Performance of AI to exclude normal chest radiographs to reduce radiologists' workload.

INTRODUCTION: This study investigates the performance of a commercially available artificial intelligence (AI) system to identify normal chest radiographs and its potential to reduce radiologist workload. METHODS: Retrospective analysis included consecutive chest radiographs from two medical centers between Oct 1, 2016 and Oct 14, 2016. Exclusions comprised follow-up exams within the inclusion period, bedside radiographs, incomplete images, imported radiographs, and pediatric radiographs. Three chest radiologists categorized findings into normal, clinically irrelevant, clinically relevant, urgent, and critical. A commercial AI system processed all radiographs, scoring 10 chest abnormalities on a 0-100 confidence scale. AI system performance was evaluated using the area under the ROC curve (AUC), assessing the detection of normal radiographs. Sensitivity was calculated for the default and a conservative operating point. the detection of negative predictive value (NPV) for urgent and critical findings, as well as the potential workload reduction, was calculated. RESULTS: A total of 2603 radiographs were acquired in 2141 unique patients. Post-exclusion, 1670 radiographs were analyzed. Categories included 479 normal, 332 clinically irrelevant, 339 clinically relevant, 501 urgent, and 19 critical findings. The AI system achieved an AUC of 0.92. Sensitivity for normal radiographs was 92% at default and 53% at the conservative operating point. At the conservative operating point, NPV was 98% for urgent and critical findings, and could result in a 15% workload reduction. CONCLUSION: A commercially available AI system effectively identifies normal chest radiographs and holds the potential to lessen radiologists' workload by omitting half of the normal exams from reporting. CLINICAL RELEVANCE STATEMENT: The AI system is able to detect half of all normal chest radiographs at a clinically acceptable operating point, thereby potentially reducing the workload for the radiologists by 15%. KEY POINTS: The AI system reached an AUC of 0.92 for the detection of normal chest radiographs. Fifty-three percent of normal chest radiographs were identified with a NPV of 98% for urgent findings. AI can reduce the workload of chest radiography reporting by 15%.

Enhancing diagnostic deep learning via self-supervised pretraining on large-scale, unlabeled non-medical images.

BACKGROUND: Pretraining labeled datasets, like ImageNet, have become a technical standard in advanced medical image analysis. However, the emergence of self-supervised learning (SSL), which leverages unlabeled data to learn robust features, presents an opportunity to bypass the intensive labeling process. In this study, we explored if SSL for pretraining on non-medical images can be applied to chest radiographs and how it compares to supervised pretraining on non-medical images and on medical images. METHODS: We utilized a vision transformer and initialized its weights based on the following: (i) SSL pretraining on non-medical images (DINOv2), (ii) supervised learning (SL) pretraining on non-medical images (ImageNet dataset), and (iii) SL pretraining on chest radiographs from the MIMIC-CXR database, the largest labeled public dataset of chest radiographs to date. We tested our approach on over 800,000 chest radiographs from 6 large global datasets, diagnosing more than 20 different imaging findings. Performance was quantified using the area under the receiver operating characteristic curve and evaluated for statistical significance using bootstrapping. RESULTS: SSL pretraining on non-medical images not only outperformed ImageNet-based pretraining (p < 0.001 for all datasets) but, in certain cases, also exceeded SL on the MIMIC-CXR dataset. Our findings suggest that selecting the right pretraining strategy, especially with SSL, can be pivotal for improving diagnostic accuracy of artificial intelligence in medical imaging. CONCLUSIONS: By demonstrating the promise of SSL in chest radiograph analysis, we underline a transformative shift towards more efficient and accurate AI models in medical imaging. RELEVANCE STATEMENT: Self-supervised learning highlights a paradigm shift towards the enhancement of AI-driven accuracy and efficiency in medical imaging. Given its promise, the broader application of self-supervised learning in medical imaging calls for deeper exploration, particularly in contexts where comprehensive annotated datasets are limited.

Is a Camera-Type Portable X-Ray Device Clinically Feasible in Chest Imaging?: Image Quality Comparison with Chest Radiographs Taken with Traditional Mobile Digital X-Ray Devices.

