Segmentation of Arteries in Minimally Invasive Surgery Using Change Detection

Akbari, Hamed; Kosugi, Yukio; Kojima, Kazuyuki

doi:10.1587/transinf.e92.d.498

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternative methods for assisting in blood vessel detection described in the literature included a change in detection using artery pulsations (Akbari et al, 2009 ) and Doppler ultrasonography-based imaging of vessels (Kempski et al, 2019 ). However, artery pulsations and photoacoustic detection margins may not be as precise or as straightforward as the ICG videoangiography margins ( Figure 2 ) and, thus, less adequate for an exactly matched vessel ground-truth generation.…”

Section: Discussionmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

There have been few anatomical structure segmentation studies using deep learning. Numbers of training and ground truth images applied were small and the accuracies of which were low or inconsistent. For a surgical video anatomy analysis, various obstacles, including a variable fast-changing view, large deformations, occlusions, low illumination, and inadequate focus occur. In addition, it is difficult and costly to obtain a large and accurate dataset on operational video anatomical structures, including arteries. In this study, we investigated cerebral artery segmentation using an automatic ground-truth generation method. Indocyanine green (ICG) fluorescence intraoperative cerebral videoangiography was used to create a ground-truth dataset mainly for cerebral arteries and partly for cerebral blood vessels, including veins. Four different neural network models were trained using the dataset and compared. Before augmentation, 35,975 training images and 11,266 validation images were used. After augmentation, 260,499 training and 90,129 validation images were used. A Dice score of 79% for cerebral artery segmentation was achieved using the DeepLabv3+ model trained using an automatically generated dataset. Strict validation in different patient groups was conducted. Arteries were also discerned from the veins using the ICG videoangiography phase. We achieved fair accuracy, which demonstrated the appropriateness of the methodology. This study proved the feasibility of operating field view of the cerebral artery segmentation using deep learning, and the effectiveness of the automatic blood vessel ground truth generation method using ICG fluorescence videoangiography. Using this method, computer vision can discern blood vessels and arteries from veins in a neurosurgical microscope field of view. Thus, this technique is essential for neurosurgical field vessel anatomy-based navigation. In addition, surgical assistance, safety, and autonomous surgery neurorobotics that can detect or manipulate cerebral vessels would require computer vision to identify blood vessels and arteries.

show abstract

Section: Discussionmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

show abstract

An improved variational level set method for MR image segmentation and bias field correction

Zhan

Zhang

Xiao

et al. 2013

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Blood vessel detection and artery-vein differentiation using hyperspectral imaging

Akbari

Kosugi

Kojima

et al. 2009

2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Blood vessel detection is an important but difficult task during surgeries. An unexpected location of a blood vessel or anatomical variations may result in an accidental injury to the blood vessel. This problem would extend the operation time or cause a serious complication. Moreover, differentiating the arteries from veins is necessary in majority of medical procedures. Hyperspectral imaging has entered as a new modality in medicine. This imaging and spectroscopic tool can be used for different applications including medical diagnosis. The unpredictable anatomy of blood vasculature during surgeries especially in anatomical variations makes the visibility very important. In this paper, a hyperspectral imaging technique is proposed as a visual supporting tool to detect blood vessels and to differentiate between the artery and vein during surgeries. This technique can aid the surgeon to find blood vessels and to diagnose normal anatomical variation and abnormalities. The hyperspectral images are captured using two cameras: a visible plus near infrared camera (400-1000nm) and an infrared camera (900-1700nm). Using hyperspectral images, a library of spectral signatures for abdominal organs, arteries, and veins are created. The high-dimensional data are classified using support vector machine (SVM). This method is evaluated for the detection of arteries and veins in abdominal surgeries on a pig.

show abstract

Segmentation of Arteries in Minimally Invasive Surgery Using Change Detection

Cited by 4 publications

References 23 publications

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

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

An improved variational level set method for MR image segmentation and bias field correction

Blood vessel detection and artery-vein differentiation using hyperspectral imaging

Contact Info

Product

Resources

About