary to adjust the threshold or perform additional training with such data that reflects this environment well. • Prospective test accuracy studies, randomised controlled trials, or cohort studies are needed to examine AI software to be implemented in real clinical practice.

Concordance rate of radiologists and a commercialized deep-learning solution for chest X-ray: Real-world experience with a multicenter health screening cohort.

PURPOSE: Lunit INSIGHT CXR (Lunit) is a commercially available deep-learning algorithm-based decision support system for chest radiography (CXR). This retrospective study aimed to evaluate the concordance rate of radiologists and Lunit for thoracic abnormalities in a multicenter health screening cohort. METHODS AND MATERIALS: We retrospectively evaluated the radiology reports and Lunit results for CXR at several health screening centers in August 2020. Lunit was adopted as a clinical decision support system (CDSS) in routine clinical practice. Subsequently, radiologists completed their reports after reviewing the Lunit results. The DLA result was provided as a color map with an abnormality score (%) for thoracic lesions when the score was greater than the predefined cutoff value of 15%. Concordance was achieved when (a) the radiology reports were consistent with the DLA results ("accept"), (b) the radiology reports were partially consistent with the DLA results ("edit") or had additional lesions compared with the DLA results ("add"). There was discordance when the DLA results were rejected in the radiology report. In addition, we compared the reading times before and after Lunit was introduced. Finally, we evaluated systemic usability scale questionnaire for radiologists and physicians who had experienced Lunit. RESULTS: Among 3,113 participants (1,157 men; mean age, 49 years), thoracic abnormalities were found in 343 (11.0%) based on the CXR radiology reports and 621 (20.1%) based on the Lunit results. The concordance rate was 86.8% (accept: 85.3%, edit: 0.9%, and add: 0.6%), and the discordance rate was 13.2%. Except for 479 cases (7.5%) for whom reading time data were unavailable (n = 5) or unreliable (n = 474), the median reading time increased after the clinical integration of Lunit (median, 19s vs. 14s, P < 0.001). CONCLUSION: The real-world multicenter health screening cohort showed a high concordance of the chest X-ray report and the Lunit result under the clinical integration of the deep-learning solution. The reading time slight increased with the Lunit assistance.

Not so FAST-Chest ultrasound underdiagnoses traumatic pneumothorax.

BACKGROUND: Ultrasonography for trauma is a widely used tool in the initial evaluation of trauma patients with complete ultrasonography of trauma (CUST) demonstrating equivalence to computed tomography (CT) for detecting clinically significant abdominal hemorrhage. Initial reports demonstrated high sensitivity of CUST for the bedside diagnosis of pneumothorax. We hypothesized that the sensitivity of CUST would be greater than initial supine chest radiograph (CXR) for detecting pneumothorax. METHODS: A retrospective analysis of patients diagnosed with pneumothorax from 2018 through 2020 at a Level I trauma center was performed. Patients included had routine supine CXR and CUST performed prior to intervention as well as confirmatory CT imaging. All CUST were performed during the initial evaluation in the trauma bay by a registered sonographer. All imaging was evaluated by an attending radiologist. Subgroup analysis was performed after excluding occult pneumothorax. Immediate tube thoracostomy was defined as tube placement with confirmatory CXR within 8 hours of admission. RESULTS: There were 568 patients screened with a diagnosis of pneumothorax, identifying 362 patients with a confirmed pneumothorax in addition to CXR, CUST, and confirmatory CT imaging. The population was 83% male, had a mean age of 45 years, with 85% presenting due to blunt trauma. Sensitivity of CXR for detecting pneumothorax was 43%, while the sensitivity of CUST was 35%. After removal of occult pneumothorax (n = 171), CXR was 78% sensitive, while CUST was 65% sensitive (p < 0.01). In this subgroup, CUST had a false-negative rate of 36% (n = 62). Of those patients with a false-negative CUST, 50% (n = 31) underwent tube thoracostomy, with 85% requiring immediate placement. CONCLUSION: Complete ultrasonography of trauma performed on initial trauma evaluation had lower sensitivity than CXR for identification of pneumothorax including clinically significant pneumothorax requiring tube thoracostomy. Using CUST as the primary imaging modality in the initial evaluation of chest trauma should be considered with caution. LEVEL OF EVIDENCE: Diagnostic Test study, Level IV.

