Portable Chest Radiographs Research Articles

Artificial intelligence-driven automated lung sizing from chest radiographs

Lung size measurements play an important role in transplantation, as optimal donor-recipient size matching is necessary to ensure the best possible outcome. Although several strategies for size matching are currently used, all have limitations, and none has proven superior. In this pilot study, we leveraged deep learning and computer vision to develop an automated system for generating standardized lung size measurements using portable chest radiographs to improve accuracy, reduce variability, and streamline donor/recipient matching. We developed a 2-step framework involving lung mask extraction from chest radiographs followed by feature point detection to generate 6 distinct lung height and width measurements, which we validated against measurements reported by 2 radiologists (T.A. and W.B.G.) for 50 lung transplant recipients. Our system demonstrated <2.5% error (<7.0 mm) with robust interrater and intrarater agreement compared with an expert radiologist review. This is especially promising given that the radiographs used in this study were purposely chosen to include images with technical challenges such as consolidations, effusions, and patient rotation. Although validation in a larger cohort is necessary, this study highlights artificial intelligence’s potential to both provide reproducible lung size assessment in real patients and enable studies on the effect of lung size matching on transplant outcomes in large data sets.

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.

Investigation of Imaging Conditions Using Human Body Equivalent Phantom and Neonatal Phantom in Portable Chest Radiography of Newborns

Investigation of imaging conditions using human body equivalent phantom and neonatal phantom in portable chest radiography of newborns. Although attempts have been made to reduce dose by image processing in portable X-ray radiography of neonates, no evaluation has been made at the raw data level of the images. In this study, we investigated dose reduction from the current imaging conditions using a simulated phantom and a neonatal phantom in terms of raw data level image quality and incident surface dose. The pixel values of each region were calculated from chest photographs of newborn infants taken at 60 kV and 2.0 mAs, and the thickness and combination of acrylic, aluminum, and copper were adjusted to create a simulated phantom with equivalent pixel values. The SdNR and incident surface dose at each site obtained from the simulated phantom were compared to obtain imaging conditions equivalent to or better than 60 kV, 2.0 mAs. The neonatal phantom was imaged, and the CNR of the processed images was compared to that of 60 kV, 2.0 mAs. SdNR and incident surface dose results showed that 62 kV, 1.8 mAs was superior. Comparison with neonatal phantoms showed no significant difference. The simulated phantom was used to reproduce the clinical situation and to obtain excellent imaging conditions.

Portable Chest Radiography: Must-Know Findings and Mimics.

Portable Chest Radiography: Must-Know Findings and Mimics.

Feasibility of Ultrasound-Guided, Peripherally Inserted Central Catheter Placement at the Bedside in a Communicable-Disease Isolation Unit.

Previous studies have investigated the safety of peripherally inserted central catheters (PICCs) in the intensive care unit (ICU). However, it remains uncertain whether PICC placement can be successfully carried out in settings with limited resources and a challenging environment for procedures, such as communicable-disease isolation units (CDIUs). This study investigated the safety of PICCs in patients admitted to CDIUs. These researchers used a handheld portable ultrasound device (PUD) to guide venous access and confirmed catheter-tip location with electrocardiography (ECG) or portable chest radiography. Among 74 patients, the basilic vein and the right arm were the most common access site and location, respectively. The incidence of malposition was significantly higher with chest radiography compared to ECG (52.4% vs. 2.0%, p < 0.001). Using a handheld PUD to place PICCs at the bedside and confirming the tip location with ECG is a feasible option for CDIU patients.

A Reminder of the Value of Portable Chest Radiography

A Reminder of the Value of Portable Chest Radiography

Portable Chest Radiograph: A Boon for Critically Ill Patients With COVID-19 Pneumonia.

In the present study, we evaluated the role of portable chest radiographs in critically ill patients with COVID-19 pneumonia in whom computed tomography (CT) of the chest was not feasible. A retrospective chest X-ray study of patients under investigation for COVID-19 was performed in our dedicated COVID hospital (DCH) during the exponential growth phase of the COVID-19 outbreak (August-October, 2020).A total of 562 on-bed chest radiographs were examined comprising 289 patients (critically ill who couldn't be mobilized for CT) along with positive reverse transcription-polymerase chain reaction (RT-PCR) tests. We categorized each chest radiograph as progressive, with changes, or improvement in appearance for COVID-19, utilizing well-documented COVID-19 imaging patterns. In our study, portable radiographs provided optimum image quality for diagnosing pneumonia, in critically ill patients. Although less informative than CT, nevertheless radiographs detected serious complications like pneumothorax or lung cavitation and estimated the evolution of pneumonia. A portable chest X-ray is a simple but reliable alternative for critically ill SARS-CoV-2 patients who could not undergo chest CT. With the help of portable chest radiographs, we could monitor the severity of the disease as well as different complications with minimal radiation exposure which would help in identifying the prognosis of the patient and thus help in medical management.

