Deep learning model for pleural effusion detection via active learning and pseudo-labeling: a multisite study.

BACKGROUND: The study aimed to develop and validate a deep learning-based Computer Aided Triage (CADt) algorithm for detecting pleural effusion in chest radiographs using an active learning (AL) framework. This is aimed at addressing the critical need for a clinical grade algorithm that can timely diagnose pleural effusion, which affects approximately 1.5 million people annually in the United States. METHODS: In this multisite study, 10,599 chest radiographs from 2006 to 2018 were retrospectively collected from an institution in Taiwan to train the deep learning algorithm. The AL framework utilized significantly reduced the need for expert annotations. For external validation, the algorithm was tested on a multisite dataset of 600 chest radiographs from 22 clinical sites in the United States and Taiwan, which were annotated by three U.S. board-certified radiologists. RESULTS: The CADt algorithm demonstrated high effectiveness in identifying pleural effusion, achieving a sensitivity of 0.95 (95% CI: [0.92, 0.97]) and a specificity of 0.97 (95% CI: [0.95, 0.99]). The area under the receiver operating characteristic curve (AUC) was 0.97 (95% DeLong's CI: [0.95, 0.99]). Subgroup analyses showed that the algorithm maintained robust performance across various demographics and clinical settings. CONCLUSION: This study presents a novel approach in developing clinical grade CADt solutions for the diagnosis of pleural effusion. The AL-based CADt algorithm not only achieved high accuracy in detecting pleural effusion but also significantly reduced the workload required for clinical experts in annotating medical data. This method enhances the feasibility of employing advanced technological solutions for prompt and accurate diagnosis in medical settings.

¿Es necesario utilizar protectores de gónadas durante la realización de radiografías de tórax en los lactantes? / Is the use of gonad protection protectors necessary during infants chest radiography?

Introducción y objetivos: Comparar las dosis de radiación en las gónadas con y sin protector gonadal y optimizar el uso de estos protectores al realizar radiografías de tórax a lactantes. Materiales y métodos: Se utilizan 2 maniquíes antropomórficos pediátricos, un sistema de rayos X KXO-50SS/DRX-3724HD, y un sistema de radiografía digital CALNEO Smart C12, con y sin protector de gónadas durante la realización de radiografías de tórax. Se coloca un dosímetro cutáneo en tiempo real en el sistema de rayos X y se inserta un dosímetro cutáneo en tiempo real en la cara anterior de la glándula mamaria, en la cara anterior y posterior de la pelvis verdadera, y en los ovarios y testículos. El sistema de rayos X se irradia 15 veces con maniquíes, con y sin el protector de gónadas. Se comparan los valores de las dosis de entrada del paciente medidos por el dosímetro cutáneo en tiempo real para cada maniquí, con y sin el protector de gónadas. Resultados: Los valores medios de las dosis a la entrada del paciente medidos para la cara anterior a nivel de la pelvis verdadera, con y sin el protector, son 10,00 y 5,00μGy en el recién nacido, y 10,00 y 0,00μGy al año, respectivamente. Los valores medios de las dosis a la entrada del paciente medidos para la cara posterior a nivel de la pelvis verdadera con y sin el protector son de 0,00 y 0,00μGy tanto en el recién nacido como al año, respectivamente. Las dosis a la entrada del paciente medidas no se pueden detectar en los ovarios y los testículos ni con el protector ni sin él. No se observan diferencias significativas en los valores de las dosis a la entrada del paciente medidas en la cara anterior y posterior de la pelvis, los ovarios y los testículos en el recién nacido y al año, con y sin el protector (p>0,05).(AU)

