Automated Quantitative Analysis of Blood Flow in Extracranial–Intracranial Arterial Bypass Based on Indocyanine Green Angiography

Abstract

Microvascular imaging based on indocyanine green is an important tool for surgeons who carry out extracranial–intracranial arterial bypass surgery. In terms of blood perfusion, indocyanine green images contain abundant information, which cannot be effectively interpreted by humans or currently available commercial software. In this paper, an automatic processing framework for perfusion assessments based on indocyanine green videos is proposed and consists of three stages, namely, vessel segmentation based on the UNet deep neural network, preoperative and postoperative image registrations based on scale-invariant transform features, and blood flow evaluation based on the Horn–Schunck optical flow method. This automatic processing flow can reveal the blood flow direction and intensity curve of any vessel, as well as the blood perfusion changes before and after an operation. Commercial software embedded in a microscope is used as a reference to evaluate the effectiveness of the algorithm in this study. A total of 120 patients from multiple centers were sampled for the study. For blood vessel segmentation, a Dice coefficient of 0.80 and a Jaccard coefficient of 0.73 were obtained. For image registration, the success rate was 81%. In preoperative and postoperative video processing, the coincidence rates between the automatic processing method and commercial software were 89 and 87%, respectively. The proposed framework not only achieves blood perfusion analysis similar to that of commercial software but also automatically detects and matches blood vessels before and after an operation, thus quantifying the flow direction and enabling surgeons to intuitively evaluate the perfusion changes caused by bypass surgery.

Deep-Learning-Based Cerebral Artery Semantic Segmentation in Neurosurgical Operating Microscope Vision Using Indocyanine Green Fluorescence Videoangiography

“…In recent studies, for surgical instrument segmentation, the mean Dice score was ∼0.769-0.9 (Kalavakonda, 2019;Kamrul Hasan and Linte, 2019). However, studies on anatomical structure segmentation using neurosurgical microscope operational video are rare (Jiang et al, 2021). This is probably because anatomical features are more difficult to accurately segmentize through machine learning.…”

“…However, studies on anatomical structure segmentation using neurosurgical microscope operational video are rare (Jiang et al, 2021 ). This is probably because anatomical features are more difficult to accurately segmentize through machine learning.…”

“…A recent study on anatomy segmentation using a neurosurgical operating microscope focused on manual ground truth marking methods, and results of the analysis have yet to be reported (Pangal et al, 2021 ). In a recent study, U-net-based vessel segmentation was reported not for visible light color neurosurgical video but for grayscale infrared ICG videoangiography vessels (Jiang et al, 2021 ). In addition, the main focus was blood flow analysis, and only 150 cortical vessel images were used for training (Jiang et al, 2021 ).…”

“…In a recent study, U-net-based vessel segmentation was reported not for visible light color neurosurgical video but for grayscale infrared ICG videoangiography vessels (Jiang et al, 2021 ). In addition, the main focus was blood flow analysis, and only 150 cortical vessel images were used for training (Jiang et al, 2021 ).…”

“…In addition, recent research into advanced neural network architectures used in image semantic segmentation may improve the semantic segmentation of anatomical structures (Wang et al, 2020 ). In previous studies, earlier architectures, such as U-Net (Kamrul Hasan and Linte, 2019 ; Sadda et al, 2019 ; Jiang et al, 2021 ), were adopted. However, recent architectures, such as DeepLabv3+ (Chen et al, 2018 ) or convolutional neural networks with modified or deeper network architectures, may achieve a better performance (Wang et al, 2020 ).…”