Publications by authors named "Cynthia Hui"
Article Synopsis
- Hepatocellular carcinoma (HCC) has a high mortality rate, and current diagnostic methods like LI-RADS often lead to indeterminate results, complicating accurate diagnosis.
- Researchers developed four deep learning models using CT scans, finding that the Spatio-Temporal 3D Convolution Network (ST3DCN) performed best, significantly outperforming standard radiological interpretation in identifying HCC.
- The ST3DCN model demonstrated strong diagnostic accuracy in both internal validation (AUCs up to 0.919) and external testing (AUC of 0.901), indicating its potential as an effective tool for HCC diagnosis.
Introduction: Both artificial intelligence (AI) and distal attachment devices have been shown to improve adenoma detection rate and reduce miss rate during colonoscopy. We studied the combined effect of Endocuff and AI on enhancing detection rates of various colonic lesions.
Methods: This was a 3-arm prospective randomized colonoscopy study involving patients aged 40 years or older.
Background And Aims: Blue-light imaging (BLI) is a new image-enhanced endoscopy with a wavelength filter similar to narrow-band imaging (NBI). We compared the 2 with white-light imaging (WLI) on proximal colonic lesion detection and miss rates.
Methods: In this 3-arm prospective randomized study with tandem examination of the proximal colon, we enrolled patients aged ≥40 years.
Background And Aims: Computer-assisted detection (CADe) is a promising technologic advance that enhances adenoma detection during colonoscopy. However, the role of CADe in reducing missed colonic lesions is uncertain. The aim of this study was to determine the miss rates of proximal colonic lesions by CADe and conventional colonoscopy.
View Article and Find Full Text PDFArticle Synopsis
- A study found that sometimes doctors can miss up to 26% of growths called adenomas during a procedure called colonoscopy, where they check the colon for problems.
- Researchers tested a special AI technology that helps doctors find these missed growths by reviewing videos of colon exams, and it could spot around 79% of the missed adenomas in one test.
- The AI was used in real procedures, finding missed adenomas in about 27% of patients, suggesting that using AI could help doctors be more careful and catch more of these growths.