Introduction and objectives: To compare gonad doses with and without a gonad protector and to optimize the use of gonadal protectors in infants thorax radiography. Materials and methods: Two pediatric anthropomorphic phantoms are used: an X-ray system for KXO-50SS/DRX-3724HD, and a digital radiography system for CALNEO Smart C12, with and without a gonad protector during infants thorax radiography. A real time skin dosimeter is placed on the X-ray system, and a real time skin dosimeter is inserted on the front side of the mammary gland, the front and back sides of the true pelvis level, and on the ovaries and testes. The X-ray system is irradiated 15 times using phantoms with and without a gonad protector. The measured entrance patient doses values of for the real time skin dosimeter are compared for each phantom, with and without the gonad protector. Results: The medium of measured entrance patient doses values for front side dose of the true pelvis level with and without the protector are 10.00 and 5.00μGy at newborn, and 10.00 and 0.00μGy at one year, respectively. The medium of measured entrance patient doses values for the back side dose of the true pelvis level with and without the protector are 0.00 and 0.00μGy at both newborn one year, respectively. The measured entrance patient doses cannot be detected in the ovaries and testes with or without the protector. No significant differences are observed in the measured entrance patient doses values for the front and back side doses of the pelvis, ovaries, and testes at newborn and one year, with and without the protector (p>0.05). Conclusions: No significant difference was observed in gonad dose measurements with and without the gonad protector during infants chest radiography. We believe that gonadal protector wearing is not necessary.(AU)

Improving Computer-Aided Thoracic Disease Diagnosis through Comparative Analysis Using Chest X-ray Images Taken at Different Times.

Medical professionals in thoracic medicine routinely analyze chest X-ray images, often comparing pairs of images taken at different times to detect lesions or anomalies in patients. This research aims to design a computer-aided diagnosis system that enhances the efficiency of thoracic physicians in comparing and diagnosing X-ray images, ultimately reducing misjudgments. The proposed system encompasses four key components: segmentation, alignment, comparison, and classification of lung X-ray images. Utilizing a public NIH Chest X-ray14 dataset and a local dataset gathered by the Chiayi Christian Hospital in Taiwan, the efficacy of both the traditional methods and deep-learning methods were compared. Experimental results indicate that, in both the segmentation and alignment stages, the deep-learning method outperforms the traditional method, achieving higher average IoU, detection rates, and significantly reduced processing time. In the comparison stage, we designed nonlinear transfer functions to highlight the differences between pre- and post-images through heat maps. In the classification stage, single-input and dual-input network architectures were proposed. The inclusion of difference information in single-input networks enhances AUC by approximately 1%, and dual-input networks achieve a 1.2-1.4% AUC increase, underscoring the importance of difference images in lung disease identification and classification based on chest X-ray images. While the proposed system is still in its early stages and far from clinical application, the results demonstrate potential steps forward in the development of a comprehensive computer-aided diagnostic system for comparative analysis of chest X-ray images.

Portable Dynamic Chest Radiography: Literature Review and Potential Bedside Applications.

Dynamic digital radiography (DDR) is a high-resolution radiographic imaging technique using pulsed X-ray emission to acquire a multiframe cine-loop of the target anatomical area. The first DDR technology was orthostatic chest acquisitions, but new portable equipment that can be positioned at the patient's bedside was recently released, significantly expanding its potential applications, particularly in chest examination. It provides anatomical and functional information on the motion of different anatomical structures, such as the lungs, pleura, rib cage, and trachea. Native images can be further analyzed with dedicated post-processing software to extract quantitative parameters, including diaphragm motility, automatically projected lung area and area changing rate, a colorimetric map of the signal value change related to respiration and motility, and lung perfusion. The dynamic diagnostic information along with the significant advantages of this technique in terms of portability, versatility, and cost-effectiveness represents a potential game changer for radiological diagnosis and monitoring at the patient's bedside. DDR has several applications in daily clinical practice, and in this narrative review, we will focus on chest imaging, which is the main application explored to date in the literature. However, studies are still needed to understand deeply the clinical impact of this method.

Radiographic Imaging of Community-Acquired Pneumonia: A Case-Based Review.

The chest radiograph is the most common imaging examination performed in most radiology departments, and one of the more common indications for these studies is suspected infection. Radiologists must therefore be aware of less common radiographic patterns of pulmonary infection if they are to add value in the interpretation of chest radiographs for this indication. This review uses a case-based format to illustrate a range of imaging findings that can be associated with acute pulmonary infection and highlight findings that should prompt investigation for diseases other than community-acquired pneumonia to prevent misdiagnosis and delays in appropriate management.

