Influence of Monoenergetic Images at Different Energy Levels in Dual-Energy Spectral CT on the Accuracy of Computer-Aided Detection for Pulmonary Embolism

Improved detection of small pulmonary embolism on unenhanced computed tomography using an artificial intelligence-based algorithm - a single centre retrospective study

To preliminarily verify the feasibility of a deep-learning (DL) artificial intelligence (AI) model to localize pulmonary embolism (PE) on unenhanced chest-CT by comparison with pulmonary artery (PA) CT angiography (CTA). In a monocentric study, we retrospectively reviewed 99 oncological patients (median age in years: 64 (range: 28-92 years); percentage of female: 39.4%) who received unenhanced and contrast-enhanced chest CT examinations in one session between January 2020 and October 2022 and who were diagnosed incidentally with PE. Findings in the unenhanced images were correlated with the contrast-enhanced images, which were considered the gold standard for central, segmental and subsegmental PE. The new algorithm was trained and tested based on the 99 unenhanced chest-CT image data sets. Based on them, candidate boxes, which were output by the model, were post-processed by evaluating whether the predicted box intersects with the patient's lung segmentation at any position. The AI-based algorithm proved to have an overall sensitivity of 54.5% for central, of 81.9% for segmental and 80.0% for subsegmental PE if taking n = 20 candidate boxes into account. Depending on the localization of the pulmonary embolism, the detection rate for only one box was: 18.1% central, 34.7% segmental and 0.0% subsegmental. The median volume of the clots differed significantly between the three subgroups and was 846.5 mm3 (IQR:591.1-964.8) in central, 201.3 mm3 (IQR:98.3-390.9) in segmental and 110.6 mm3 (IQR:94.3-128.0) in subsegmental PA (p < 0.05). The new algorithm proved to have high sensitivity in detecting PE in particular in segmental/subsegmental localization and may guide to decide whether a second contrast enhanced CT is necessary.

Value of low-keV virtual monoenergetic plus dual-energy computed tomographic imaging for detection of acute pulmonary embolism

Objective

To compare diagnostic values between the 40 keV virtual monoenergetic plus (40 keV VMI+) dual source dual energy computed tomography (DSDECT) pulmonary angiography images and the standard mixed (90 and 150 kV) images for the detection of acute pulmonary embolism (PE).

Methods

Chest DSDECTs of 64 patients who were suspected of having acute PE were retrospectively reviewed by two independent reviewers. The assessments of acute PE of all patients on a per-location basis were compared between the 40 keV VMI+ and the standard mixed datasets (reference standard) with a two-week interval.

Results

This study consisted of 64 patients (33 women and 31 men; mean age, 60.2 years; range 18–90 years), with a total of 512 locations. The interobserver agreement (Kappa) for detection of acute PE using the 40 keV VMI+ images and the standard mixed CT images were 0.7478 and 0.8750 respectively. The area under receiver operating characteristics (AuROC) for diagnosis of acute PE using the 40 keV VMI+ was 0.882. Four locations (0.78%) revealed a false negative result. Hypodense filling defects were identified in twelve locations (1.95%) in the 40 keV VMI+ images but had been interpreted as a negative study in the standard mixed CT images. The repeated reviews revealed that each location contained a hypodense filling defect but was overlooked on the standard mixed CT images.

Conclusions

Low-energy VMI + DSDECT images have beneficial in improving the diagnostic value of acute PE in doubtful or disregarded standard mixed images.

Jointly Optimized Deep Neural Networks to Synthesize Monoenergetic Images from Single-Energy CT Angiography for Improving Classification of Pulmonary Embolism

Detector-based spectral CT offers the possibility of obtaining spectral information from which discrete acquisitions at different energy levels can be derived, yielding so-called virtual monoenergetic images (VMI). In this study, we aimed to develop a jointly optimized deep-learning framework based on dual-energy CT pulmonary angiography (DE-CTPA) data to generate synthetic monoenergetic images (SMI) for improving automatic pulmonary embolism (PE) detection in single-energy CTPA scans. For this purpose, we used two datasets: our institutional DE-CTPA dataset D1, comprising polyenergetic arterial series and the corresponding VMI at low-energy levels (40 keV) with 7892 image pairs, and a 10% subset of the 2020 RSNA Pulmonary Embolism CT Dataset D2, which consisted of 161,253 polyenergetic images with dichotomous slice-wise annotations (PE/no PE). We trained a fully convolutional encoder-decoder on D1 to generate SMI from single-energy CTPA scans of D2, which were then fed into a ResNet50 network for training of the downstream PE classification task. The quantitative results on the reconstruction ability of our framework revealed high-quality visual SMI predictions with reconstruction results of 0.984 ± 0.002 (structural similarity) and 41.706 ± 0.547 dB (peak signal-to-noise ratio). PE classification resulted in an AUC of 0.84 for our model, which achieved improved performance compared to other naïve approaches with AUCs up to 0.81. Our study stresses the role of using joint optimization strategies for deep-learning algorithms to improve automatic PE detection. The proposed pipeline may prove to be beneficial for computer-aided detection systems and could help rescue CTPA studies with suboptimal opacification of the pulmonary arteries from single-energy CT scanners.

