Purpose

Plain radiography of the cervical spine is used as a screening test for trauma patients. We evaluated the diagnostic yield of performing anteroposterior (AP), odontoid, and oblique views in addition to the lateral view in the current era when radiographs are performed only on low-risk patients.

Methods

All imaging reports from cervical spine radiography studies on patients aged 18 years and older in the emergency room of a major academic medical center between November 22, 2003, and January 17, 2012, were retrospectively reviewed. For the clinical workflow employed at the time of study acquisition, radiologists prospectively reviewed the lateral projection and subsequently reviewed the entirety of the images obtained. Exam reports and, when necessary, images were reviewed to determine which patients had fractures and on which projection the fractures were identified.

Results

Six fractures were detected in 7218 exams. Three of these fractures were identified on the lateral radiograph, and three of these fractures were visualized on the additional projections (two on oblique and one on odontoid views). The yield of the additional projections is one fracture per 9713 radiographic projections (90% confidence interval of one fracture per 1245-47,946 examinations). For two of the patients with fractures identified on the lateral projection, an additional fracture was seen when CT was then performed.

Conclusions

Performing additional radiographs of the cervical spine including AP, odontoid, and bilateral oblique projections in trauma patients with low pretest probability of fracture augments the diagnostic yield of lateral radiographs. Considering the potential for devastating neurological outcomes from missed cervical fractures, addition of AP, odontoid, and oblique projections continues to detect fractures at a low rate.

Supplemental material is available for this article.

Explainability of convolutional neural networks (CNNs) is integral for their adoption into radiological practice. Commonly used attribution methods localize image areas important for CNN prediction but do not characterize relevant imaging features underlying these areas, acting as a barrier to the adoption of CNNs for clinical use. We therefore propose Semantic Exploration and Explainability using a Style-based Generative Adversarial Autoencoder Network (SEE-GAAN), an explainability framework that uses latent space manipulation to generate a sequence of synthetic images that semantically visualizes how clinical and CNN features manifest within medical images. Visual analysis of changes in these sequences then facilitates the interpretation of features, thereby improving explainability. SEE-GAAN was first developed on a cohort of 26,664 chest radiographs across 15,409 patients from our institution. SEE-GAAN sequences were then generated across several clinical features and CNN predictions of NT-pro B-type natriuretic peptide (BNPP) as a proxy for acute heart failure. Radiological interpretations indicated SEE-GAAN sequences captured relevant changes in anatomical and pathological morphology associated with clinical and CNN predictions and clarified ambiguous areas highlighted by commonly used attribution methods. Our study demonstrates SEE-GAAN can facilitate our understanding of clinical features for imaging biomarker exploration and improve CNN transparency over commonly used explainability methods.

CT pulmonary angiography (CTPA) is the first-line imaging test for evaluation of acute pulmonary emboli. However, diagnostic quality is heterogeneous across institutions and is frequently limited by suboptimal pulmonary artery (PA) contrast enhancement. In this retrospective study, a deep learning algorithm for measuring enhancement of the central PAs was developed and assessed for feasibility of its use in quality improvement of CTPA. In a convenience sample of 450 patients, automated measurement of CTPA enhancement showed high agreement with manual radiologist measurement (r = 0.996). Using a threshold of less than 250 HU for suboptimal enhancement, the sensitivity and specificity of the automated classification were 100% and 99.5%, respectively. The algorithm was further evaluated in a random sampling of 3195 CTPA examinations from January 2019 through May 2021. Beginning in January 2021, the scanning protocol was transitioned from bolus tracking to a timing bolus strategy. Automated analysis of these examinations showed that most suboptimal examinations following the change in protocol were performed using one scanner, highlighting the potential value of deep learning algorithms for quality improvement in the radiology department. Keywords: CT Angiography, Pulmonary Arteries © RSNA, 2022.