Evaluation of the diagnostic performance of physician lung ultrasound versus chest radiography for pneumonia diagnosis in a peri-urban South African cohort.

BACKGROUND: Lung ultrasound (US), which is radiation-free and cheaper than chest radiography (CXR), may be a useful modality for the diagnosis of pediatric pneumonia, but there are limited data from low- and middle-income countries. OBJECTIVES: The aim of this study was to evaluate the diagnostic performance of non-radiologist, physician-performed lung US compared to CXR for pneumonia in children in a resource-constrained, African setting. MATERIALS AND METHODS: Children under 5 years of age enrolled in a South African birth cohort study, the Drakenstein Child Health Study, who presented with clinically defined pneumonia and had a CXR performed also had a  lung US performed by a study doctor. Each modality was reported by two readers, using standardized methodology. Agreement between modalities, accuracy (sensitivity and specificity) of lung US and inter-rater agreement were assessed. Either consolidation or any abnormality (consolidation or interstitial picture) was considered as endpoints. In the 98 included cases (median age: 7.2 months; 53% male; 69% hospitalized), prevalence was 37% vs. 39% for consolidation and 52% vs. 76% for any abnormality on lung US and CXR, respectively. Agreement between modalities was poor for consolidation (observed agreement=61%, Kappa=0.18, 95% confidence interval [95% CI]: - 0.02 to 0.37) and for any abnormality (observed agreement=56%, Kappa=0.10, 95% CI: - 0.07 to 0.28). Using CXR as the reference standard, sensitivity of lung US was low for consolidation (47%, 95% CI: 31-64%) or any abnormality (5%, 95% CI: 43-67%), while specificity was moderate for consolidation (70%, 95% CI: 57-81%), but lower for any abnormality (58%, 95% CI: 37-78%). Overall inter-observer agreement of CXR was poor (Kappa=0.25, 95% CI: 0.11-0.37) and was significantly lower than the substantial agreement of lung US (Kappa=0.61, 95% CI: 0.50-0.75). Lung US demonstrated better agreement than CXR for all categories of findings, showing a significant difference for consolidation (Kappa=0.72, 95% CI: 0.58-0.86 vs. 0.32, 95% CI: 0.13-0.51). CONCLUSION: Lung US identified consolidation with similar frequency to CXR, but there was poor agreement between modalities. The significantly higher inter-observer agreement of LUS compared to CXR supports the utilization of lung US by clinicians in a low-resource setting.

Retrospectively assessing evaluation and management of artificial-intelligence detected nodules on uninterpreted chest radiographs in the era of radiologists shortage.

PURPOSE: High volumes of chest radiographs (CXR) remain uninterpreted due to severe shortage of radiologists. These CXRs may be informally reported by non-radiologist physicians, or not reviewed at all. Artificial intelligence (AI) software can aid lung nodule detection. Our aim was to assess evaluation and management by non-radiologists of uninterpreted CXRs with AI detected nodules, compared to retrospective radiology reports. MATERIALS AND METHODS: AI detected nodules on uninterpreted CXRs of adults, performed 30/6/2022-31/1/2023, were evaluated. Excluded were patients with known active malignancy and duplicate CXRs of the same patient. The electronic medical records (EMR) were reviewed, and the clinicians' notes on the CXR and AI detected nodule were documented. Dedicated thoracic radiologists retrospectively interpreted all CXRs, and similarly to the clinicians, they had access to the AI findings, prior imaging and EMR. The radiologists' interpretation served as the ground truth, and determined if the AI-detected nodule was a true lung nodule and if further workup was required. RESULTS: A total of 683 patients met the inclusion criteria. The clinicians commented on 386 (56.5%) CXRs, identified true nodules on 113 CXRs (16.5%), incorrectly mentioned 31 (4.5%) false nodules as real nodules, and did not mention the AI detected nodule on 242 (35%) CXRs, of which 68 (10%) patients were retrospectively referred for further workup by the radiologist. For 297 patients (43.5%) there were no comments regarding the CXR in the EMR. Of these, 77 nodules (11.3%) were retrospectively referred for further workup by the radiologist. CONCLUSION: AI software for lung nodule detection may be insufficient without a formal radiology report, and may lead to over diagnosis or misdiagnosis of nodules.

