Kock Farina, Thielke Felix, Abolmaali Nasreddin, Meine Hans, Schenk Andrea
Fraunhofer Institute for Digital Medicine MEVIS, Max-von-Laue-Str. 2, Bremen, 28359, Germany.
Diagnostic and Interventional Radiology and Nuclear Medicine, St. Josef-Hospital, University Hospitals of the Ruhr University of Bochum, Gudrunstr. 56, Bochum, 44791, Germany.
Int J Comput Assist Radiol Surg. 2024 Feb;19(2):233-240. doi: 10.1007/s11548-023-03005-x. Epub 2023 Aug 3.
The segmentation of the hepatic arteries (HA) is essential for state-of-the-art pre-interventional planning of selective internal radiation therapy (SIRT), a treatment option for malignant tumors in the liver. In SIRT a catheter is placed through the aorta into the tumor-feeding hepatic arteries, injecting small beads filled with radiation emitting material for local radioembolization. In this study, we evaluate the suitability of a deep neural network (DNN) based vessel segmentation for SIRT planning.
We applied our DNN-based HA segmentation on 36 contrast-enhanced computed tomography (CT) scans from the arterial contrast agent phase and rated its segmentation quality as well as the overall image quality. Additionally, we applied a traditional machine learning algorithm for HA segmentation as comparison to our deep learning (DL) approach. Moreover, we assessed by expert ratings whether the produced HA segmentations can be used for SIRT planning.
The DL approach outperformed the traditional machine learning algorithm. The DL segmentation can be used for SIRT planning in [Formula: see text] of the cases, while the reference segmentations, which were manually created by experienced radiographers, are sufficient in [Formula: see text]. Seven DL cases cannot be used for SIRT planning while the corresponding reference segmentations are sufficient. However, there are two DL segmentations usable for SIRT, where the reference segmentations for the same cases were rated as insufficient.
HA segmentation is a difficult and time-consuming task. DL-based methods have the potential to support and accelerate the pre-interventional planning of SIRT therapy.
肝动脉（HA）的分割对于选择性内放射治疗（SIRT）这一肝脏恶性肿瘤治疗方案的先进介入前规划至关重要。在SIRT中，通过主动脉将导管置入为肿瘤供血的肝动脉，注入填充有放射性物质的小珠子进行局部放射栓塞。在本研究中，我们评估基于深度神经网络（DNN）的血管分割在SIRT规划中的适用性。
我们将基于DNN的HA分割应用于36例动脉期对比增强计算机断层扫描（CT）图像，并对其分割质量以及整体图像质量进行评分。此外，我们应用传统机器学习算法进行HA分割，以与深度学习（DL）方法进行比较。而且，我们通过专家评分评估生成的HA分割是否可用于SIRT规划。
DL方法优于传统机器学习算法。DL分割在[公式：见原文]的病例中可用于SIRT规划，而由经验丰富的放射技师手动创建的参考分割在[公式：见原文]中是足够的。7例DL分割不能用于SIRT规划，而相应的参考分割是足够的。然而，有2例DL分割可用于SIRT，而相同病例的参考分割被评为不足。
HA分割是一项困难且耗时的任务。基于DL的方法有潜力支持并加速SIRT治疗的介入前规划。