Purpose: To evaluate whether the image quality of chest radiographs obtained using a camera-type portable X-ray device is appropriate for clinical practice by comparing them with traditional mobile digital X-ray devices. Materials and Methods: Eighty-six patients who visited our emergency department and underwent endotracheal intubation, central venous catheterization, or nasogastric tube insertion were included in the study. Two radiologists scored images captured with traditional mobile devices before insertion and those captured with camera-type devices after insertion. Identification of the inserted instruments was evaluated on a 5-point scale, and the overall image quality was evaluated on a total of 20 points scale. Results: The identification score of the instruments was 4.67 ± 0.71. The overall image quality score was 19.70 ± 0.72 and 15.02 ± 3.31 (p < 0.001) for the mobile and camera-type devices, respectively. The scores of the camera-type device were significantly lower than those of the mobile device in terms of the detailed items of respiratory motion artifacts, trachea and bronchus, pulmonary vessels, posterior cardiac blood vessels, thoracic intervertebral disc space, subdiaphragmatic vessels, and diaphragm (p = 0.013 for the item of diaphragm, p < 0.001 for the other detailed items). Conclusion: Although caution is required for general diagnostic purposes as image quality degrades, a camera-type device can be used to evaluate the inserted instruments in chest radiographs.

Use of artificial intelligence in triaging of chest radiographs to reduce radiologists' workload.

OBJECTIVES: To evaluate whether deep learning-based detection algorithms (DLD)-based triaging can reduce outpatient chest radiograph interpretation workload while maintaining noninferior sensitivity. METHODS: This retrospective study included patients who underwent initial chest radiography at the outpatient clinic between June 1 and June 30, 2017. Readers interpreted radiographs with/without a commercially available DLD that detects nine radiologic findings (atelectasis, calcification, cardiomegaly, consolidation, fibrosis, nodules, pneumothorax, pleural effusion, and pneumoperitoneum). The reading order was determined in a randomized, crossover manner. The radiographs were classified into negative and positive examinations. In a 50% worklist reduction scenario, radiographs were sorted in descending order of probability scores: the lower half was regarded as negative exams, while the remaining were read with DLD by radiologists. The primary analysis evaluated noninferiority in sensitivity between radiologists reading all radiographs and simulating a 50% worklist reduction, with the inferiority margin of 5%. The specificities were compared using McNemar's test. RESULTS: The study included 1964 patients (median age [interquartile range], 55 years [40-67 years]). The sensitivity was 82.6% (195 of 236; 95% CI: 77.5%, 87.3%) when readers interpreted all chest radiographs without DLD and 83.5% (197 of 236; 95% CI: 78.8%, 88.1%) in the 50% worklist reduction scenario. The difference in sensitivity was 0.8% (95% CI: - 3.8%, 5.5%), establishing noninferiority of 50% worklist reduction (p = 0.01). The specificity increased from 86.7% (1498 of 1728) to 90.4% (1562 of 1728) (p < 0.001) with DLD-based triage. CONCLUSION: Deep learning-based triaging may substantially reduce workload without lowering sensitivity while improving specificity. CLINICAL RELEVANCE STATEMENT: Substantial workload reduction without lowering sensitivity was feasible using deep learning-based triaging of outpatient chest radiograph; however, the legal responsibility for incorrect diagnoses based on AI-standalone interpretation remains an issue that should be defined before clinical implementation. KEY POINTS: • A 50% workload reduction simulation using deep learning-based detection algorithm maintained noninferior sensitivity while improving specificity. • The CT recommendation rate significantly decreased in the disease-negative patients, whereas it slightly increased in the disease-positive group without statistical significance. • In the exploratory analysis, the noninferiority of sensitivity was maintained until 70% of the workload was reduced; the difference in sensitivity was 0%.

Manejo conservador del neumotórax oculto en trauma

Introducción: El neumotórax oculto (NTXO) se encuentra hasta en el 15% de los traumatismos torácicos. Existen antecedentes del manejo conservador de esta patología (sólo observación), aunque su práctica continúa siendo discutida, especialmente, en traumatismos penetrantes. El objetivo de este trabajo es describir nuestra experiencia en el manejo conservador del NTXO. Materiales y Método: Estudio de cohorte retrospectivo realizado durante un período de 3 años en un Hospital de Trauma nivel I. Se incluyeron pacientes con traumatismo torácico (cerrado o penetrante) con NTXO. Se dividieron en dos grupos (conservados o drenados), realizándose una comparación de su evolución. Resultados: En 3 años fueron admitidos con traumatismo torácico 679 pacientes. De 93 pacientes con NTXO, 74 (80%) fueron conservados inicialmente y 19 (20%) tratados con drenaje pleural. Dos (3%) presentaron progresión del neumotórax en el seguimiento radiológico (conservación fallida). No se registraron complicaciones relacionadas con la ausencia de drenaje pleural. Las complicaciones y estancia hospitalaria fueron menores en el grupo de manejo conservador. Conclusión: Pacientes con NTXO por traumatismo de tórax (cerrado o penetrante), sin requerimiento de ventilación asistida y hemodinámicamente estables, pueden manejarse de manera conservadora con un monitoreo cercano durante 24 horas en forma segura, con menor tasa de complicaciones y de estancia hospitalaria.