Influence of the use of various imaging units and projections on the radiation dose received by children during chest digital radiography.

OBJECTIVE: To investigate the impact of the use of different imaging units and projections on radiation dose and image quality during chest digital radiography (DR) in 3- and 4-year-old children. METHODS: Two hundred forty 3- and 4-year-old participants requiring chest DR were included; they were divided into three groups: supine anterior-posterior projection (APP), standing APP and standing posterior-anterior projection (PAP). Each group included 40 participants who were evaluated using the same imaging unit. The dose area product (DAP) and the entrance surface dose (ESD) were recorded after each exposure. The visual grading analysis score (VGAS) was used to evaluate image quality, and the longitudinal distance (LD) from the apex of the right lung to the apex of the right diaphragm was used to evaluate the inspiration extent. RESULTS: DAP and ESD were significantly lower in the standing PAP and APP groups than in the supine APP group (P<0.05), but LD was significantly higher in the standing PAP and APP groups than in the supine APP group (P<0.05). Additionally, the pulmonary field area was significantly higher for the standing PAP group than for the standing and supine APP groups (P<0.05). The correlations between ESD, DAP, and VGAS were positive (P<0.001), showing that larger ESD and DAP correspond to higher VGAS. The correlations between ESD, DAP, and body mass index (BMI) were also positive (P<0.05), indicating that higher BMI corresponds to larger ESD and DAP. Finally, no differences in DAP, ESD, VGAS, LD, pulmonary field area, or BMI were noted between males and females (P>0.05). CONCLUSION: The radiation dose to superficial organs may be lower with standing PAP than with standing APP during chest DR. Standing PAP should be selected for chest DR in 3- and 4-year-old children, as it may decrease the required radiation dose.

Screening performance of the chest X-ray in adult blunt trauma evaluation: Is it effective and what does it miss?

BACKGROUND: Although chest x-ray (CXR) is often used as a screening tool for thoracic injury in adult blunt trauma assessment, its screening performance is unclear. Using chest CT as the referent standard, we sought to determine the screening performance of CXR for injury. METHODS: We analyzed data from the NEXUS Chest CT study, in which we prospectively enrolled blunt trauma patients older than 14 years who received chest imaging as part of their evaluation at nine level I trauma centers. For this analysis, we included patients who had both CXR and chest CT. We used CT as the referent standard and categorized injuries as clinically major or minor according to an a priori expert panel classification. RESULTS: Of 11,477 patients enrolled, 4501 had both CXR and chest CT; 1496 (33.2%) were found to have injury, of which 256 (17%) were classified as major injury. CXR missed injuries in 818 patients (54.7%), of which 63 (7.7%) were classified as major injuries. For injuries of major clinical significance, CXR had a sensitivity of 75.4% (95% confidence interval [CI] 69.6-80.4%), specificity of 86.2% (95% CI 85.1-87.2%), negative predictive value of 98.3 (95%CI 97.9-98.6%), and positive predictive value of 24.7 (95%CI 22.9-26.7%). For any injury CXR had a sensitivity of 45.3% (95% CI 42.8-47.9%), specificity of 96.6% (95% CI 95.9-97.2%), negative predictive value of 78% (95% CI 77.2-78.8%), and positive predictive value of 86.9% (95% CI 84.5-89.0%). The most common missed major injuries were pneumothorax (30/185; 16.2%), spinal fractures (19/39; 48.7%), and hemothorax (8/70; 11.4%). The most common missed minor injuries were rib fractures (381/836; 45.6%), pulmonary contusion (203/462; 43.9%), and sternal fractures (153/229; 66.8%). CONCLUSIONS: When used alone, without other trauma screening criteria, CXR has poor screening performance for blunt thoracic injury.

Performance and educational training of radiographers in lung nodule or mass detection: Retrospective comparison with different deep learning algorithms.

