EnLVAM: Enhanced Left Ventricle Linear Measurements Utilizing Anatomical Motion Mode
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913914968604672 |
|---|---|
| author | Singh, Durgesh K. Boubekki, Ahcene Cao, Qing Aase, Svein Arne Jenssen, Robert Kampffmeyer, Michael |
| author_facet | Singh, Durgesh K. Boubekki, Ahcene Cao, Qing Aase, Svein Arne Jenssen, Robert Kampffmeyer, Michael |
| contents | Linear measurements of the left ventricle (LV) in the Parasternal Long Axis (PLAX) view using B-mode echocardiography are crucial for cardiac assessment. These involve placing 4-6 landmarks along a virtual scanline (SL) perpendicular to the LV axis near the mitral valve tips. Manual placement is time-consuming and error-prone, while existing deep learning methods often misalign landmarks, causing inaccurate measurements. We propose a novel framework that enhances LV measurement accuracy by enforcing straight-line constraints. A landmark detector is trained on Anatomical M-Mode (AMM) images, computed in real time from B-mode videos, then transformed back to B-mode space. This approach addresses misalignment and reduces measurement errors. Experiments show improved accuracy over standard B-mode methods, and the framework generalizes well across network architectures. Our semi-automatic design includes a human-in-the-loop step where the user only places the SL, simplifying interaction while preserving alignment flexibility and clinical relevance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22063 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EnLVAM: Enhanced Left Ventricle Linear Measurements Utilizing Anatomical Motion Mode Singh, Durgesh K. Boubekki, Ahcene Cao, Qing Aase, Svein Arne Jenssen, Robert Kampffmeyer, Michael Computer Vision and Pattern Recognition Linear measurements of the left ventricle (LV) in the Parasternal Long Axis (PLAX) view using B-mode echocardiography are crucial for cardiac assessment. These involve placing 4-6 landmarks along a virtual scanline (SL) perpendicular to the LV axis near the mitral valve tips. Manual placement is time-consuming and error-prone, while existing deep learning methods often misalign landmarks, causing inaccurate measurements. We propose a novel framework that enhances LV measurement accuracy by enforcing straight-line constraints. A landmark detector is trained on Anatomical M-Mode (AMM) images, computed in real time from B-mode videos, then transformed back to B-mode space. This approach addresses misalignment and reduces measurement errors. Experiments show improved accuracy over standard B-mode methods, and the framework generalizes well across network architectures. Our semi-automatic design includes a human-in-the-loop step where the user only places the SL, simplifying interaction while preserving alignment flexibility and clinical relevance. |
| title | EnLVAM: Enhanced Left Ventricle Linear Measurements Utilizing Anatomical Motion Mode |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.22063 |