Background: Occult pneumothorax (OPTX) is found in up to 15% of chest injuries. There is a history of conservative management of this pathology (only observation), although its practice continues to be discussed, especially in penetrating trauma. The objective of this paper is to describe our experience in the conservative management of OPTX. Materials and Method: Retrospective cohort study conducted over a 3-year period at a level I Trauma Center. Patients with thoracic trauma (blunt or penetrating) with OPTX were included. They were divided into two groups (preserved or drained) comparing their evolution. Results: Over a 3-year period 679 patients were admitted with chest trauma. From 93 patients with OPTX, 74 (80%) were initially preserved and 19 (20%) drained. Two patients (3%) presented pneumothorax progression in the follow-up imaging. There were no complications related to the absence of pleural drainage. Complications and hospital stay were lower in the conservative management group. Conclusion: Patients with OPTX due to chest trauma (blunt or penetrating), without requiring assisted ventilation and hemodynamically stable, can be safely conservative managed with close monitoring for 24 hours, with a lower rate of complications and hospital stay.

Imaging of bronchopulmonary dysplasia.

Bronchopulmonary dysplasia (BPD) is a multifactorial disease with many associated co-morbidities, responsible for most cases of chronic lung disease in childhood. The use of imaging exams is pivotal for the clinical care of BPD and the identification of candidates for experimental therapies and a closer follow-up. Imaging is also useful to improve communication with the family and objectively evaluate the clinical evolution of the patient's disease. BPD imaging has been classically performed using only chest X-rays, but several modern techniques are currently available, such as lung ultrasound, thoracic tomography, magnetic resonance imaging and electrical impedance tomography. These techniques are more accurate and provide clinically meaningful information. We reviewed the most recent evidence published in the last five years regarding these techniques and analyzed their advantages and disadvantages.

Learning from the machine: AI assistance is not an effective learning tool for resident education in chest x-ray interpretation.

OBJECTIVES: To assess whether a computer-aided detection (CADe) system could serve as a learning tool for radiology residents in chest X-ray (CXR) interpretation. METHODS: Eight radiology residents were asked to interpret 500 CXRs for the detection of five abnormalities, namely pneumothorax, pleural effusion, alveolar syndrome, lung nodule, and mediastinal mass. After interpreting 150 CXRs, the residents were divided into 2 groups of equivalent performance and experience. Subsequently, group 1 interpreted 200 CXRs from the "intervention dataset" using a CADe as a second reader, while group 2 served as a control by interpreting the same CXRs without the use of CADe. Finally, the 2 groups interpreted another 150 CXRs without the use of CADe. The sensitivity, specificity, and accuracy before, during, and after the intervention were compared. RESULTS: Before the intervention, the median individual sensitivity, specificity, and accuracy of the eight radiology residents were 43% (range: 35-57%), 90% (range: 82-96%), and 81% (range: 76-84%), respectively. With the use of CADe, residents from group 1 had a significantly higher overall sensitivity (53% [n = 431/816] vs 43% [n = 349/816], p < 0.001), specificity (94% [i = 3206/3428] vs 90% [n = 3127/3477], p < 0.001), and accuracy (86% [n = 3637/4244] vs 81% [n = 3476/4293], p < 0.001), compared to the control group. After the intervention, there were no significant differences between group 1 and group 2 regarding the overall sensitivity (44% [n = 309/696] vs 46% [n = 317/696], p = 0.666), specificity (90% [n = 2294/2541] vs 90% [n = 2285/2542], p = 0.642), or accuracy (80% [n = 2603/3237] vs 80% [n = 2602/3238], p = 0.955). CONCLUSIONS: Although it improves radiology residents' performances for interpreting CXRs, a CADe system alone did not appear to be an effective learning tool and should not replace teaching. CLINICAL RELEVANCE STATEMENT: Although the use of artificial intelligence improves radiology residents' performance in chest X-rays interpretation, artificial intelligence cannot be used alone as a learning tool and should not replace dedicated teaching. KEY POINTS: • With CADe as a second reader, residents had a significantly higher sensitivity (53% vs 43%, p < 0.001), specificity (94% vs 90%, p < 0.001), and accuracy (86% vs 81%, p < 0.001), compared to residents without CADe. • After removing access to the CADe system, residents' sensitivity (44% vs 46%, p = 0.666), specificity (90% vs 90%, p = 0.642), and accuracy (80% vs 80%, p = 0.955) returned to that of the level for the group without CADe.

