Grutman Tal, Bismuth Mike, Glickstein Bar, Ilovitsh Tali
School of Biomedical Engineering, Tel-Aviv University, Tel Aviv-Yafo, Israel.
The Sagol School of Neuroscience, Tel-Aviv University, Tel Aviv-Yafo, Israel.
NPJ Acoust. 2025;1(1):14. doi: 10.1038/s44384-025-00018-5. Epub 2025 Aug 8.
Although volumetric ultrasound is limited by cost and availability of 2D arrays, 3D volumes can be reconstructed from 2D slices if transducer position is known, which is not usually the case. Even with position data, existing algorithms for reconstruction are impractical due to their discrete nature that struggles with scale. We propose a 1D array on a programmable motor for scanning and implicit neural representations for continuous reconstruction. Our network's ability to sample at arbitrary positions was compared to classic algorithms, achieving x7.9 performance while maintaining accuracy. Based on these, a reconstruction pipeline was tested on simulated data with 93% accuracy using only 36 B-mode images. This was evaluated in-vivo to measure tumor volumes in mice, with 6.3% mean error. Our findings suggest implicit neural representations can reduce data needed to recreate volumes from 2D slices and replace interpolation methods to enable interactive analysis.
尽管容积超声受到二维阵列成本和可用性的限制，但如果换能器位置已知，三维容积可以从二维切片重建，而实际情况通常并非如此。即使有位置数据，现有的重建算法由于其离散性质在处理尺度方面存在困难，因而不切实际。我们提出在可编程电机上使用一维阵列进行扫描，并使用隐式神经表示进行连续重建。我们将网络在任意位置采样的能力与经典算法进行了比较，在保持准确性的同时实现了7.9倍的性能提升。基于这些，一个重建流程在仅使用36幅B模式图像的模拟数据上进行了测试，准确率达到93%。在体内对其进行评估以测量小鼠的肿瘤体积，平均误差为6.3%。我们的研究结果表明，隐式神经表示可以减少从二维切片重建容积所需的数据，并取代插值方法以实现交互式分析。