Determination of scattered radiation dose for radiological staff during portable chest examinations of COVID-19 patients.

The COVID-19 pandemic has resulted in a large increase in the number of patients admitted to hospitals. Radiological technologists (RTs) are often required to perform portable chest X-ray radiography on these patients. Normally, when performing a portable X-ray, radiation protection equipment is critical as it reduces the scatter radiation dose to hospital workers. However, during the pandemic, the use of a lead shield caused a heavy weight burden on workers who were responsible for a large number of patients. This study aimed to investigate scatter radiation doses received at various distances, directions, and positions. Radiation measurements were performed using the PBU-60 whole body phantom to determine scatter radiation doses at 100-200cm and eight different angles around the phantom. The tests were conducted with and without lead shielding. Additionally, the doses were compared using the paired t test (p < 0.005) to determine suitable positions for workers who did not wear lead protection that adhered to radiation safety requirements. Scatter radiation doses of all 40 tests showed a highest and lowest value of 1285.5 nGy at 100cm in the anteroposterior (AP) semi upright position and 134.7 nGy at 200cm in the prone position, respectively. Correlation analysis between the dosimeter measurement and calculated inverse square law showed good correlation, with an R2 value of 0.99. Without lead shielding, RTs must stay at a distance greater than 200cm from patients for both vertical and horizontal beams to minimize scatter exposure. This would allow for an alternative way of performing portable chest radiography for COVID-19 patients without requiring lead shielding.

Thoracic Inlet in Cervical Spine CT of Blunt Trauma Patients: Prevalence of Pathologies and Importance of CT Interpretation.

The thoracic inlet of blunt trauma patients may have pathologies that can be diagnosed on cervical spine computed tomography (CT) but that are not evident on concurrent portable chest radiography (pCXR). This retrospective investigation aimed to identify the prevalence of thoracic inlet pathologies on cervical spine CT and their importance by measuring the diagnostic performance of pCXR and the predictive factors of such abnormalities. This investigation was performed at a level-1 trauma center and included CT and concurrent pCXR of 385 consecutive adult patients (280 men, mean age of 47.6 years) who presented with suspected cervical spine injury. CT and pCXR findings were independently re-reviewed, and CT was considered the reference standard. Traumatic, significant nontraumatic and nonsignificant pathologies were present at 23.4%, 23.6% and 58.2%, respectively. The most common traumatic diagnoses were pneumothorax (12.7%) and pulmonary contusion (10.4%). The most common significant nontraumatic findings were pulmonary nodules (8.1%), micronodules (6.8%) and septal thickening (4.2%). The prevalence of active tuberculosis was 3.4%. The sensitivity and positive predictive value of pCXR was 56.67% and 49.51% in diagnosing traumatic and 8.89% and 50% in significant nontraumatic pathologies. No demographic or pre-admission clinical factors could predict these abnormalities. Several significant pathologies of the thoracic inlet were visualized on trauma cervical spine CT. Since a concurrent pCXR was not sensitive and no demographic or clinical factors could predict these abnormalities, a liberal use of chest CT is suggested, particularly among those experiencing high-energy trauma with significant injuries of the thoracic inlet. If chest CT is not available, a meticulous evaluation of the thoracic inlet in the cervical spine CT of blunt trauma patients is important.

This Month in Anesthesiology

This Month in Anesthesiology

Prediction of COVID-19 patients in danger of death using radiomic features of portable chest radiographs.

Computer-aided diagnostic systems have been developed for the detection and differential diagnosis of coronavirus disease 2019 (COVID-19) pneumonia using imaging studies to characterise a patient's current condition. In this radiomic study, we propose a system for predicting COVID-19 patients in danger of death using portable chest X-ray images. In this retrospective study, we selected 100 patients, including ten that died and 90 that recovered from the COVID-19-AR database of the Cancer Imaging Archive. Since it can be difficult to analyse portable chest X-ray images of patients with COVID-19 because bone components overlap with the abnormal patterns of this disease, we employed a bone-suppression technique during pre-processing. A total of 620 radiomic features were measured in the left and right lung regions, and four radiomic features were selected using the least absolute shrinkage and selection operator technique. We distinguished death from recovery cases using a linear discriminant analysis (LDA) and a support vector machine (SVM). The leave-one-out method was used to train and test the classifiers, and the area under the receiver-operating characteristic curve (AUC) was used to evaluate discriminative performance. The AUCs for LDA and SVM were 0.756 and 0.959, respectively. The discriminative performance was improved when the bone-suppression technique was employed. When the SVM was used, the sensitivity for predicting disease severity was 90.9% (9/10), and the specificity was 95.6% (86/90). We believe that the radiomic features of portable chest X-ray images can predict COVID-19 patients in danger of death.