ABSTRACT: The aim of this investigation was to compare the diagnostic performance of radiographers and deep learning algorithms in pulmonary nodule/mass detection on chest radiograph.A test set of 100 chest radiographs containing 53 cases with no pathology (normal) and 47 abnormal cases (pulmonary nodules/masses) independently interpreted by 6 trained radiographers and deep learning algorithems in a random order. The diagnostic performances of both deep learning algorithms and trained radiographers for pulmonary nodules/masses detection were compared.QUIBIM Chest X-ray Classifier, a deep learning through mass algorithm that performs superiorly to practicing radiographers in the detection of pulmonary nodules/masses (AUCMass: 0.916 vs AUCTrained radiographer: 0.778, P < .001). In addition, heat-map algorithm could automatically detect and localize pulmonary nodules/masses in chest radiographs with high specificity.In conclusion, the deep-learning based computer-aided diagnosis system through 4 algorithms could potentially assist trained radiographers by increasing the confidence and access to chest radiograph interpretation in the age of digital age with the growing demand of medical imaging usage and radiologist burnout.

Usefulness of staging chest-CT in patients with operable breast cancer.

OBJECTIVE: The aim of this study was to investigate the usefulness of staging chest-CT in terms of diagnostic yield and false-referral rate in patients with operable breast cancer. MATERIALS AND METHODS: This study was approved by the institutional review border. In this retrospective study, we reviewed patients who underwent staging chest-CT between January 2014 and June 2016. Reference standard was defined as a combination of pathology and radiologic tumor changes in accordance with primary tumor or metastatic lesions and stability during the 12-month follow-up period. We calculated diagnostic yield and false-referral rates stratified by pathologic stage. The important ancillary findings of staging chest-CT were also recorded. RESULTS: A total of 1,342 patients were included in this study. Of these, four patients (0.3%; 4/1342) had true pulmonary metastasis. Diagnostic yields of stage I, II, III disease were 0.0% (0/521), 0.3% (2/693), and 1.6% (2/128), respectively. The overall false-referral rate was 4.6% (62/1342); false-referral rates of stage I, II, and III disease were 5.0% (26/521), 3.8% (26/693), and 7.8% (10/128), respectively. No occult thoracic metastasis occurred within 12 months of staging chest-CT. Nineteen patients showed significant ancillary findings besides lung metastasis, including primary lung cancer (n = 9). The overall diagnostic yield of ancillary findings was 1.7% (23 of 1342). CONCLUSIONS: The incidence of pulmonary metastasis was near zero for pathologic stages I/II and slightly higher (although still low; 1.6%). for stage III. Considering its low diagnostic yield and substantial false-referral rates, staging chest-CT might not be useful in patients with operable breast cancer.

Proof of Concept: Phantom Study to Ensure Quality and Safety of Portable Chest Radiography Through Glass During the COVID-19 Pandemic.

BACKGROUND: Chest radiography is often used to detect lung involvement in patients with suspected pneumonia. Chest radiography through glass walls of an isolation room is a technique that could be immensely useful in the current COVID-19 pandemic. PURPOSE: The purpose of this study was to ensure quality and radiation safety while acquiring portable chest radiographs through the glass doors of isolation rooms using an adult anthropomorphic thorax phantom. MATERIALS AND METHODS: Sixteen chest radiographs were acquired utilizing different exposure factors without glass, through the smart glass, and through regular glass. Images were scored independently by 2 radiologists for quantum mottle and sharpness of anatomical structures using a 5-point Likert scale. Statistically significant differences in Likert scale scores and entrance surface dose (ESD) between images acquired without glass and through the smart and regular glass were tested. Interreader reliability was also evaluated. RESULTS: Compared with conventional radiography, equal or higher mean image quality scores (mottle and anatomical structures) were observed with the smart glass using 100 kVp at 12 mAs and 20 mAs and 125 kVp at 6.3 mAs (100 kVp at 2 mAs and 125 kVp at 3.2 mAs were used for conventional radiography observations). There was no statistically significant difference in the Likert scale scores for image quality and the entrance surface dose for radiographs acquired without glass, through the smart glass, and through regular glass. Backscatter from the smart glass was minimal at a distance of 3 m and was recorded as zero at a distance of 4 m from the x-ray tube outside an isolation room. CONCLUSIONS: Good-quality portable chest radiographs can be obtained safely through the smart glass doors of the isolation room. However, this technique does result in minor backscatter radiation. Modifications in the exposure factors (such as increasing milliampere seconds) may be required to optimize image quality while using this technique.

