Benefits of Anatomical Motion Mode Imaging in LV Automatic Measurement.

Presenter: Durgesh Kumar Singh, Visual Intelligence PhD student at UiT The Arctic University of Norway

Abstract: Linear measurements of the left ventricle (LV) are crucial for evaluating heart function and are typically performed using echocardiography to assess dimensions and detect abnormalities. Accurate measurements are essential for diagnosing and monitoring cardiac conditions, particularly those affecting the heart's structure. However, automatic B-mode LV measurement models can sometimes produce misaligned landmarks due to the limitations of heatmap regression or classification techniques. These methods, influenced by label smoothing and low input resolution, can lead to less precise landmark placement, potentially affecting clinical relevance. In this talk, I will present an AMM-based method that improves the accuracy of LV linear measurements by incorporating temporal information into the imaging process. This approach effectively addresses the alignment issues common in fully automatic B-mode methods. It offers the added benefit of allowing users to perform measurements at different ventricular levels without requiring additional training supervision.

‍

‍

In compliance with GDPR consent requirements, presentations given in a Visual Intelligence context may be recorded with the consent of the speaker. All recordings are edited to remove all faces, names and voices of other participants. Questions and comments by the audience will hence be removed and will not appear in the recording.  With the freely given consent from the speaker, recorded presentation may be posted on the Visual Intelligence YouTube channel.

‍