Dynamic chest radiography: a state-of-the-art review.

Dynamic chest radiography (DCR) is a real-time sequential high-resolution digital X-ray imaging system of the thorax in motion over the respiratory cycle, utilising pulsed image exposure and a larger field of view than fluoroscopy coupled with a low radiation dose, where post-acquisition image processing by computer algorithm automatically characterises the motion of thoracic structures. We conducted a systematic review of the literature and found 29 relevant publications describing its use in humans including the assessment of diaphragm and chest wall motion, measurement of pulmonary ventilation and perfusion, and the assessment of airway narrowing. Work is ongoing in several other areas including assessment of diaphragmatic paralysis. We assess the findings, methodology and limitations of DCR, and we discuss the current and future roles of this promising medical imaging technology.Critical relevance statement Dynamic chest radiography provides a wealth of clinical information, but further research is required to identify its clinical niche.

Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study.

BACKGROUND: An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19. OBJECTIVE: We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19. METHODS: This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration. RESULTS: The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859). CONCLUSIONS: The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.

A study on changes in lung function, neutralizing antibodies, and symptoms of adult patients hospitalized with COVID-19.

BACKGROUND/AIMS: To identify changes in symptoms and pulmonary sequelae in patients with coronavirus disease 2019 (COVID-19). METHODS: Patients with COVID-19 hospitalized at seven university hospitals in Korea between February 2020 and February 2021 were enrolled, provided they had ≥ 1 outpatient follow-up visit. Between January 11 and March 9, 2021 (study period), residual symptom investigations, chest computed tomography (CT) scans, pulmonary function tests (PFT), and neutralizing antibody tests (NAb) were performed at the outpatient visit (cross-sectional design). Additionally, data from patients who already had follow-up outpatient visits before the study period were collected retrospectively. RESULTS: Investigation of residual symptoms, chest CT scans, PFT, and NAb were performed in 84, 35, 31, and 27 patients, respectively. After 6 months, chest discomfort and dyspnea persisted in 26.7% (4/15) and 33.3% (5/15) patients, respectively, and 40.0% (6/15) and 26.7% (4/15) patients experienced financial loss and emotional distress, respectively. When the ratio of later CT score to previous ones was calculated for each patient between three different time intervals (1-14, 15-60, and 61-365 days), the median values were 0.65 (the second interval to the first), 0.39 (the third to the second), and 0.20 (the third to the first), indicating that CT score decreases with time. In the high-severity group, the ratio was lower than in the low-severity group. CONCLUSION: In COVID-19 survivors, chest CT score recovers over time, but recovery is slower in severely ill patients. Subjects complained of various ongoing symptoms and socioeconomic problems for several months after recovery.

CT Findings of Thymic Epidermoid Cyst in the Anterior Mediastinum: A Case Report and Literature Review.

An epidermoid cyst is a benign tumor found anywhere in the body. However, the occurrence of epidermoid cysts in the thymus is extremely rare, with only six cases reported worldwide. The correct diagnosis of thymic epidermoid cysts is often difficult due to the unusual location and nonspecific imaging findings. Herein, we present a case of a thymic epidermoid cyst in a 37-year-old female with clinical information and chest CT findings. Further, we have reviewed previous literature reports describing imaging findings of thymic epidermoid cysts.

Reproducibility of a protocol for standardized reading of chest X-rays of children household contact of patients with tuberculosis.

