Publications by authors named "Gino E Jansen"

Article Synopsis
  • The study aims to automate the selection process for echocardiographic exams by classifying routine views, recognizing unknown views, and assessing image quality.
  • A neural network is trained for view classification, and a linear regression model predicts view quality using feature embeddings.
  • Results show that the method performs nearly at expert level, significantly improving efficiency in selecting appropriate echocardiography views for analysis.
View Article and Find Full Text PDF

Label noise hampers supervised training of neural networks. However, data without label noise is often infeasible to attain, especially for medical tasks. Attaining high-quality medical labels would require a pool of experts and their consensus reading, which would be extremely costly.

View Article and Find Full Text PDF