Performance of artificial intelligence-based software for the automatic detection of lung lesions on chest radiographs of patients with suspected lung cancer.

PURPOSE: This study aimed to evaluate the performance of the commercially available artificial intelligence-based software CXR-AID for the automatic detection of pulmonary nodules on the chest radiographs of patients suspected of having lung cancer. MATERIALS AND METHODS: This retrospective study included 399 patients with clinically suspected lung cancer who underwent CT and chest radiography within 1 month between June 2020 and May 2022. The candidate areas on chest radiographs identified by CXR-AID were categorized into target (properly detected areas) and non-target (improperly detected areas) areas. The non-target areas were further divided into non-target normal areas (false positives for normal structures) and non-target abnormal areas. The visibility score, characteristics and location of the nodules, presence of overlapping structures, and background lung score and presence of pulmonary disease were manually evaluated and compared between the nodules detected or undetected by CXR-AID. The probability indices calculated by CXR-AID were compared between the target and non-target areas. RESULTS: Among the 450 nodules detected in 399 patients, 331 nodules detected in 313 patients were visible on chest radiographs during manual evaluation. CXR-AID detected 264 of these 331 nodules with a sensitivity of 0.80. The detection sensitivity increased significantly with the visibility score. No significant correlation was observed between the background lung score and sensitivity. The non-target area per image was 0.85, and the probability index of the non-target area was lower than that of the target area. The non-target normal area per image was 0.24. Larger and more solid nodules exhibited higher sensitivities, while nodules with overlapping structures demonstrated lower detection sensitivities. CONCLUSION: The nodule detection sensitivity of CXR-AID on chest radiographs was 0.80, and the non-target and non-target normal areas per image were 0.85 and 0.24, respectively. Larger, solid nodules without overlapping structures were detected more readily by CXR-AID.

Dynamic chest radiography for pulmonary vascular diseases: clinical applications and correlation with other imaging modalities.

Dynamic chest radiography (DCR) is a novel functional radiographic imaging technique that can be used to visualize pulmonary perfusion without using contrast media. Although it has many advantages and clinical utility, most radiologists are unfamiliar with this technique because of its novelty. This review aims to (1) explain the basic principles of lung perfusion assessment using DCR, (2) discuss the advantages of DCR over other imaging modalities, and (3) review multiple specific clinical applications of DCR for pulmonary vascular diseases and compare them with other imaging modalities.

Clinical Predictors of Major Intrathoracic Injury in Pediatric Blunt Trauma.

OBJECTIVES: Blunt trauma in pediatric patients accounts for a significant proportion of pediatric death from traumatic injury. Currently, there are no clinical decision-making tools available to guide imaging choice in the evaluation of pediatric patients with blunt thoracic trauma (BTT). This study aimed to analyze the rates of missed major intrathoracic injuries on chest x-ray (CXR) and identify clinical risk factors associated with major intrathoracic injuries to formulate a clinical decision-making tool for computed tomography (CT) use in pediatric patients with BTT. METHODS: We performed a retrospective single-center study using an institutional trauma database of pediatric patients. Inclusion criteria included age, blunt trauma, and patients who received a CXR and thoracic CT within 24 hours of presentation. Thoracic CT findings were graded as major, minor, or none, and comparison CXR was used to determine the rate of missed thoracic injuries. Eighty-four patient variables were then collected, and clinically relevant variables associated with major intrathoracic injuries were placed in a logistic regression model to determine the best predictors of major injury in pediatric BTT patients. RESULTS: A total of 180 patients (48.3%) had CXR that missed an injury that was seen on thoracic CT. In our cohort, 20 patients (5.4%) had major injuries that were missed on CXR. Characteristics correlating with major thoracic injuries were older age (odds ratio [OR], 1.125; 95% confidence interval [CI], 1.015-1.247), chest pain (OR, 4.907; 95% CI, 2.173-11.083), abnormal chest auscultation (OR, 3.564; 95% CI, 1.406-9.035), and tachycardia (OR, 2.876; 95% CI, 1.256-6.586). Using these 4 variables, receiver operating characteristic analysis revealed an area under the curve of 0.7903. CONCLUSIONS: Pediatric BTT patients older than 15 years with tachycardia, chest pain, or abnormal chest auscultation are at increased risk for major intrathoracic injuries and may benefit from thoracic CT.