BACKGROUND: The interpretation of the chest radiograph may vary because it depends on the reader and due to the non-specificity of findings in tuberculosis (TB). We aim to assess the reproducibility of a standardized chest radiograph reading protocol in contacts of patients with pulmonary TB under the 5 years of age. METHODS: Descriptive, cross-sectional study with children under the age of five, household contacts of patients with confirmed pulmonary TB from Medellín, Bello and Itagüí (Colombia) between Jan-01-2015 and May-31-2016. Standardized reading protocol: two radiologists, blinded independent reading, use of template (Dr. Andronikou design) in case of disagreement a third reading was performed. Kappa coefficient for intra and inter observer agreement, and prevalence ratio were estimated of sociodemographic characteristics, TB exposure and interpretation of chest X-ray. RESULTS: From 278 children, standardized reading found 255 (91.7%) normal X-rays, 10 (3.6%) consistent with TB, and 13 (4.7%) other alterations. Global agreement was 91.3% (Kappa = 0.51). Inter-observer agreement between readers 1-2 was 90.0% (Kappa = 0.59) and 1-3 93.2% (Kappa = 0.59). Intra-observer agreement for reader 1 was 95.5% (Kappa = 0.86), 2 84.0% (Kappa = 0.51), and 3 94.7% (Kappa = 0.68). Greater inter-observer disagreement was between readers 1-2 for soft tissue density suggestive of adenopathy (4.6%), airspace opacification (1.17%) and pleural effusion (0.58%); between readers 1-3 for soft tissue density suggestive of adenopathy (4.2%), opacification of airspace (2.5%) and cavities (0.8%). CONCLUSIONS: Chest radiographs are an affordable tool that contributes to the diagnosis of TB, so having a standardized reading protocol showed good agreement and improves the reproducibility of radiograph interpretation.

Inteligencia artificial explicable, una perspectiva al problema de la clasificación automática de COVID-19 mediante radiografías de tórax

RESUMEN Esta investigación pretende dilucidar, a partir del análisis de técnicas de inteligencia artificial explicables, la robustez y el nivel de generalización de los métodos de visión por computadora propuestos para identificar COVID-19 utilizando imágenes de radiografías de tórax. Asimismo, alertar a los investigadores y revisores sobre el problema del aprendizaje por atajos. En este estudio se siguen recomendaciones para identificar si los modelos de clasificación automática de COVID-19 se ven afectados por el aprendizaje por atajos. Para ello, se revisaron los artículos que utilizan métodos de inteligencia artificial explicable en dicha tarea. Se evidenció que al utilizar la imagen de radiografía de tórax completa o el cuadro delimitador de los pulmones, las regiones de la imagen que más contribuyen a la clasificación aparecen fuera de la región pulmonar, algo que no tiene sentido. Los resultados indican que, hasta ahora, los modelos existentes presentan el problema de aprendizaje por atajos, lo cual los hace inapropiados para ser usados en entornos clínicos.

ABSTRACT This research aims to elucidate, from the analysis of explainable artificial intelligence techniques, the robustness and level of generalization of the proposed computer vision methods to identify COVID-19 using chest X-ray images. Also, alert researchers and reviewers about the problem of learning by shortcuts. In this study, recommendations are followed to identify if the automatic classification models of COVID-19 are affected by shortcut learning. To do this, articles that use explainable artificial intelligence methods were reviewed. It was shown that when using the full chest X-ray image or the bounding box of the lungs, the regions of the image that contribute the most to the classification appear outside the lung region, something that does not make sense. The results indicate that, so far, the existing models present the problem of learning by shortcuts, which makes them inappropriate to be used in clinical settings.

Dark-field chest x-ray imaging: first experience in patients with alpha1-antitrypsin deficiency.

