Chest CT for rapid triage of patients in multiple emergency departments during COVID-19 epidemic: experience report from a large French university hospital.

OBJECTIVES: To assess the diagnostic performances of chest CT for triage of patients in multiple emergency departments during COVID-19 epidemic, in comparison with reverse transcription polymerase chain reaction (RT-PCR) test. METHOD: From March 3 to April 4, 2020, 694 consecutive patients from three emergency departments of a large university hospital, for which a hospitalization was planned whatever the reasons, i.e., COVID- or non-COVID-related, underwent a chest CT and one or several RT-PCR tests. Chest CTs were rated as "Surely COVID+," "Possible COVID+," or "COVID-" by experienced radiologists. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated using the final RT-PCR test as standard of reference. The delays for CT reports and RT-PCR results were recorded and compared. RESULTS: Among the 694 patients, 287 were positive on the final RT-PCR exam. Concerning the 694 chest CT, 308 were rated as "Surely COVID+", 34 as "Possible COVID+," and 352 as "COVID-." When considering only the "Surely COVID+" CT as positive, accuracy, sensitivity, specificity, PPV, and NPV reached 88.9%, 90.2%, 88%, 84.1%, and 92.7%, respectively, with respect to final RT-PCR test. The mean delay for CT reports was three times shorter than for RT-PCR results (187 ± 148 min versus 573 ± 327 min, p < 0.0001). CONCLUSION: During COVID-19 epidemic phase, chest CT is a rapid and most probably an adequately reliable tool to refer patients requiring hospitalization to the COVID+ or COVID- hospital units, when response times for virological tests are too long. KEY POINTS: • In a large university hospital in Lyon, France, the accuracy, sensitivity, specificity, PPV, and NPV of chest CT for COVID-19 reached 88.9%, 90.2%, 88%, 84.1%, and 92.7%, respectively, using RT-PCR as standard of reference. • The mean delay for CT reports was three times shorter than for RT-PCR results (187 ± 148 min versus 573 ± 327 min, p < 0.0001). • Due to high accuracy of chest CT for COVID-19 and shorter time for CT reports than RT-PCR results, chest CT can be used to orient patients suspected to be positive towards the COVID+ unit to decrease congestion in the emergency departments.

Synthetic MR image generation of macrotrabecular-massive hepatocellular carcinoma using generative adversarial networks.

PURPOSE: The purpose of this study was to develop a method for generating synthetic MR images of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC). MATERIALS AND METHODS: A set of abdominal MR images including fat-saturated T1-weighted images obtained during the arterial and portal venous phases of enhancement and T2-weighted images of 91 patients with MTM-HCC, and another set of MR abdominal images from 67 other patients were used. Synthetic images were obtained using a 3-step pipeline that consisted in: (i), generating a synthetic MTM-HCC tumor on a neutral background; (ii), randomly selecting a background among the 67 patients and a position inside the liver; and (iii), merging the generated tumor in the background at the specified location. Synthetic images were qualitatively evaluated by three radiologists and quantitatively assessed using a mix of 1-nearest neighbor classifier metric and Fréchet inception distance. RESULTS: A set of 1000 triplets of synthetic MTM-HCC images with consistent contrasts were successfully generated. Evaluation of selected synthetic images by three radiologists showed that the method gave realistic, consistent and diversified images. Qualitative and quantitative evaluation led to an overall score of 0.64. CONCLUSION: This study shows the feasibility of generating realistic synthetic MR images with very few training data, by leveraging the wide availability of liver backgrounds. Further studies are needed to assess the added value of those synthetic images for automatic diagnosis of MTM-HCC.

A conventional-to-spectral CT image translation augmentation workflow for robust contrast injection-independent organ segmentation.