Using AI to Improve Radiologist Performance in Detection of Abnormalities on Chest Radiographs.

Background Chest radiography remains the most common radiologic examination, and interpretation of its results can be difficult. Purpose To explore the potential benefit of artificial intelligence (AI) assistance in the detection of thoracic abnormalities on chest radiographs by evaluating the performance of radiologists with different levels of expertise, with and without AI assistance. Materials and Methods Patients who underwent both chest radiography and thoracic CT within 72 hours between January 2010 and December 2020 in a French public hospital were screened retrospectively. Radiographs were randomly included until reaching 500 radiographs, with about 50% of radiographs having abnormal findings. A senior thoracic radiologist annotated the radiographs for five abnormalities (pneumothorax, pleural effusion, consolidation, mediastinal and hilar mass, lung nodule) based on the corresponding CT results (ground truth). A total of 12 readers (four thoracic radiologists, four general radiologists, four radiology residents) read half the radiographs without AI and half the radiographs with AI (ChestView; Gleamer). Changes in sensitivity and specificity were measured using paired t tests. Results The study included 500 patients (mean age, 54 years ± 19 [SD]; 261 female, 239 male), with 522 abnormalities visible on 241 radiographs. On average, for all readers, AI use resulted in an absolute increase in sensitivity of 26% (95% CI: 20, 32), 14% (95% CI: 11, 17), 12% (95% CI: 10, 14), 8.5% (95% CI: 6, 11), and 5.9% (95% CI: 4, 8) for pneumothorax, consolidation, nodule, pleural effusion, and mediastinal and hilar mass, respectively (P < .001). Specificity increased with AI assistance (3.9% [95% CI: 3.2, 4.6], 3.7% [95% CI: 3, 4.4], 2.9% [95% CI: 2.3, 3.5], and 2.1% [95% CI: 1.6, 2.6] for pleural effusion, mediastinal and hilar mass, consolidation, and nodule, respectively), except in the diagnosis of pneumothorax (-0.2%; 95% CI: -0.36, -0.04; P = .01). The mean reading time was 81 seconds without AI versus 56 seconds with AI (31% decrease, P < .001). Conclusion AI-assisted chest radiography interpretation resulted in absolute increases in sensitivity for all radiologists of various levels of expertise and reduced the reading times; specificity increased with AI, except in the diagnosis of pneumothorax. © RSNA, 2023 Supplemental material is available for this article.

Evaluating the performance of artificial intelligence software for lung nodule detection on chest radiographs in a retrospective real-world UK population.

