论文标题
3D光声成像的记忆有效的可逆神经网络
Memory Efficient Invertible Neural Networks for 3D Photoacoustic Imaging
论文作者
论文摘要
光声成像（PAI）可以成像临床兴趣的高分辨率结构，例如癌肿瘤监测中的血管性。在成像人类受试者时，几何限制将限制视图数据检索导致成像伪像。基于迭代的物理模型方法减少了伪影，但需要过时的PDE解决方案。机器学习（ML）通过结合物理模型和学习的网络加速了PAI。但是，ML方法的深度和整体功率受到内存密集型培训的限制。我们建议使用可逆神经网络（INNS）缓解记忆压力。我们演示了Inns可以在限量视图，嘈杂和亚采样数据的设置中图像3D光声体积。节俭的不断记忆使用Inns使我们能够用16GB RAM培训在消费者GPU上的任意深度。
Photoacoustic imaging (PAI) can image high-resolution structures of clinical interest such as vascularity in cancerous tumor monitoring. When imaging human subjects, geometric restrictions force limited-view data retrieval causing imaging artifacts. Iterative physical model based approaches reduce artifacts but require prohibitively time consuming PDE solves. Machine learning (ML) has accelerated PAI by combining physical models and learned networks. However, the depth and overall power of ML methods is limited by memory intensive training. We propose using invertible neural networks (INNs) to alleviate memory pressure. We demonstrate INNs can image 3D photoacoustic volumes in the setting of limited-view, noisy, and subsampled data. The frugal constant memory usage of INNs enables us to train an arbitrary depth of learned layers on a consumer GPU with 16GB RAM.