Validation of a Deep Learning-based Automatic Detection Algorithm for Measurement of Endotracheal Tube-to-Carina Distance on Chest Radiographs.

Improper endotracheal tube (ETT) positioning is frequently observed and potentially hazardous in the intensive care unit. The authors developed a deep learning-based automatic detection algorithm detecting the ETT tip and carina on portable supine chest radiographs to measure the ETT-carina distance. This study investigated the hypothesis that the algorithm might be more accurate than frontline critical care clinicians in ETT tip detection, carina detection, and ETT-carina distance measurement. A deep learning-based automatic detection algorithm was developed using 1,842 portable supine chest radiographs of 1,842 adult intubated patients, where two board-certified intensivists worked together to annotate the distal ETT end and tracheal bifurcation. The performance of the deep learning-based algorithm was assessed in 4-fold cross-validation (1,842 radiographs), external validation (216 radiographs), and an observer performance test (462 radiographs) involving 11 critical care clinicians. The performance metrics included the errors from the ground truth in ETT tip detection, carina detection, and ETT-carina distance measurement. During 4-fold cross-validation and external validation, the median errors (interquartile range) of the algorithm in ETT-carina distance measurement were 3.9 (1.8 to 7.1) mm and 4.2 (1.7 to 7.8) mm, respectively. During the observer performance test, the median errors (interquartile range) of the algorithm were 2.6 (1.6 to 4.8) mm, 3.6 (2.1 to 5.9) mm, and 4.0 (1.7 to 7.2) mm in ETT tip detection, carina detection, and ETT-carina distance measurement, significantly superior to that of 6, 10, and 7 clinicians (all P < 0.05), respectively. The algorithm outperformed 7, 3, and 0, 9, 6, and 4, and 5, 5, and 3 clinicians (all P < 0.005) regarding the proportions of chest radiographs within 5 mm, 10 mm, and 15 mm error in ETT tip detection, carina detection, and ETT-carina distance measurement, respectively. No clinician was significantly more accurate than the algorithm in any comparison. A deep learning-based algorithm can match or even outperform frontline critical care clinicians in ETT tip detection, carina detection, and ETT-carina distance measurement.

A Man With Severe Chest Pain after a Motor Vehicle Crash

A 56-year-old man with shortness of breath, severe chest pain, and cold sweats after a motor vehicle crash presented to the emergency department (ED). He had low blood pressure (80/54 mm Hg), tachycardia (118 beats/min), and low Glasgow Coma Scale score (E3V4M5). He was intubated immediately on arrival because of shock. Extended focused assessment with sonography for trauma showed no hemopneumothorax, pericardial effusion, or intra-abdominal free fluid. Portable chest radiography was performed (Figure 1).

Efficacy of the scatter correction algorithm in portable chest radiography.

Purpose Portable chest radiographs (CXRs) continue to be a vital diagnostic tool for emergency and critical care medicine. The scatter correction algorithm (SCA) is a post-processing algorithm aiming to reduce scatter within portable images. This study aimed to assess whether the SCA improved image quality (IQ) in portable CXRs.MethodsObjective and subjective IQ assessments were undertaken on both phantom and clinical images, respectively. For objective analysis, attenuators were placed on the anterior surface of the patient’s thorax to simulate pathologies present within uniform regions of the phantom’s lung and heart. Phantom CXRs were acquired with three different tube-current-times (mAs). Phantom images were processed with different SCA strengths. Contrast to noise ratios (CNR) within the attenuator were determined for each algorithm strength and compared to non-SCA images. For subjective analysis, two independent radiologists graded 30 clinical images with and without the SCA activated. The images were graded for IQ in different anatomical structures and overall diagnostic confidence.ResultsObjectively, most strengths of the SCA improved the CNR in both regions. However, a detrimental effect was recorded for some algorithm strengths in regions of high contrast. Subjectively, both observers recorded the SCA significantly improved IQ in clinical CXRs in all anatomical regions. Observers indicated the greatest improvement in the lung and hilar regions, and least improvement in the chest wall and bone. All images with and without the SCA were deemed diagnostic.ConclusionThis study shows the potential radiation dose neutral IQ improvement when using an SCA in clinical patient CXRs.