OBJECTIVES: Early identification of lung cancer on chest radiographs improves patient outcomes. Artificial intelligence (AI) tools may increase diagnostic accuracy and streamline this pathway. This study evaluated the performance of commercially available AI-based software trained to identify cancerous lung nodules on chest radiographs. DESIGN: This retrospective study included primary care chest radiographs acquired in a UK centre. The software evaluated each radiograph independently and outputs were compared with two reference standards: (1) the radiologist report and (2) the diagnosis of cancer by multidisciplinary team decision. Failure analysis was performed by interrogating the software marker locations on radiographs. PARTICIPANTS: 5722 consecutive chest radiographs were included from 5592 patients (median age 59 years, 53.8% women, 1.6% prevalence of cancer). RESULTS: Compared with radiologist reports for nodule detection, the software demonstrated sensitivity 54.5% (95% CI 44.2% to 64.4%), specificity 83.2% (82.2% to 84.1%), positive predictive value (PPV) 5.5% (4.6% to 6.6%) and negative predictive value (NPV) 99.0% (98.8% to 99.2%). Compared with cancer diagnosis, the software demonstrated sensitivity 60.9% (50.1% to 70.9%), specificity 83.3% (82.3% to 84.2%), PPV 5.6% (4.8% to 6.6%) and NPV 99.2% (99.0% to 99.4%). Normal or variant anatomy was misidentified as an abnormality in 69.9% of the 943 false positive cases. CONCLUSIONS: The software demonstrated considerable underperformance in this real-world patient cohort. Failure analysis suggested a lack of generalisability in the training and testing datasets as a potential factor. The low PPV carries the risk of over-investigation and limits the translation of the software to clinical practice. Our findings highlight the importance of training and testing software in representative datasets, with broader implications for the implementation of AI tools in imaging.

MultiCOVID: a multi modal deep learning approach for COVID-19 diagnosis.

The rapid spread of the severe acute respiratory syndrome coronavirus 2 led to a global overextension of healthcare. Both Chest X-rays (CXR) and blood test have been demonstrated to have predictive value on Coronavirus Disease 2019 (COVID-19) diagnosis on different prevalence scenarios. With the objective of improving and accelerating the diagnosis of COVID-19, a multi modal prediction algorithm (MultiCOVID) based on CXR and blood test was developed, to discriminate between COVID-19, Heart Failure and Non-COVID Pneumonia and healthy (Control) patients. This retrospective single-center study includes CXR and blood test obtained between January 2017 and May 2020. Multi modal prediction models were generated using opensource DL algorithms. Performance of the MultiCOVID algorithm was compared with interpretations from five experienced thoracic radiologists on 300 random test images using the McNemar-Bowker test. A total of 8578 samples from 6123 patients (mean age 66 ± 18 years of standard deviation, 3523 men) were evaluated across datasets. For the entire test set, the overall accuracy of MultiCOVID was 84%, with a mean AUC of 0.92 (0.89-0.94). For 300 random test images, overall accuracy of MultiCOVID was significantly higher (69.6%) compared with individual radiologists (range, 43.7-58.7%) and the consensus of all five radiologists (59.3%, P < .001). Overall, we have developed a multimodal deep learning algorithm, MultiCOVID, that discriminates among COVID-19, heart failure, non-COVID pneumonia and healthy patients using both CXR and blood test with a significantly better performance than experienced thoracic radiologists.

Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis.

In this study, we developed a model to predict culture test results for pulmonary tuberculosis (PTB) with a customized multimodal approach and evaluated its performance in different clinical settings. Moreover, we investigated potential performance improvements by combining this approach with deep learning-based automated detection algorithms (DLADs). This retrospective observational study enrolled patients over 18 years of age who consecutively visited the level 1 emergency department and underwent chest radiograph and sputum testing. The primary endpoint was positive sputum culture for PTB. We compared the performance of the diagnostic models by replacing radiologists' interpretations of chest radiographs with screening scores calculated through DLAD. The optimal diagnostic model had an area under the receiver operating characteristic curve of 0.924 (95% CI 0.871-0.976) and an area under precision recall curve of 0.403 (95% CI 0.195-0.580) while maintaining a specificity of 81.4% when sensitivity was fixed at 90%. Multicomponent models showed improved performance for detecting PTB when chest radiography interpretation was replaced by DLAD. Multicomponent diagnostic models with DLAD customized for different clinical settings are more practical than traditional methods for detecting patients with PTB. This novel diagnostic approach may help prevent the spread of PTB and optimize healthcare resource utilization in resource-limited clinical settings.

Have Chest Imaging Habits Changed in the Emergency Department after the Pandemic?

