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.

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.

Nasogastric tube after small bowel obstruction surgery could be avoided: a retrospective cohort study.

PURPOSE: The safety and feasibility of early removal of nasogastric tube (NGT) after small bowel obstruction (SBO) surgery have not yet been assessed. Such a practice could allow to implement enhanced recovery after surgery (ERAS) protocols after acute SBO surgery. The aims of this study were to assess the safety of early NGT removal by comparing the short-term outcomes of patients with postoperative NGTs and those with no postoperative NGT. METHODS: All patients undergoing surgery for strangulation or adhesive SBO between January the 1st of 2014 and December the 31st of 2017 were retrospectively included. RESULTS: Among the 123 included, NGT was removed immediately after the end of the procedure in 26 cases (21.1%) and 19 patients required NGT replacement (15.4%). In univariate analysis, early removal of NGT was significantly associated with a reduction of overall morbidity, severe morbidity and postoperative ileus occurrence. Multivariate analysis confirmed that NGT left in place was a risk factor for postoperative ileus [Odd Ratio (OR) 4.9, Confidence Interval (CI) 95% 1.3-19.2; p = 0.02], while it has no incidence on severe morbidity. CONCLUSIONS: Early NGT removal after ASBO surgery seemed to be feasible, safe and efficient, at least in selected patients. This primary study represents the initial foundations for building the implementation of ERAS protocols after ASBO surgery.

Diagnosis of single adhesive bands versus matted adhesions in small bowel obstructions: a radiological predictive score.

PURPOSE: The objective was to develop a radiological score obtained from multi-detector computed tomography (MDCT) to differentiate between single band adhesion (SBA) and matted adhesions (MA) as the etiology of small bowel obstruction (SBO). METHODS: All consecutive patients who underwent surgery from January 2013 to June 2018 for adhesion-induced SBO were retrospectively included. RESULTS: Among the 193 patients having surgery for SBO, 119 (61.6%) had SBA and 74 (38.4%) had MA surgically proven. In multivariate analysis, the presence of a beak sign (OR = 3.47, CI [1.26; 9.53], p = 0.02), a closed loop (OR = 11.37, CI [1.84; 70.39], p = 0.009), focal mesenteric haziness (OR = 3.71, CI [1.33; 10.34], p = 0.01) and focal and diffuse peritoneal fluid (OR = 4.30, CI [1.45; 12.73], p = 0.009 and OR = 6.34, CI [1.77; 22.59], p = 0.004, respectively) were significantly associated with SBA. Conversely, the presence of diffuse mesenteric fluid without focal fluid (OR = 0.23, CI [0.06; 0.92], p = 0.04) and an increase of the diameter of the most dilated loop (OR = 0.94, CI [0.90; 0.99], p = 0.02) were inversely associated with SBA. Using the significant predictive factors of SBA, we built a composite score to radiologically predict the etiology of SBO. The area under the receiver operating characteristic (ROC) curve of the score was 0.8274. For a cut-off score of -0.523, sensitivity, specificity and the percentage of patients correctly classified were 78.4%, 84.6% and 80%, respectively. If the score is ≥ 7, the probability that the mechanism of SBO is not SBA was 100%. CONCLUSIONS: The present score, validated in a different population, could be a significant tool in the decision for surgical management.

Incidental findings on emergency CT scans: Predictive factors and medico-economic impact.

PURPOSE: The main objective was to evaluate types and predictive factors of incidental findings (IFs) on multidetector computed tomographies (MDCTs) performed for an emergency department (ED). The secondary aim was to analyze additional investigations, their benefits, side effects, costs and the final diagnoses. METHOD: One thousand consecutive patients over 18 years old who underwent an MDCT in the ED of our institution from January 2011 to November 2011 were retrospectively included, accounting for 300 head MDCTs and 700 other MDCTs. The following criteria were collected in patient electronic medical records: IFs (divided into low and high clinical significance), body areas covered, availability of a prior imaging, radiologist's experience and subspecialty, additional investigations, their outcomes and costs. RESULTS: Among the 1000 included patients, 232 had at least one IF and 122 had at least one IF of high clinical significance (IFCS). There were 340 IFs and 150 IFCSs. A significant association with the presence of at least one IF was noted for older patients, less-experienced radiologists, no subspecialty of the radiologist, the abdominopelvic area, and the absence of prior imaging. Eighteen IFs generated additional investigations in our institution, including five invasive samplings and three surgical operations, with two diagnoses of malignancy (a gastrointestinal stromal tumor and a Bosniak IV cystic renal lesion). One benign iatrogenic complication occurred. Total cost of these investigations was €41,247 (with an average of €2292 per IF investigated). CONCLUSION: IFs on emergency MDCTs were frequent, rarely severe, rarely iatrogenic and relatively expensive.