Technique, radiation safety and image quality for chest X-ray imaging through glass and in mobile settings during the COVID-19 pandemic.

The COVID-19 pandemic in 2020 has led to preparations within our hospital for an expected surge of patients. This included developing a technique to perform mobile chest X-ray imaging through glass, allowing the X-ray unit to remain outside of the patient's room, effectively reducing the cleaning time associated with disinfecting equipment. The technique also reduced the infection risk of radiographers. We assessed the attenuation of different types of glass in the hospital and the technique parameters required to account for the glass filtration and additional source to image distance (SID). Radiation measurements were undertaken in a simulated set-up to determine the appropriate position for staff inside and outside the room to ensure occupational doses were kept as low as reasonably achievable. Image quality was scored and technical parameter information collated. The alternative to imaging through glass is the standard portable chest X-ray within the room. The radiation safety requirements for this standard technique were also assessed. Image quality was found to be acceptable or borderline in 90% of the images taken through glass and the average patient dose was 0.02 millisieverts (mSv) per image. The majority (67%) of images were acquired at 110 kV, with an average 5.5 mAs and with SID ranging from 180 to 300 cm. With staff positioned at greater than 1 m from the patient and at more than 1 m laterally from the tube head outside the room to minimise scatter exposure, air kerma values did not exceed 0.5 microgray (µGy) per image. This method has been implemented successfully.

Radiation dose reduction and improvement of image quality in digital chest radiography by new spatial noise reduction algorithm.

PURPOSE: To evaluate the image quality of low-dose chest digital radiographic images obtained with a new spatial noise reduction algorithm, compared to a conventional de-noising technique. MATERIALS AND METHODS: In 69 patients, the dose reduction protocol was divided into A, B, and C test groups- 60% (n = 22), 50% (n = 23), and 40% (n = 24) of the baseline dose. In each patient, baseline dose radiographs were obtained with conventional image processing while low-dose images were acquired with new image processing. A set of baseline and low-dose radiographic images per patient was evaluated and scored on a 5-point scale over seven anatomical landmarks (radiolucency of unobscured lung, pulmonary vascularity, trachea, edge of rib, heart border, intervertebral disc space, and pulmonary vessels in the retrocardiac area) and three representative abnormal findings (nodule, consolidation, and interstitial marking) by two thoracic radiologists. A comparison of paired baseline and low-dose images was statistically analyzed using a non-inferiority test based on the paired t-test or the Wilcoxon signed-rank test. RESULTS: In A, B, and C test groups, the mean dose reduction rate of the baseline radiation dose was 63.4%, 53.9%, and 47.8%, respectively. In all test groups, the upper limit of the 95% confidence interval was less than the non-inferiority margin of 0.5 every seven anatomical landmarks and three representative abnormal findings, which suggested that the image quality of the low-dose image was not inferior to that of the baseline dose image even if the maximum average dose reduction rate was reduced to 47.8% of the baseline dose. CONCLUSION: In our study, an image processing technique integrating a new noise reduction algorithm achieved dose reductions of approximately half without compromising image quality for abnormal lung findings and anatomical landmarks seen on chest radiographs. This feature-preserving, noise reduction algorithm adopted in the proposed engine enables a lower radiation dose boundary for the sake of patient's and radiography technologist's radiation safety in routine clinical practice, in compliance with regulatory guidelines.