The rate of patients undergoing tomography in the emergency department has increased in the last two decades. In the last few years, there has been a more significant increase due to the effects of the pandemic. This study aimed to determine the rate of patients who underwent chest imaging in the emergency department, the preferred imaging method, and the demographic characteristics of the patients undergoing imaging during the pre-pandemic and post-pandemic periods. This retrospective cross-sectional study included patients admitted to the emergency department between January 2019 and March 2023. The number of female, male, and total emergency admissions, the rate of patients who underwent chest X-ray (CXR) and chest computed tomography (CCT), and the age and gender distribution of the cases who underwent chest imaging were compared according to the pre-pandemic (January 2019-February 2020), pandemic (March 2020-March 2022), and post-pandemic (April 2022-March 2023) periods. Total emergency admissions were similar in the pre-pandemic and post-pandemic periods (pre-pandemic period: 21,984 ± 2087; post-pandemic period: 22,732 ± 1701). Compared to the pre-pandemic period, the CCT rate increased (pre-pandemic period: 4.9 ± 0.9, post-pandemic period: 7.46 ± 1.2), and the CXR rate decreased (pre-pandemic period: 16.6 ± 1.7%, post-pandemic period: 13.3 ± 1.9%) in the post-pandemic period (p < 0.001). The mean age of patients who underwent chest imaging (CXR; Pre-pandemic period: 56.6 ± 1.1 years; post-pandemic period: 53.3 ± 5.6 years. CCT; Pre-pandemic period: 68.5 ± 1.7 years; post-pandemic period: 61 ± 4.0 years) in the post-pandemic period was lower than in the pre-pandemic period (p < 0.001). Chest imaging preferences in the emergency department have changed during the post-pandemic period. In the post-pandemic period, while younger patients underwent chest imaging in the emergency department, CCT was preferred, and the rate of CXR decreased. It is alarming for public health that patients are exposed to higher doses of radiation at a younger age.

An organ-effective modulation for non-contrast chest computed tomography imaging: effect on image quality and thyroid exposure reduction.

We investigate the efficacy of organ-effective modulation (OEM) technique for thyroid dose reduction among various body habitus and its impact on image quality in chest non-contrast computed tomography (CT). We prospectively enrolled 64 patients who underwent non-contrast chest CT from January to May 2022. The skin-absorbed radiation dose over the thyroid (Dthyroid) was obtained using a thermoluminescence dosemeter. Signal-to-noise ratio and image noise was also quantitatively assessed. In subjective analyses, two radiologists independently evaluated images based on a 5-point scale. The OEM group showed a markedly decrease in Dthyroid when compared with the non-OEM group (p < 0.05). No significant difference was observed regarding the image noise (p < 0.05), except for the ventral air space. The subjective scores of two radiologists showed no significant differences between the non-OEM and OEM groups. OEM can effectively reduce the radiation exposure of thyroid without compromising on image quality in non-contrast chest CT.

An AI-based algorithm for the automatic evaluation of image quality in canine thoracic radiographs.

The aim of this study was to develop and test an artificial intelligence (AI)-based algorithm for detecting common technical errors in canine thoracic radiography. The algorithm was trained using a database of thoracic radiographs from three veterinary clinics in Italy, which were evaluated for image quality by three experienced veterinary diagnostic imagers. The algorithm was designed to classify the images as correct or having one or more of the following errors: rotation, underexposure, overexposure, incorrect limb positioning, incorrect neck positioning, blurriness, cut-off, or the presence of foreign objects, or medical devices. The algorithm was able to correctly identify errors in thoracic radiographs with an overall accuracy of 81.5% in latero-lateral and 75.7% in sagittal images. The most accurately identified errors were limb mispositioning and underexposure both in latero-lateral and sagittal images. The accuracy of the developed model in the classification of technically correct radiographs was fair in latero-lateral and good in sagittal images. The authors conclude that their AI-based algorithm is a promising tool for improving the accuracy of radiographic interpretation by identifying technical errors in canine thoracic radiographs.

An Opportunity to Seize From Low Hanging Fruits: Capitalising on Incidentally Reported Coronary Artery Calcification.

