Budd Charlie, Qiu Jianrong, MacCormac Oscar, Huber Martin, Mower Christopher, Janatka Mirek, Trotouin Théo, Shapey Jonathan, Bergholt Mads S, Vercauteren Tom
King's College London, Biomedical Engineering & Imaging Science, London.
King's College London, School of Craniofacial and Regenerative Biology, London.
Med Image Comput Comput Assist Interv. 2023 Oct 1:658-667. doi: 10.1007/978-3-031-43996-4_63.
Hyperspectral imaging (HSI) captures a greater level of spectral detail than traditional optical imaging, making it a potentially valuable intraoperative tool when precise tissue differentiation is essential. Hardware limitations of current optical systems used for handheld realtime video HSI result in a limited focal depth, thereby posing usability issues for integration of the technology into the operating room. This work integrates a focus-tunable liquid lens into a video HSI exoscope, and proposes novel video autofocusing methods based on deep reinforcement learning. A first-of-its-kind robotic focal-time scan was performed to create a realistic and reproducible testing dataset. We benchmarked our proposed autofocus algorithm against traditional policies, and found our novel approach to perform significantly ( < 0.05) better than traditional techniques (0.070 ±.098 mean absolute focal error compared to 0.146 ±.148). In addition, we performed a blinded usability trial by having two neurosurgeons compare the system with different autofocus policies, and found our novel approach to be the most favourable, making our system a desirable addition for intraoperative HSI.
高光谱成像（HSI）比传统光学成像能够捕捉到更精细的光谱细节，这使得它在精确组织区分至关重要时成为一种潜在的有价值的术中工具。用于手持式实时视频HSI的当前光学系统的硬件限制导致焦深有限，从而给将该技术集成到手术室带来了可用性问题。这项工作将可聚焦调谐的液体透镜集成到视频HSI外视镜中，并提出了基于深度强化学习的新型视频自动聚焦方法。进行了首次机器人聚焦时间扫描，以创建一个真实且可重复的测试数据集。我们将提出的自动聚焦算法与传统策略进行了基准测试，发现我们的新方法比传统技术表现显著更好（<0.05）（平均绝对聚焦误差为0.070±0.098，而传统技术为0.146±0.148）。此外，我们通过让两名神经外科医生比较具有不同自动聚焦策略的系统进行了盲法可用性试验，发现我们的新方法是最有利的，使我们的系统成为术中HSI的理想补充。
