AI used to identify pancreatic cancer in CT scans Cancer CT Pancreatic Cancer NTU_Hospital nvidia ResearchNTUML radiology_rsna
Study: Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study. Image Credit: Suttha Burawonk / Shutterstock
In one of their previous works, the researchers demonstrated that a DL-based convolutional neural network could accurately distinguish pancreatic cancer from the non-cancerous pancreas. The researchers searched the registry of the National Health Insurance Major Illness Certificate to retrieve CT studies of 669 patients with newly diagnosed pancreatic cancer between January 2018 and July 2019. Likewise, they extracted CT studies of 72 kidney and liver donors during the same time from the NHI database, which formed the control group.
Study findings In the internal test set, the CAD tool sensitivity and specificity to distinguish between CT malignancies and control studies were 89.7% and 92.8%, respectively, with nearly 75% sensitivity for pancreatic cancers smaller than 2 cm. Overall, it demonstrated high robustness and generalizability.
Belgique Dernières Nouvelles, Belgique Actualités
Similar News:Vous pouvez également lire des articles d'actualité similaires à celui-ci que nous avons collectés auprès d'autres sources d'information.
Final results of the PATHFINDER study by GRAIL on multi-cancer early detection tests announcedA new press release announced the results of their interventional PATHFINDER study on the early detection of cancer using multi-cancer early detection (MCED) blood tests.
Lire la suite »
Kerry Katona books CT scan after mum’s heart attack five months agoThe former Atomic Kitten singer is taking her health more seriously following her mother's heart attack earlier this year.
Lire la suite »