AI 中文总结
该研究提出结合多爆发扫描的神经网络框架，将AS-DOCT单位置采集帧从数百减至16帧，29个癌症球状体验证SSIM>0.8，26.2秒完成全体积采集，实现高速高通量3D动态组织筛查。
AI 中文摘要
动态光学相干断层成像（DOCT）可实现组织动力学的无标记三维（3D）评估，但传统时谱DOCT因每个位置需数百次重复OCT帧采集而存在扫描时间长的问题。本文提出一种结合非均匀时间扫描协议（多爆发扫描）的神经网络（NN）框架，用于加速振幅谱DOCT（AS-DOCT）。该模型采用3D卷积层、长短期记忆（LSTM）层，以时间OCT序列及其伪振幅谱为双输入，仅用每个位置16帧即可生成AS-DOCT图像。在29个癌症球状体上验证，该方法高保真分辨出不同功能域结构，结构相似性指数度量（SSIM）大于0.8，且能在26.2秒内完成全体积AS-DOCT采集，可实现高通量3D动态组织筛查。
英文摘要
Dynamic optical coherence tomography (DOCT) enables label-free, three-dimensional (3D) assessment of tissue dynamics. However, it suffers from long acquisition times because conventional time-spectrum DOCT requires hundreds of repeated OCT frames per location. Here we present a neural network (NN) framework integrated with a non-uniform-time scanning protocol (multi-burst scan) to accelerate amplitude-spectrum DOCT (AS-DOCT). Combining 3D convolutional and long-short term memory (LSTM) layers with dual inputs (the temporal OCT sequence and its pseudo-amplitude spectrum), the model generates AS-DOCT images from only 16 frames per location. Validated on 29 cancer spheroids, the proposed method resolved distinct functional domain structures with high fidelity (structural similarity index metric (SSIM) > 0.8) and enabled full volumetric AS-DOCT acquisition in 26.2 seconds. This method will enable high-throughput 3D dynamic tissue screening.