Dual-energy CT in pulmonary vascular disease

Dual-energy CT (DECT) imaging is a technique that extends the capabilities of CT beyond that of established densitometric evaluations. CT pulmonary angiography (CTPA) performed with dual-energy technique benefits from both the availability of low kVp CT data and also the concurrent ability to quantify iodine enhancement in the lung parenchyma. Parenchymal enhancement, presented as pulmonary perfused blood volume maps, may be considered as a surrogate of pulmonary perfusion. These distinct capabilities have led to new opportunities in the evaluation of pulmonary vascular diseases. Dual-energy CTPA offers the potential for improvements in pulmonary emboli detection, diagnostic confidence, and most notably severity stratification. Furthermore, the appreciated insights of pulmonary vascular physiology conferred by DECT have resulted in increased use for the assessment of pulmonary hypertension, with particular utility in the subset of patients with chronic thromboembolic pulmonary hypertension. With the increasing availability of dual energy-capable CT systems, dual energy CTPA is becoming a standard-of-care protocol for CTPA acquisition in acute PE. Furthermore, qualitative and quantitative pulmonary vascular DECT data heralds promise for the technique as a "one-stop shop" for diagnosis and surveillance assessment in patients with pulmonary hypertension. This review explores the current application, clinical value, and limitations of DECT imaging in acute and chronic pulmonary vascular conditions. It should be noted that certain manufacturers and investigators prefer alternative terms, such as spectral or multi-energy CT imaging. In this review, the term dual energy is utilised, although readers can consider these terms synonymous for purposes of the principles explained.

Present Limitations of Artificial Intelligence in the Emergency Setting - Performance Study of a Commercial, Computer-Aided Detection Algorithm for Pulmonary Embolism

PURPOSE

 Since artificial intelligence is transitioning from an experimental stage to clinical implementation, the aim of our study was to evaluate the performance of a commercial, computer-aided detection algorithm of computed tomography pulmonary angiograms regarding the presence of pulmonary embolism in the emergency room.

MATERIALS AND METHODS

 This retrospective study includes all pulmonary computed tomography angiogram studies performed in a large emergency department over a period of 36 months that were analyzed by two radiologists experienced in emergency radiology to set a reference standard. Original reports and computer-aided detection results were compared regarding the detection of lobar, segmental, and subsegmental pulmonary embolism. All computer-aided detection findings were analyzed concerning the underlying pathology. False-positive findings were correlated to the contrast-to-noise ratio.

RESULTS

 Expert reading revealed pulmonary embolism in 182 of 1229 patients (49 % men, 10-97 years) with a total of 504 emboli. The computer-aided detection algorithm reported 3331 findings, including 258 (8 %) true-positive findings and 3073 (92 %) false-positive findings. Computer-aided detection analysis showed a sensitivity of 47 % (95 %CI: 33-61 %) on the lobar level and 50 % (95 %CI 43-56 %) on the subsegmental level. On average, there were 2.25 false-positive findings per study (median 2, range 0-25). There was no significant correlation between the number of false-positive findings and the contrast-to-noise ratio (Spearman's Rank Correlation Coefficient = 0.09). Soft tissue (61.0 %) and pulmonary veins (24.1 %) were the most common underlying reasons for false-positive findings.

CONCLUSION

 Applied to a population at a large emergency room, the tested commercial computer-aided detection algorithm faced relevant performance challenges that need to be addressed in future development projects.

KEY POINTS

  · Computed tomography pulmonary angiograms are frequently acquired in emergency radiology.. · Computer-aided detection algorithms (CADs) can support image analysis.. · CADs face challenges regarding false-positive and false-negative findings.. · Radiologists using CADs need to be aware of these limitations.. · Further software improvements are necessary ahead of implementation in the daily routine..

CITATION FORMAT

· Müller-Peltzer K, Kretzschmar L, Negrão de Figueiredo G et al. Present Limitations of Artificial Intelligence in the Emergency Setting - Performance Study of a Commercial, Computer-Aided Detection Algorithm for Pulmonary Embolism. Fortschr Röntgenstr 2021; DOI: 10.1055/a-1515-2923.