PURPOSE: In computed tomography (CT) cardiovascular imaging, the numerous contrast injection protocols used to enhance structures make it difficult to gather training datasets for deep learning applications supporting diverse protocols. Moreover, creating annotations on noncontrast scans is extremely tedious. Recently, spectral CT's virtual-noncontrast images (VNC) have been used as data augmentation to train segmentation networks performing on enhanced and true-noncontrast (TNC) scans alike, while improving results on protocols absent of their training dataset. However, spectral data are not widely available, making it difficult to gather specific datasets for each task. As a solution, we present a data augmentation workflow based on a trained image translation network, to bring spectral-like augmentation to any conventional CT dataset. METHOD: The conventional CT-to-spectral image translation network (HUSpectNet) was first trained to generate VNC from conventional housnfied units images (HU), using an unannotated spectral dataset of 1830 patients. It was then tested on a second dataset of 300 spectral CT scans by comparing VNC generated through deep learning (VNCDL ) to their true counterparts. To illustrate and compare our workflow's efficiency with true spectral augmentation, HUSpectNet was applied to a third dataset of 112 spectral scans to generate VNCDL along HU and VNC images. Three different three-dimensional (3D) networks (U-Net, X-Net, and U-Net++) were trained for multilabel heart segmentation, following four augmentation strategies. As baselines, trainings were performed on contrasted images without (HUonly) and with conventional gray-values augmentation (HUaug). Then, the same networks were trained using a proportion of contrasted and VNC/VNCDL images (TrueSpec/GenSpec). Each training strategy applied to each architecture was evaluated using Dice coefficients on a fourth multicentric multivendor single-energy CT dataset of 121 patients, including different contrast injection protocols and unenhanced scans. The U-Net++ results were further explored with distance metrics on every label. RESULTS: Tested on 300 full scans, our HUSpectNet translation network shows a mean absolute error of 6.70 ± 2.83 HU between VNCDL and VNC, while peak signal-to-noise ratio reaches 43.89 dB. GenSpec and TrueSpec show very close results regardless of the protocol and used architecture: mean Dice coefficients (DSCmean ) are equal with a margin of 0.006, ranging from 0.879 to 0.938. Their performances significantly increase on TNC scans (p-values < 0.017 for all architectures) compared to HUonly and HUaug, with DSCmean of 0.448/0.770/0.879/0.885 for HUonly/HUaug/TrueSpec/GenSpec using the U-Net++ architecture. Significant improvements are also noted for all architectures on chest-abdominal-pelvic scans (p-values < 0.007) compared to HUonly and for pulmonary embolism scans (p-values < 0.039) compared to HUaug. Using U-Net++, DSCmean reaches 0.892/0.901/0.903 for HUonly/TrueSpec/GenSpec on pulmonary embolism scans and 0.872/0.896/0.896 for HUonly/TrueSpec/GenSpec on chest-abdominal-pelvic scans. CONCLUSION: Using the proposed workflow, we trained versatile heart segmentation networks on a dataset of conventional enhanced CT scans, providing robust predictions on both enhanced scans with different contrast injection protocols and TNC scans. The performances obtained were not significantly inferior to training the model on a genuine spectral CT dataset, regardless of the architecture implemented. Using a general-purpose conventional-to-spectral CT translation network as data augmentation could therefore contribute to reducing data collection and annotation requirements for machine learning-based CT studies, while extending their range of application.

Spectral augmentation for heart chambers segmentation on conventional contrasted and unenhanced CT scans: an in-depth study.

PURPOSE: Recently, machine learning has outperformed established tools for automated segmentation in medical imaging. However, segmentation of cardiac chambers still proves challenging due to the variety of contrast agent injection protocols used in clinical practice, inducing disparities of contrast between cavities. Hence, training a generalist network requires large training datasets representative of these protocols. Furthermore, segmentation on unenhanced CT scans is further hindered by the challenge of obtaining ground truths from these images. Newly available spectral CT scanners allow innovative image reconstructions such as virtual non-contrast (VNC) imaging, mimicking non-contrasted conventional CT studies from a contrasted scan. Recent publications have demonstrated that networks can be trained using VNC to segment contrasted and unenhanced conventional CT scans to reduce annotated data requirements and the need for annotations on unenhanced scans. We propose an extensive evaluation of this statement. METHOD: We undertake multiple trainings of a 3D multi-label heart segmentation network with (HU-VNC) and without (HUonly) VNC as augmentation, using decreasing training dataset sizes (114, 76, 57, 38, 29, 19 patients). At each step, both networks are tested on a multi-vendor, multi-centric dataset of 122 patients, including different protocols: pulmonary embolism (PE), chest-abdomen-pelvis (CAP), heart CT angiography (CTA) and true non-contrast scans (TNC). An in-depth comparison of resulting Dice coefficients and distance metrics is performed for the networks trained on the largest dataset. RESULTS: HU-VNC-trained on 57 patients significantly outperforms HUonly trained on 114 regarding CAP and TNC scans (mean Dice coefficients of 0.881/0.835 and 0.882/0.416, respectively). When trained on the largest dataset, significant improvements in all labels are noted for TNC and CAP scans (mean Dice coefficient of 0.882/0.416 and 0.891/0.835, respectively). CONCLUSION: Adding VNC images as training augmentation allows the network to perform on unenhanced scans and improves segmentations on other imaging protocols, while using a reduced training dataset.