Evaluating the utility of computed tomography of the chest for gastric cancer staging

Background: International guidelines recommend routine computed tomography (CT) of the chest for gastric cancer staging. In Asian countries, where the incidence of pulmonary metastases is less than 1%, some guidelines recommend chest CT only for gastroesophageal junction cancers. If the incidence of pulmonary metastases is also low in Canada, routine chest CT may not be beneficial. Methods: We performed a retrospective review of patients in northern Alberta with newly diagnosed gastric cancer from January 2010 to July 2016. The primary aim of the study was to determine the incidence of pulmonary metastases at the time of diagnosis in this population. A secondary aim was to identify potential predictors of pulmonary metastases. We reviewed CT reports for pulmonary metastases. Imaging data also included liver metastases, abdominal lymphadenopathy (> 1 cm), ascites and omental or peritoneal nodules. Other data recorded were age, sex, primary tumour location, histologic type and tumour grade. Results: Four hundred and sixty-two patients (311 men, 151 women) were included in the analysis. Pulmonary metastases were identified in 25 patients (5.4%) overall and in 11 of 299 patients (3.7%) whose primary cancer was not in the cardia. On univariate analysis the presence of liver metastases (odds ratio [OR] 7.72, 95% confidence interval [CI] 3.24­18.37, p < 0.001) and abdominal lymphadenopathy (OR 3.30, 95% CI 1.29­8.48, p = 0.01) was associated with an increased risk of pulmonary metastases. Liver metastases retained statistical significance on multivariate analysis (OR 6.17, 95% CI 2.53­15.03, p < 0.001). Conclusion: The incidence of pulmonary metastases at the time of gastric cancer diagnosis is higher in northern Alberta than previously reported in Asian studies. Abdominal lymphadenopathy and liver metastases confer an elevated risk of pulmonary metastases.

Contexte: Les lignes directrices internationales recommandent une tomodensitométrie (TDM) thoracique de routine pour la stadification du cancer de l'estomac. Dans les pays asiatiques, où l'incidence des métastases pulmonaires est inférieure à 1 %, certaines lignes directrices recommandent la TMD thoracique seulement dans les cancers de la jonction gastro-oesophagienne. Si l'incidence des métastases pulmonaires est également faible au Canada, la TDM thoracique de routine pourrait ne pas être bénéfique. Méthodes: Nous avons procédé à une analyse rétrospective des patients du Nord de l'Alberta ayant reçu un diagnostic de cancer de l'estomac entre janvier 2010 et juillet 2016. L'objectif principal de l'étude était de déterminer l'incidence des métastases pulmonaires au moment du diagnostic chez cette population. Un objectif secondaire consistait à identifier les prédicteurs potentiels des métastases pulmonaires. Les rapports de TDM ont été passés en revue pour ce qui est des métastases pulmonaires. Les données provenant des épreuves d'imagerie incluaient aussi les métastases hépatiques, la lymphadénopathie abdominale (> 1 cm), l'ascite et les nodules épiploïques ou péritonéaux. Parmi les autres données consignées, mentionnons l'âge, le sexe, de même que la localisation, le type histologique et le grade de la tumeur principale. Résultats: Quatre cent soixante-deux patients (311 hommes, 151 femmes) ont été inclus dans l'analyse. Globalement, des métastases pulmonaires ont été observées chez 25 patients (5,4 %), et chez 11 patients sur 299 (3,7 %) dont le cancer principal ne se situait pas dans le cardia. À l'analyse univariée, la présence de métastases hépatiques (rapport des cotes [RC] 7,72, intervalle de confiance [IC] de 95 % de 3,24 à 18,37, p < 0,001) et de lymphadénopathie abdominale (RC 3,30, IC de 95 %, de 1,29 à 8,48, p = 0,01) a été associée à un risque accru de métastases pulmonaires. Les métastases hépatiques ont conservé leur portée statistique lors de l'analyse multivariée (RC 6,17, IC de 95 % de 2,53 à 15,03, p < 0,001). Conclusion: L'incidence des métastases pulmonaires au moment où un diagnostic de cancer de l'estomac est posé s'est révélée plus élevée dans le Nord de l'Alberta que dans les rapports d'études asiatiques précédentes. La lymphadénopathie abdominale et les métastases hépatiques confèrent un risque élevé de métastases pulmonaires.

Comparison of image quality and radiation doses between rapid kV-switching and dual-source DECT techniques in the chest.