Comparison of conventional and through glass portable chest computed radiography: A Phantom study

Background: Since the outbreak of COVID-19, modified hospital unit or area for chest radiography of positive cases have become necessary. To date, relatively few studies have been investigated on the effects of portable chest radiography through glass barrier. Objectives: Our goal was to evaluate exposure technique and radiation dose between conventional and through glass portable chest computed radiography. Materials and methods: Experiments using an anthropomorphic phantom were performed for acquired portable chest PA radiography at SID 180 cm with glass door being open and closed. The EI and DI values were optimized to provide the appropriate exposure technique for glass barrier. Entrance surface air kerma and scatter survey were made to assess the radiation dose both inside and outside the room. Finally, HVL measurement of primary X-ray beam and after transmission through glass were determined. Results: Based on the fixed kVp and mAs technique, the EI value with glass barrier was less than the EI without the glass. Imaging through glass barrier showed the average EI reduction of 10.4% for Carestream and 37% for Konica. The average entrance surface air kerma reduction was 56.6% over a range of 90-120 kVp. The appropriate exposure technique for conventional portable chest PA using computed radiography was 100 kVp 2.5 mAs. With the same kVp setting, doubling the mAs is required for imaging through glass barrier to produce good diagnostic image quality (100 kVp and 4.0 mAs). The acceptable EI and DI ranges for CR used were EI=1742, DI=-0.02 (without glass) and EI=1795, DI=0.11 (with glass) for Carestream and EI=352, DI=-0.03 (without glass) and EI=373, DI=0.22 (with glass) for Konica respectively. The primary beam after transmission through the glass thickness 5 mm was 36%. The measured scatter of inside room compared to outside was very low at 1-2 meters. Increasing od HVL from 3.9 to 6.1 mm Al indicates the effect of beam hardening by glass. Conclusion: These experiments confirmed that through glass portable chest computed radiography are feasible and safe. The findings of this study have several practical implications which minimizes risk to radiographers during their work.

The rapid atrial swirl sign for ultrasound-guided tip positioning of antegrade-tunneled hemodialysis catheters: A cross-sectional pilot study.

We have previously reported that the rapid atrial swirl sign (RASS) is an accurate and safe procedure for ultrasound (US)-guided tip positioning of retrograde-tunneled hemodialysis catheters (HDCs). However, application of RASS for placement of antegrade HDCs has not been investigated yet. Therefore, we here report our first experience of applying RASS for US-guided tip positioning of antegrade-tunneled HDCs. We performed a cross-sectional study to assess the feasibility of applying the RASS for US-guided tip positioning of antegrade-tunneled HDCs. We included a total number of 15 antegrade-tunneled HDC insertions in 13 patients requiring placement of a HDC for the temporary or permanent treatment of ESKD in a single-center, cross-sectional pilot study. The overall success rate of applying the RASS for US-guided tip positioning of antegrade-tunneled HDCs was 15/15 (100%) confirmed by portable anterior-posterior chest radiography, with no major adverse events after HDC insertions. In addition, this insertion technique demonstrated optimal HDC flow without any observed malfunction. This study investigated the efficacy of the RASS for US-guided tip positioning of antegrade-tunneled HDCs in patients with ESKD. Application of the RASS for US-guided tip positioning is an accurate and safe procedure for proper placement of antegrade-tunneled HDCs.

Method of determining technique from weight and height to achieve targeted detector exposures in portable chest and abdominal digital radiography.

This study presents a methodology to develop an X‐ray technique chart for portable chest and abdomen imaging which utilizes patient data available in the modality worklist (MWL) to reliably achieve a predetermined exposure index (EI) at the detector for any patient size. The method assumes a correlation between the patients’ tissue equivalent thickness and the square root of the ratio of the patient's weight to height. To assess variability in detector exposures, the EI statistics for 75 chest examinations and 99 abdominal portable X‐ray images acquired with the new technique chart were compared to those from a single portable unit (chest: 3877 images; abdomen: 200 images) using a conventional technique chart with three patient sizes, and to a stationary radiography room utilizing automatic exposure control (AEC) (chest: 360 images; abdomen: 112 images). The results showed that when using the new technique chart on a group of portable units, the variability in EI was significantly reduced (p < 0.01) for both AP chest and AP abdomen images compared to the single portable using a standard technique chart with three patient sizes. The variability in EI for the images acquired with the new chart was comparable to the stationary X‐ray room with an AEC system (p > 0.05). This method could be used to streamline the entire imaging chain by automatically selecting an X‐ray technique based on patient demographic information contained in the MWL to provide higher quality examinations to clinicians by eliminating outliers. In addition, patient height and weight can be used to estimate the patients’ tissue equivalent thickness.