BACKGROUND: Spirometry and conventional chest x-ray have limitations in investigating early emphysema, while computed tomography, the reference imaging method in this context, is not part of routine patient care due to its higher radiation dose. In this work, we investigated a novel low-dose imaging modality, dark-field chest x-ray, for the evaluation of emphysema in patients with alpha1-antitrypsin deficiency. METHODS: By exploiting wave properties of x-rays for contrast formation, dark-field chest x-ray visualises the structural integrity of the alveoli, represented by a high signal over the lungs in the dark-field image. We investigated four patients with alpha1-antitrypsin deficiency with a novel dark-field x-ray prototype and simultaneous conventional chest x-ray. The extent of pulmonary function impairment was assessed by pulmonary function measurement and regional emphysema distribution was compared with CT in one patient. RESULTS: We show that dark-field chest x-ray visualises the extent of pulmonary emphysema displaying severity and regional differences. Areas with low dark-field signal correlate with emphysematous changes detected by computed tomography using a threshold of -950 Hounsfield units. The airway parameters obtained by whole-body plethysmography and single breath diffusing capacity of the lungs for carbon monoxide demonstrated typical changes of advanced emphysema. CONCLUSIONS: Dark-field chest x-ray directly visualised the severity and regional distribution of pulmonary emphysema compared to conventional chest x-ray in patients with alpha1-antitrypsin deficiency. Due to the ultra-low radiation dose in comparison to computed tomography, dark-field chest x-ray could be beneficial for long-term follow-up in these patients.

Artificial intelligence system for identification of false-negative interpretations in chest radiographs.

OBJECTIVES: To investigate the efficacy of an artificial intelligence (AI) system for the identification of false negatives in chest radiographs that were interpreted as normal by radiologists. METHODS: We consecutively collected chest radiographs that were read as normal during 1 month (March 2020) in a single institution. A commercialized AI system was retrospectively applied to these radiographs. Radiographs with abnormal AI results were then re-interpreted by the radiologist who initially read the radiograph ("AI as the advisor" scenario). The reference standards for the true presence of relevant abnormalities in radiographs were defined by majority voting of three thoracic radiologists. The efficacy of the AI system was evaluated by detection yield (proportion of true-positive identification among the entire examination) and false-referral rate (FRR, proportion of false-positive identification among all examinations). Decision curve analyses were performed to evaluate the net benefits of applying the AI system. RESULTS: A total of 4208 radiographs from 3778 patients (M:F = 1542:2236; median age, 56 years) were included. The AI system identified initially overlooked relevant abnormalities with a detection yield and an FRR of 2.4% and 14.0%, respectively. In the "AI as the advisor" scenario, radiologists detected initially overlooked relevant abnormalities with a detection yield and FRR of 1.2% and 0.97%, respectively. In a decision curve analysis, AI as an advisor scenario exhibited a positive net benefit when the cost-to-benefit ratio was below 1:0.8. CONCLUSION: An AI system could identify relevant abnormalities overlooked by radiologists and could enable radiologists to correct their false-negative interpretations by providing feedback to radiologists. KEY POINTS: • In consecutive chest radiographs with normal interpretations, an artificial intelligence system could identify relevant abnormalities that were initially overlooked by radiologists. • The artificial intelligence system could enable radiologists to correct their initial false-negative interpretations by providing feedback to radiologists when overlooked abnormalities were present.

Vector-field dynamic x-ray (VF-DXR) using optical flow method in patients with chronic obstructive pulmonary disease.

BACKGROUND: We assessed the difference in lung motion during inspiration/expiration between chronic obstructive pulmonary disease (COPD) patients and healthy volunteers using vector-field dynamic x-ray (VF-DXR) with optical flow method (OFM). METHODS: We enrolled 36 COPD patients and 47 healthy volunteers, classified according to pulmonary function into: normal, COPD mild, and COPD severe. Contrast gradient was obtained from sequential dynamic x-ray (DXR) and converted to motion vector using OFM. VF-DXR images were created by projection of the vertical component of lung motion vectors onto DXR images. The maximum magnitude of lung motion vectors in tidal inspiration/expiration, forced inspiration/expiration were selected and defined as lung motion velocity (LMV). Correlations between LMV with demographics and pulmonary function and differences in LMV between COPD patients and healthy volunteers were investigated. RESULTS: Negative correlations were confirmed between LMV and % forced expiratory volume in one second (%FEV1) in the tidal inspiration in the right lung (Spearman's rank correlation coefficient, rs = -0.47, p < 0.001) and the left lung (rs = -0.32, p = 0.033). A positive correlation between LMV and %FEV1 in the tidal expiration was observed only in the right lung (rs = 0.25, p = 0.024). LMVs among normal, COPD mild and COPD severe groups were different in the tidal respiration. COPD mild group showed a significantly larger magnitude of LMV compared with the normal group. CONCLUSIONS: In the tidal inspiration, the lung parenchyma moved faster in COPD patients compared with healthy volunteers. VF-DXR was feasible for the assessment of lung parenchyma using LMV.