PURPOSE: To compare image quality and radiation doses for chest DECT acquired with dual-source and rapid-kV switching techniques. MATERIALS AND METHODS: Our institutional Review Board approved retrospective study included 97 patients (54 men, 43 women; 63 ±â€¯14 years) who underwent contrast-enhanced chest DECT with both single source, rapid kV-switching (SS-DECT) and dual source (DS-DECT) techniques per standard of care departmental protocols. Reconstructed images from both scanners had identical section thickness and section interval for virtual monoenergetic and material decomposition iodine (MDI) images. Two thoracic radiologists independently evaluated all DECT for findings, quality of images, perfusion defects (MDI), and presence of artifacts. Radiation dose descriptor, size-specific dose estimates (SSDE), was recorded. Data were analyzed with Wilcoxon Signed Rank and Cohen's Kappa tests. RESULTS: There were no significant differences in patient weight or SSDE for the two DECT techniques (p > 0.06). Both radiologists reported no difference in lesion and artifact evaluation on the virtual monoenergetic images from either technique (p > 0.05). However, SS-DECT (in 63-71/97 patients) had substantial artifactual heterogeneity in pulmonary perfusion on MDI images compared to none on DS-DECT (p < 0.001). CONCLUSION: Despite identical patients and associated radiation doses, there were substantial differences in material decomposition iodine images generated from SS-DECT and DS-DECT techniques. Pulmonary heterogeneity on MDI images from SS-DECT leads to artifactual areas of low perfusion and can confound interpretation of true pulmonary perfusion.

Trends in radiation dose and image quality for pediatric patients with a multidetector CT and a third-generation dual-source dual-energy CT.

AIM: To provide an overview on dose reduction and image quality after the installation of a third-generation dual-source CT (dsCT) in a Pediatric Radiology Department. MATERIALS AND METHODS: We included pediatric patients (< 20 years old) undergoing CT for oncological staging (neck, chest and abdomen) or low-dose chest CT for lung diseases. Each of these two groups were further divided in two age groups (≤ or > 10 years old) including patients scanned in the same period of two consecutive years, in 2017 with a 16-row LightSpeed CT (GE Healthcare) or in 2018 with a Somatom Force dsCT (Siemens Healthineers). Technical parameters such as kVp, mAs, slice thickness, exposure times and dose indicators were retrieved and compared. Image quality was evaluated in consensus by two radiologists on a five-point semiquantitative scale. Nonparametric tests were used. RESULTS: In oncological patients, significantly lower kVp and tube current with better image quality were achieved with the dsCT. Radiation dose (total DLP) was 5-6 times lower with dsCT, thanks also to virtual non-contrast images. In low-dose chest CT, the frequent use of tin filter required higher tube current; a total DLP 3 times lower was achieved with dsCT in patients ≤ 10 years old. The image quality was better with the dsCT in low-dose chest CT protocols. CONCLUSION: The third-generation dsCT provides high-quality images with reduced motion artifacts at lower dose.

Deimplementation of Routine Chest X-rays in Adult Intensive Care Units.

BACKGROUND: Choosing Wisely® is a national initiative to deimplement or reduce low-value care. However, there is limited evidence on the effectiveness of strategies to influence ordering patterns. OBJECTIVE: We aimed to describe the effectiveness of an intervention to reduce daily chest X-ray (CXR) ordering in two intensive care units (ICUs) and evaluate deimplementation strategies. DESIGN: We aimed to describe the effectiveness of an intervention to reduce daily chest X-ray (CXR) ordering in two intensive care units (ICUs) and evaluate deimplementation strategies. SETTING: The study was performed in the medical intensive care unit (MICU) and cardiovascular intensive care unit (CVICU) of an academic medical center in the United States from October 2015 to June 2016. PARTICIPANTS: The initiative included the staff of the MICU and CVICU (physicians, surgeons, nurse practitioners, fellows, residents, medical students, and X-ray technologists). INTERVENTION COMPONENTS: We utilized provider education, peer champions, and weekly data feedback of CXR ordering rates. MEASUREMENTS: We analyzed the CXR ordering rates and factors facilitating or inhibiting deimplementation. RESULTS: Segmented linear time-series analysis suggested a small but statistically significant decrease in CXR ordering rates in the CVICU (P < .001) but not in the MICU. Facilitators of deimplementation, which were more prominent in the CVICU, included engagement of peer champions, stable staffing, and regular data feedback. Barriers included the need to establish goal CXR ordering rates, insufficient intervention visibility, and waning investment among medical residents in the MICU due to frequent rotation and competing priorities. CONCLUSIONS: Intervention modestly reduced CXRs ordered in one of two ICUs evaluated. Understanding why adoption differed between the two units may inform future interventions to deimplement low-value diagnostic tests.

