Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution.

PURPOSE: The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations. MATERIALS AND METHODS: Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio. RESULTS: Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850-0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810-0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668-0.760) and of 0.723 (95% CI: 0.668-0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set. CONCLUSION: This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

Assessing fluvial organic carbon flux and its response to short climate variability and damming on a large-scale tropical Asian river basin.

Fluvial organic carbon (OC) transfer is an essential resource for downstream ecosystems. Multiple factors affect its transfer process, e.g., climate or anthropogenic activities. Quantifying OC fluxes with fine spatiotemporal resolution is challenging in anthropised catchments. This study aims to quantify daily OC dynamics and to assess the impacts of short climate variability and damming on OC spatiotemporal transfer processes in a large tropical Asian river basin (the Red River) for an extended period (2003-2013) by combining empirical equations with modelling outputs. Firstly, empirical equations for calculating dissolved (DOC) and particulate OC (POC) concentrations were calibrated based on in-situ sampling data. Then, simulated daily discharge (Q) and suspended sediment concentrations were used to quantify daily OC fluxes. Results show that the parameters of the DOC and POC equations well represent the subbasins characteristics, underlining the effects of soil OC content, mean annual Q and Chlorophyll a. DOC and POC exports reached 222 and 406 kt yr-1 at the basin outlet, accounting for 0.38 % of the total OC (TOC) exported by Asian rivers to the ocean. However, the specific yields of DOC (1.62 t km-2 yr-1) and POC (2.96 t km-2 yr-1) of the Red River basin were ~ 1.5 times those of other Asian basins. By comparing a reference scenario (without dams) to current conditions, we estimated 12 % and 88 % decreases in DOC and POC fluxes between 2008-2013 and 2003-2007, mainly due to damming. This study shows that climate variability may not impact OC dynamics in rivers as it explained <2 % of the variations. However, dam management, especially recent ones operating since 2008, deeply influences OC variations as the POC/TOC ratio decreased from 86 % to 47 %. Damming significantly decreased POC exports due to sediment retention, altering the equilibrium of OC cycling downstream, which may impact the food chain.

Detection and quantification of pulmonary embolism with artificial intelligence: The SFR 2022 artificial intelligence data challenge.

PURPOSE: In 2022, the French Society of Radiology together with the French Society of Thoracic Imaging and CentraleSupelec organized their 13th data challenge. The aim was to aid in the diagnosis of pulmonary embolism, by identifying the presence of pulmonary embolism and by estimating the ratio between right and left ventricular (RV/LV) diameters, and an arterial obstruction index (Qanadli's score) using artificial intelligence. MATERIALS AND METHODS: The data challenge was composed of three tasks: the detection of pulmonary embolism, the RV/LV diameter ratio, and Qanadli's score. Sixteen centers all over France participated in the inclusion of the cases. A health data hosting certified web platform was established to facilitate the inclusion process of the anonymized CT examinations in compliance with general data protection regulation. CT pulmonary angiography images were collected. Each center provided the CT examinations with their annotations. A randomization process was established to pool the scans from different centers. Each team was required to have at least a radiologist, a data scientist, and an engineer. Data were provided in three batches to the teams, two for training and one for evaluation. The evaluation of the results was determined to rank the participants on the three tasks. RESULTS: A total of 1268 CT examinations were collected from the 16 centers following the inclusion criteria. The dataset was split into three batches of 310, 580 and 378 C T examinations provided to the participants respectively on September 5, 2022, October 7, 2022 and October 9, 2022. Seventy percent of the data from each center were used for training, and 30% for the evaluation. Seven teams with a total of 48 participants including data scientists, researchers, radiologists and engineering students were registered for participation. The metrics chosen for evaluation included areas under receiver operating characteristic curves, specificity and sensitivity for the classification task, and the coefficient of determination r2 for the regression tasks. The winning team achieved an overall score of 0.784. CONCLUSION: This multicenter study suggests that the use of artificial intelligence for the diagnosis of pulmonary embolism is possible on real data. Moreover, providing quantitative measures is mandatory for the interpretability of the results, and is of great aid to the radiologists especially in emergency settings.

Global carbon sequestration through continental chemical weathering in a climatic change context.

This study simulates carbon dioxide (CO2) sequestration in 300 major world river basins (about 70% of global surface area) through carbonates dissolution and silicate hydrolysis. For each river basin, the daily timescale impacts under the RCP 2.6 and RCP 8.5 climate scenarios were assessed relative to a historical baseline (1969-1999) using a cascade of models accounting for the hydrological evolution under climate change scenarios. Here we show that the global temporal evolution of the CO2 uptake presents a general increase in the annual amount of CO2 consumed from 0.247 ± 0.045 Pg C year-1 to 0.261 and 0.273 ± 0.054 Pg C year-1, respectively for RCP 2.6 and RCP 8.5. Despite showing a general increase in the global daily carbon sequestration, both climate scenarios show a decrease between June and August. Such projected changes have been mapped and evaluated against changes in hydrology, identifying hot spots and moments for the annual and seasonal periods.