AIM: We investigated the prevalence of incidental coronary artery calcifications (CAC) from non-electrocardiogram (ECG)-gated computed tomography (CT) chest (both contrast and non-contrast) for inpatients. We also assessed for downstream investigation and statin prescription from the inpatient teams. Incidental CAC are frequent findings on non-ECG-gated CT chest. It is associated with adverse prognosis in multiple patient cohorts. METHOD: All non-ECG-gated CT chest done as inpatients from a single centre referred from 1 January 2022 to 31 December 2022 with reported incidental CAC were reviewed for inclusion. Patients who had a history of known coronary artery disease, history of coronary stent or bypass, and presence of cardiac devices were excluded. RESULTS: Total of 123 patients were included, making the prevalence 6.2% (123/1,980). The median age is 76 years (interquartile range 69-85) and predominantly male at 54.5%. The majority of CT chest done were contrasted scans (91.1%). Only 26.8% of CAC were reported on severity with visual quantification, with 7.3% each reported for both moderate and severe CAC. Only 2.4% of CAC were reported in the conclusion of the CT report. Most of these patients were asymptomatic (34.1%). A total of 20.3% of patients had further tests done. Inpatient hospital mortality was 8.1%. About 23.6% and 34.1% of patients were on aspirin and statin therapy respectively at baseline. There was only 1 patient (1.2%) who was prescribed with new statin therapy on discharge. CONCLUSION: Incidental CAC is prevalent in inpatient settings and remains under-recognised by ordering clinicians, with low prescription rate of statin therapy. Practice-changing measures to standardise reporting of incidental CAC is needed to identify patients with subclinical coronary disease and initiate preventive interventions.

Commercially Available Chest Radiograph AI Tools for Detecting Airspace Disease, Pneumothorax, and Pleural Effusion.

Background Commercially available artificial intelligence (AI) tools can assist radiologists in interpreting chest radiographs, but their real-life diagnostic accuracy remains unclear. Purpose To evaluate the diagnostic accuracy of four commercially available AI tools for detection of airspace disease, pneumothorax, and pleural effusion on chest radiographs. Materials and Methods This retrospective study included consecutive adult patients who underwent chest radiography at one of four Danish hospitals in January 2020. Two thoracic radiologists (or three, in cases of disagreement) who had access to all previous and future imaging labeled chest radiographs independently for the reference standard. Area under the receiver operating characteristic curve, sensitivity, and specificity were calculated. Sensitivity and specificity were additionally stratified according to the severity of findings, number of findings on chest radiographs, and radiographic projection. The χ2 and McNemar tests were used for comparisons. Results The data set comprised 2040 patients (median age, 72 years [IQR, 58-81 years]; 1033 female), of whom 669 (32.8%) had target findings. The AI tools demonstrated areas under the receiver operating characteristic curve ranging 0.83-0.88 for airspace disease, 0.89-0.97 for pneumothorax, and 0.94-0.97 for pleural effusion. Sensitivities ranged 72%-91% for airspace disease, 63%-90% for pneumothorax, and 62%-95% for pleural effusion. Negative predictive values ranged 92%-100% for all target findings. In airspace disease, pneumothorax, and pleural effusion, specificity was high for chest radiographs with normal or single findings (range, 85%-96%, 99%-100%, and 95%-100%, respectively) and markedly lower for chest radiographs with four or more findings (range, 27%-69%, 96%-99%, 65%-92%, respectively) (P < .001). AI sensitivity was lower for vague airspace disease (range, 33%-61%) and small pneumothorax or pleural effusion (range, 9%-94%) compared with larger findings (range, 81%-100%; P value range, > .99 to < .001). Conclusion Current-generation AI tools showed moderate to high sensitivity for detecting airspace disease, pneumothorax, and pleural effusion on chest radiographs. However, they produced more false-positive findings than radiology reports, and their performance decreased for smaller-sized target findings and when multiple findings were present. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Yanagawa and Tomiyama in this issue.