Non-contrast magnetic resonance angiography (NC-MRA), including fresh blood imaging (FBI), is a suitable choice for evaluating patients with peripheral artery disease (PAD). We evaluated standard FBI (sFBI) and centric ky-kz FBI (cFBI) acquisitions, using 1D and 2D parallel imaging factors (PIFs) to assess the trade-off between scan time and image quality due to blurring. The bilateral legs of four volunteers (mean age 33 years, two females) were imaged in the coronal plane using a body array coil with a posterior spine coil. Two types of sFBI and cFBI sequences with 1D PIF factor 5 in the phase encode (PE) direction (in-plane) and 2D PIF 3 (PE) × 2 (slice encode (SE)) (in-plane, through-slice) were studied. Image quality was evaluated by a radiologist, the vessels signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were measured, and major vessel width was measured on the coronal maximum intensity projection (MIP) and 80-degree MIP. Results showed significant time reductions from 184 to 206 s on average when using sFBI down to 98 to 162 s when using cFBI (p = 0.003). Similar SNRs (averaging 200 to 370 across all sequences and PIF) and CNRs (averaging 190 to 360) for all techniques (p > 0.08) were found. There was no significant difference in the image quality (averaging 4.0 to 4.5; p > 0.2) or vessel width (averaging 4.1 to 4.9 mm; p > 0.1) on coronal MIP due to sequence or PIF. However, vessel width measured using 80-degree MIP demonstrated a significantly wider vessel in cFBI (5.6 to 6.8 mm) compared to sFBI (4.5 to 4.7 mm) (p = 0.022), and in 1D (4.7 to 6.8 mm) compared to 2D (4.5 to 5.6 mm) (p < 0.05) PIF. This demonstrated a trade-off in T2 blurring between 1D and 2D PIF: 1D using a PIF of 5 shortened the acquisition window, resulting in sharper arterial blood vessels in coronal images but significant blur in the 80-degree MIP. Two-dimensional PIF for cFBI provided a good balance between shorter scan time (relative to sFBI) and good sharpness in both in- and through-plane, while no benefit of 2D PIF was seen for sFBI. In conclusion, this study demonstrated the usefulness of FBI-based techniques for peripheral artery imaging and underscored the need to strike a balance between scan time and image quality in different planes through the use of 2D parallel imaging.

Purpose

To assess the potential of a transfer learning strategy leveraging radiologist supervision to enhance convolutional neural network-based (CNN) localization of pneumonia on radiographs and to further assess the prognostic value of CNN severity quantification on patients evaluated for COVID-19 pneumonia, for whom severity on the presenting radiograph is a known predictor of mortality and intubation.

Materials and methods

We obtained an initial CNN previously trained to localize pneumonia along with 25,684 radiographs used for its training. We additionally curated 1466 radiographs from patients who had a computed tomography (CT) performed on the same day. Regional likelihoods of pneumonia were then annotated by cardiothoracic radiologists, referencing these CTs. Combining data, a preexisting CNN was fine-tuned using transfer learning. Whole-image and regional performance of the updated CNN was assessed using receiver-operating characteristic area under the curve and Dice. Finally, the value of CNN measurements was assessed with survival analysis on 203 patients with COVID-19 and compared against modified radiographic assessment of lung edema (mRALE) score.

Results

Pneumonia detection area under the curve improved on both internal (0.756 to 0.841) and external (0.864 to 0.876) validation data. Dice overlap also improved, particularly in the lung bases (R: 0.121 to 0.433, L: 0.111 to 0.486). There was strong correlation between radiologist mRALE score and CNN fractional area of involvement (ρ=0.85). Survival analysis showed similar, strong prognostic ability of the CNN and mRALE for mortality, likelihood of intubation, and duration of hospitalization among patients with COVID-19.

Conclusions

Radiologist-supervised transfer learning can enhance the ability of CNNs to localize and quantify the severity of disease. Closed-loop systems incorporating radiologists may be beneficial for continued improvement of artificial intelligence algorithms.

Aims

To develop an automated method for bloodpool segmentation and imaging plane re-slicing of cardiac computed tomography (CT) via deep learning (DL) for clinical use in coronary artery disease (CAD) wall motion assessment and reproducible longitudinal imaging.

Methods and results

One hundred patients who underwent clinically indicated cardiac CT scans with manually segmented left ventricle (LV) and left atrial (LA) chambers were used for training. For each patient, long-axis (LAX) and short-axis planes were manually defined by an imaging expert. A DL model was trained to predict bloodpool segmentations and imaging planes. Deep learning bloodpool segmentations showed close agreement with manual LV [median Dice: 0.91, Hausdorff distance (HD): 6.18 mm] and LA (Dice: 0.93, HD: 7.35 mm) segmentations and a strong correlation with manual ejection fraction (Pearson r: 0.95 LV, 0.92 LA). Predicted planes had low median location (6.96 mm) and angular orientation (7.96 ° ) errors which were comparable to inter-reader differences (P > 0.71). 84-97% of DL-prescribed LAX planes correctly intersected American Heart Association segments, which was comparable (P > 0.05) to manual slicing. In a test cohort of 144 patients, we evaluated the ability of the DL approach to provide diagnostic imaging planes. Visual scoring by two blinded experts determined ≥94% of DL-predicted planes to be diagnostically adequate. Further, DL-enabled visualization of LV wall motion abnormalities due to CAD and provided reproducible planes upon repeat imaging.

Conclusion

A volumetric, DL approach provides multiple chamber segmentations and can re-slice the imaging volume along standardized cardiac imaging planes for reproducible wall motion abnormality and functional assessment.

Purpose

To assess if a novel automated method to spatially delineate and quantify the extent of hypoperfusion on multienergy CT angiograms can aid the evaluation of chronic thromboembolic pulmonary hypertension (CTEPH) disease severity.