Potential of a machine-learning model for dose optimization in CT quality assurance.

OBJECTIVES: To evaluate machine learning (ML) to detect chest CT examinations with dose optimization potential for quality assurance in a retrospective, cross-sectional study. METHODS: Three thousand one hundred ninety-nine CT chest examinations were used for training and testing of the feed-forward, single hidden layer neural network (January 2016-December 2017, 60% male, 62 ± 15 years, 80/20 split). The model was optimized and trained to predict the volumetric computed tomography dose index (CTDIvol) based on scan patient metrics (scanner, study description, protocol, patient age, sex, and water-equivalent diameter (DW)). The root mean-squared error (RMSE) was calculated as performance measurement. One hundred separate, consecutive chest CTs were used for validation (January 2018, 60% male, 63 ± 16 years), independently reviewed by two blinded radiologists with regard to dose optimization, and used to define an optimal cutoff for the model. RESULTS: RMSE was 1.71, 1.45, and 1.52 for the training, test, and validation dataset, respectively. The scanner and DW were the most important features. The radiologists found dose optimization potential in 7/100 of the validation cases. A percentage deviation of 18.3% between predicted and actual CTDIvol was found to be the optimal cutoff: 8/100 cases were flagged as suboptimal by the model (range 18.3-53.2%). All of the cases found by the radiologists were identified. One examination was flagged only by the model. CONCLUSIONS: ML can comprehensively detect CT examinations with dose optimization potential. It may be a helpful tool to simplify CT quality assurance. CT scanner and DW were most important. Final human review remains necessary. A threshold of 18.3% between the predicted and actual CTDIvol seems adequate for CT quality assurance. KEY POINTS: • Machine learning can be integrated into CT quality assurance to improve retrospective analysis of CT dose data. • Machine learning may help to comprehensively detect dose optimization potential in chest CT, but an individual review of the results by an experienced radiologist or radiation physicist is required to exclude false-positive findings.

Chest CT Scan at Radiation Dose of a Posteroanterior and Lateral Chest Radiograph Series: A Proof of Principle in Lymphangioleiomyomatosis.

BACKGROUND: Given the rising utilization of medical imaging and the risks of radiation, there is increased interest in reducing radiation exposure. The objective of this study was to evaluate, as a proof of principle, CT scans performed at radiation doses equivalent to that of a posteroanterior and lateral chest radiograph series in the cystic lung disease lymphangioleiomyomatosis (LAM). METHODS: From November 2016 to May 2018, 105 consecutive subjects with LAM received chest CT scans at standard and ultra-low radiation doses. Standard and ultra-low-dose images, respectively, were reconstructed with routine iterative and newer model-based iterative reconstruction. LAM severity can be quantified as cyst score (percentage of lung occupied by cysts), an ideal benchmark for validating CT scans performed at a reduced dose compared with a standard dose. Cyst scores were quantified using semi-automated software and evaluated by linear correlation and Bland-Altman analysis. RESULTS: Overall, ultra-low-dose CT scans represented a 96% dose reduction, with a median dose equivalent to 1 vs 22 posteroanterior and lateral chest radiograph series (0.14 mSv; 5th-95th percentile, 0.10-0.20 vs standard dose 3.4 mSv; 5th-95th percentile, 1.5-7.4; P < .0001). The mean difference in cyst scores between ultra-low- and standard-dose CT scans was 1.1% ± 2.0%, with a relative difference in cyst score of 11%. Linear correlation coefficient was excellent at 0.97 (P < .0001). CONCLUSIONS: In LAM chest CT scan at substantial radiation reduction to doses equivalent to that of a posteroanterior and lateral chest radiograph series provides cyst score quantification similar to that of standard-dose CT scan. TRIAL REGISTRY: ClinicalTrials.gov; Nos.: NCT00001465 and NCT00001532; URL: www.clinicaltrials.gov.