Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy; Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy.
The BioRobotics Institute, Scuola Superiore Sant'Anna, Pisa, Italy; Department of Excellence in Robotics and AI, Scuola Superiore Sant'Anna, Pisa, Italy.
Med Image Anal. 2021 May;70:102008. doi: 10.1016/j.media.2021.102008. Epub 2021 Feb 19.
During Twin-to-Twin Transfusion Syndrome (TTTS), abnormal vascular anastomoses in the monochorionic placenta can produce uneven blood flow between the fetuses. In the current practice, this syndrome is surgically treated by closing the abnormal connections using laser ablation. Surgeons commonly use the inter-fetal membrane as a reference. Limited field of view, low fetoscopic image quality and high inter-subject variability make the membrane identification a challenging task. However, currently available tools are not optimal for automatic membrane segmentation in fetoscopic videos, due to membrane texture homogeneity and high illumination variability.
To tackle these challenges, we present a new deep-learning framework for inter-fetal membrane segmentation on in-vivo fetoscopic videos. The framework enhances existing architectures by (i) encoding a novel (instance-normalized) dense block, invariant to illumination changes, that extracts spatio-temporal features to enforce pixel connectivity in time, and (ii) relying on an adversarial training, which constrains macro appearance.
We performed a comprehensive validation using 20 different videos (2000 frames) from 20 different surgeries, achieving a mean Dice Similarity Coefficient of 0.8780±0.1383.
The proposed framework has great potential to positively impact the actual surgical practice for TTTS treatment, allowing the implementation of surgical guidance systems that can enhance context awareness and potentially lower the duration of the surgeries.
在双胎输血综合征（TTTS）中，单绒毛膜胎盘中的异常血管吻合会导致胎儿之间血流不均。目前，该综合征采用激光消融术关闭异常连接进行手术治疗。外科医生通常将胎儿膜作为参考。由于膜纹理的同质性和高光照变异性，有限的视野、低羊膜镜图像质量和高受试者间变异性使得膜识别成为一项具有挑战性的任务。然而，目前可用的工具并不适合自动分割羊膜镜视频中的膜，因为膜纹理的同质性和高光照变异性。
为了解决这些挑战，我们提出了一种新的深度学习框架，用于对体内羊膜镜视频进行胎儿膜分割。该框架通过（i）编码新的（实例归一化）密集块，对光照变化具有不变性，提取时空特征以强制在时间上的像素连通性，以及（ii）依赖对抗训练，对宏外观进行约束，从而增强现有的架构。
我们使用 20 次不同手术的 20 个不同视频（2000 帧）进行了全面验证，平均骰子相似系数为 0.8780±0.1383。
该框架具有很大的潜力，可以积极影响 TTTS 治疗的实际手术实践，允许实施手术指导系统，增强上下文意识，并有可能缩短手术时间。
