Compact Implicit Neural Representations for Plane Wave Images
This work addresses storage and quality issues in medical ultrasound imaging for healthcare applications, representing an incremental advance by applying INRs to a new domain.
The paper tackles artifacts and shadows in ultrafast plane-wave ultrasound imaging by proposing a novel approach using implicit neural representations (INRs) to compactly encode multi-planar sequences while preserving orientation-dependent information, achieving a compression ratio of approximately 15:1 with model weights of 530 KB compared to 8 MB for raw images.
Ultrafast Plane-Wave (PW) imaging often produces artifacts and shadows that vary with insonification angles. We propose a novel approach using Implicit Neural Representations (INRs) to compactly encode multi-planar sequences while preserving crucial orientation-dependent information. To our knowledge, this is the first application of INRs for PW angular interpolation. Our method employs a Multi-Layer Perceptron (MLP)-based model with a concise physics-enhanced rendering technique. Quantitative evaluations using SSIM, PSNR, and standard ultrasound metrics, along with qualitative visual assessments, confirm the effectiveness of our approach. Additionally, our method demonstrates significant storage efficiency, with model weights requiring 530 KB compared to 8 MB for directly storing the 75 PW images, achieving a notable compression ratio of approximately 15:1.