ABSTRACT
PURPOSE: The purpose of the 2023 SFR data challenge was to invite researchers to develop artificial intelligence (AI) models to identify the presence of a pancreatic mass and distinguish between benign and malignant pancreatic masses on abdominal computed tomography (CT) examinations. MATERIALS AND METHODS: Anonymized abdominal CT examinations acquired during the portal venous phase were collected from 18 French centers. Abdominal CT examinations were divided into three groups including CT examinations with no lesion, CT examinations with benign pancreatic mass, or CT examinations with malignant pancreatic mass. Each team included at least one radiologist, one data scientist, and one engineer. Pancreatic lesions were annotated by expert radiologists. CT examinations were distributed in balanced batches via a Health Data Hosting certified platform. Data were distributed into four batches, two for training, one for internal evaluation, and one for the external evaluation. Training used 83 % of the data from 14 centers and external evaluation used data from the other four centers. The metric (i.e., final score) used to rank the participants was a weighted average of mean sensitivity, mean precision and mean area under the curve. RESULTS: A total of 1037 abdominal CT examinations were divided into two training sets (including 500 and 232 CT examinations), an internal evaluation set (including 139 CT examinations), and an external evaluation set (including 166 CT examinations). The training sets were distributed on September 7 and October 13, 2023, and evaluation sets on October 15, 2023. Ten teams with a total of 93 members participated to the data challenge, with the best final score being 0.72. CONCLUSION: This SFR 2023 data challenge based on multicenter CT data suggests that the use of AI for pancreatic lesions detection is possible on real data, but the distinction between benign and malignant pancreatic lesions remains challenging.
ABSTRACT
More than 40% of endovascular therapy (EVT) fail to achieve complete reperfusion of the territory of the occluded artery in patients with acute ischemic stroke (AIS). Understanding factors influencing EVT could help overcome its limitations. Our objective was to study the impact of thrombus cell composition on EVT procedures, using a simulation system for modeling thrombus-induced large vessel occlusion (LVO) in flow conditions. In an open comparative trial, we analyzed the behavior of size-standardized platelet-rich and red blood cells (RBC)-rich thrombi during simulated stent retriever-mediated EVT procedures. Sixteen simulated EVT procedures were performed (8 RBC- vs. 8 platelet-rich thrombi). Platelet-rich thrombi were associated with a higher number of stent retriever passes (p = 0.03) and a longer procedure duration (p = 0.02) compared to RBC-rich thrombi. Conversely, RBC-rich thrombi released more embolic fragments than platelet-rich thrombi (p = 0.004). Both RBC-rich and platelet-rich thrombi underwent drastic compaction after being injected into the in vitro circulation model, and histologic analyses showed that these EVT-retrieved thrombi displayed features comparable to those previously observed in thrombi from patients with AIS patients having LVO, including a marked structural dichotomy between RBC- and platelet-rich areas. Our results show that the injection of in vitro-produced thrombi in artificial cerebrovascular arterial networks is suitable for testing recanalization efficacy and the risk of embolization of EVT devices and strategies in association with thrombus cell composition.