Materials and methods

Multienergy CT angiograms obtained between January 2018 and December 2020 in 51 patients with CTEPH (mean age, 47 years ± 17 [SD]; 27 women) were retrospectively compared with those in 110 controls with no imaging findings suggestive of pulmonary vascular abnormalities (mean age, 51 years ± 16; 81 women). Parenchymal iodine values were automatically isolated using deep learning lobar lung segmentations. Low iodine concentration was used to delineate areas of hypoperfusion and calculate hypoperfused lung volume (HLV). Receiver operating characteristic curves, correlations with preoperative and postoperative changes in invasive hemodynamics, and comparison with visual assessment of lobar hypoperfusion by two expert readers were evaluated.

Results

Global HLV correctly separated patients with CTEPH from controls (area under the receiver operating characteristic curve = 0.84; 10% HLV cutoff: 90% sensitivity, 72% accuracy, and 64% specificity) and correlated moderately with hemodynamic severity at time of imaging (pulmonary vascular resistance [PVR], ρ = 0.67; P < .001) and change after surgical treatment (∆PVR, ρ = -0.61; P < .001). In patients surgically classified as having segmental disease, global HLV correlated with preoperative PVR (ρ = 0.81) and postoperative ∆PVR (ρ = -0.70). Lobar HLV correlated moderately with expert reader lobar assessment (ρ_HLV = 0.71 for reader 1; ρ_HLV = 0.67 for reader 2).

Conclusion

Automated quantification of hypoperfused areas in patients with CTEPH can be performed from clinical multienergy CT examinations and may aid clinical evaluation, particularly in patients with segmental-level disease.Keywords: CT-Spectral Imaging (Multienergy), Pulmonary, Pulmonary Arteries, Embolism/Thrombosis, Chronic Thromboembolic Pulmonary Hypertension, Multienergy CT, Hypoperfusion© RSNA, 2023.

Quantitative imaging measurements can be facilitated by artificial intelligence (AI) algorithms, but how they might impact decision-making and be perceived by radiologists remains uncertain. After creation of a dedicated inspiratory-expiratory CT examination and concurrent deployment of a quantitative AI algorithm for assessing air trapping, five cardiothoracic radiologists retrospectively evaluated severity of air trapping on 17 examination studies. Air trapping severity of each lobe was evaluated in three stages: qualitatively (visually); semiquantitatively, allowing manual region-of-interest measurements; and quantitatively, using results from an AI algorithm. Readers were surveyed on each case for their perceptions of the AI algorithm. The algorithm improved interreader agreement (intraclass correlation coefficients: visual, 0.28; semiquantitative, 0.40; quantitative, 0.84; P < .001) and improved correlation with pulmonary function testing (forced expiratory volume in 1 second-to-forced vital capacity ratio) (visual r = -0.26, semiquantitative r = -0.32, quantitative r = -0.44). Readers perceived moderate agreement with the AI algorithm (Likert scale average, 3.7 of 5), a mild impact on their final assessment (average, 2.6), and a neutral perception of overall utility (average, 3.5). Though the AI algorithm objectively improved interreader consistency and correlation with pulmonary function testing, individual readers did not immediately perceive this benefit, revealing a potential barrier to clinical adoption. Keywords: Technology Assessment, Quantification © RSNA, 2021.

Purpose

To assess the feasibility of a newly developed algorithm, called deep learning synthetic strain (DLSS), to infer myocardial velocity from cine steady-state free precession (SSFP) images and detect wall motion abnormalities in patients with ischemic heart disease.

Materials and methods

In this retrospective study, DLSS was developed by using a data set of 223 cardiac MRI examinations including cine SSFP images and four-dimensional flow velocity data (November 2017 to May 2021). To establish normal ranges, segmental strain was measured in 40 individuals (mean age, 41 years ± 17 [SD]; 30 men) without cardiac disease. Then, DLSS performance in the detection of wall motion abnormalities was assessed in a separate group of patients with coronary artery disease, and these findings were compared with consensus results of four independent cardiothoracic radiologists (ground truth). Algorithm performance was evaluated by using receiver operating characteristic curve analysis.

Results

Median peak segmental radial strain in individuals with normal cardiac MRI findings was 38% (IQR: 30%-48%). Among patients with ischemic heart disease (846 segments in 53 patients; mean age, 61 years ± 12; 41 men), the Cohen κ among four cardiothoracic readers for detecting wall motion abnormalities was 0.60-0.78. DLSS achieved an area under the receiver operating characteristic curve of 0.90. Using a fixed 30% threshold for abnormal peak radial strain, the algorithm achieved a sensitivity, specificity, and accuracy of 86%, 85%, and 86%, respectively.

Conclusion

The deep learning algorithm had comparable performance with subspecialty radiologists in inferring myocardial velocity from cine SSFP images and identifying myocardial wall motion abnormalities at rest in patients with ischemic heart disease.Keywords: Neural Networks, Cardiac, MR Imaging, Ischemia/Infarction Supplemental material is available for this article. © RSNA, 2023.