Publications by authors named "Gino Jansen"
Automated echocardiography view classification and quality assessment with recognition of unknown views.
J Med Imaging (Bellingham)
September 2024
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.
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 PDFUltrasound (US) imaging is a medical imaging modality that uses the reflection of sound in the range of 2-18 MHz to image internal body structures. In US, the frequency bandwidth (BW) is directly associated with image resolution. BW is a property of the transducer and more bandwidth comes at a higher cost.
View Article and Find Full Text PDF