Effects of Changing the Source-to-image Receptor Distance Parameter of Scattered X-ray Correction after Exposure on Image Quality in Portable Chest Radiography

To validate the effects of changing the source-to-image receptor distance (SID) parameter of scattered X-ray correction after exposure on the image quality in portable chest radiography. The actual SID and tube current-time product (mAs) were varied such that the direct X-ray dose to a flat panel detector (FPD) remained constant. We created two groups as follows: Group A (with the SID parameter unchanged) and Group B (with the SID parameter changed to the actual SID after a phantom chest exposure). The image contrast ratio and standard deviation (SD) were measured on the chest radiographs for physical assessment. Observer studies were performed by seven radiological technologists. Scheffé's (Ura) paired comparison methods were performed with image contrast, noise, and overall assessment as the assessment items. Receiver operating characteristic (ROC) analysis for lung nodules was performed. The image contrast ratio and SD in Group A changed, whereas the changes in Group B were less than those in Group A for both these properties. The observer study with Scheffé's methods showed a statistically significant difference (p<0.05) for all assessment items in Group A but not in Group B. The ROC analysis did not indicate any statistically significant differences in either group. Changing the SID parameter of scattered X-ray correction after exposure can possibly maintain image contrast and noise in portable chest radiography if the actual SID changes.

Evaluation of Detectability for Patient's Movement in Portable Chest Radiography: Comparison of Visual Detection and Motion Detection Software

The purpose of this study was to evaluate the detectability of the observers and motion detection software for blurred portable chest radiographies. The chest phantom radiographies of various blur sizes were obtained by moving the phantom using 4° slope. The phantom was moved in two directions, vertical (the upper and lower parts of the chest phantom were parallel to rails) and horizontal (the left and right parts of the chest phantom were parallel to rails). Six observers performed receiver operating characteristic (ROC) studies on blurred images. We used the results to compare detectability for vertical and horizontal blur by ROC analysis, and calculated sensitivity and specificity. In addition, the motion detection software was enabled during image acquisition, and the detectability was compared with that of the observers. The average of the area under the ROC curve for the detection of blur in the vertical and horizontal directions for the observers were 0.918 and 0.943, respectively, and no significant difference was found depending on the direction. The motion detection software performed better than the observers in most of the sensitivity and specificity scores. The motion detection software could be a useful support tool for motion detection in portable chest radiography.

Radiographic assessment of traction-induced esophageal growth and traction-related complications of the Foker process for treatment of long-gap esophageal atresia.

Radiographic assessment of esophageal growth in long-gap esophageal atresia while on traction and associated traction-related complications have not been described. To demonstrate how chest radiography can estimate esophageal position while on traction and to evaluate radiography's utility in diagnosing certain traction system complications. In this retrospective evaluation of portable chest radiographs obtained in infants with long-gap esophageal atresia who underwent the Foker process between 2014 and 2020, we assessed distances between the opposing trailing clips (esophageal gap) and the leading and trailing clips for each esophageal segment on serial radiographs. Growth during traction was estimated using longitudinal random-effects regression analysis to account for multiple chest radiograph measurements from the same child. Forty-three infants (25 male) had a median esophageal gap of 4.5cm. Median traction time was 14days. Median daily radiographic esophageal growth rate for both segments was 2.2mm and median cumulative growth was 23.6mm. Traction-related complications occurred in 13 (30%) children with median time of 8days from traction initiation. Daily change >12% in leading-to trailing clip distance demonstrated 86% sensitivity and 92% specificity for indicating traction-related complications (area under the curve [AUC] 0.853). Cumulative change >30% in leading- to trailing-clip distance during traction was 85% sensitive and 85% specific for indicating traction complications (AUC 0.874). Portable chest radiograph measurements can serve as a quantitative surrogate for esophageal segment position in long-gap esophageal atresia. An increase of >12% between two sequential chest radiographs or >30% increase over the traction period in leading- to trailing-clip distance is highly associated with traction system complications.