Page 12 - BH-1-1

Brain & Heart Application of the neural networks surgery

hard to distinguish; as a result, undetected IAs could speed and executive functioning independently; the
cause severe consequences [23,24] . Since 2017, deep neural study also showed direct evidence linking CAA with
networks have been used to detect cerebral aneurysms by impairments in white matter connectivity under PET .
[25]
[36]
combining them with traditional IA detection techniques, In another study, after researching Dutch CAA mutation
such as computed tomography angiography (CTA), carriers and control subjects, Drenth et al. found that both
magnetic resonance angiography (MRA), and DSA [26,27] . pre-symptomatic and symptomatic groups had decreased
Bo et al. have put forward the Global Localization-based connectivity in medial and lateral visual networks, DMN,
IA Network, which is an automatic deep-learning model executive control, and bilateral frontoparietal networks;
for IA segmentation and can be applied to CTA images. the symptomatic group, however, showed diminished
Based on the new recognition, it has been discovered connectivity in all but one network, whereas the pre-
that IAs are related to the vascular network distributed symptomatic group had decreased connectivity solely in
in the brain, indicating that the position information is the frontoparietal left network; based on the data, they
significant. This model has truly enhanced the detection concluded that although CAA affects network connectivity,
precision of IAs, thus making a progress in IA detection . it has no association with aging or other neurodegenerative
[28]
[37]
Meanwhile, Chen et al. have developed a computer- processes . This novel recognition of CAA may have
assisted detection (CAD) system for cerebral aneurysms in significant clinical implications.
contrast-unenhanced time-of-flight MRA images using a Significant carotid stenosis often causes severe clinical
fully convolutional network. When validating the internal or subclinical complications due to decompensated
and external test sets, the presented system achieved hemodynamics, and it may lead to impairment of cognitive
a sensitivity of 94.4% and 82.9%, respectively, proving function . In a previous study, asymptomatic carotid
[38]
that this CAD system can improve the accuracy of IA stenosis patients showed decreased or asymmetrical FC
diagnosis . As is known to neurosurgeons, symptomatic of the frontoparietal network, DMN, dorsal attention
[29]
cerebral vasospasm (SCV) is a common complication network, and sensorimotor network . However, the
[39]
following IA rupture, causing severe cerebral ischemia and impact of unilateral carotid stenosis on the overall
increased mortality . Dumont has validated an artificial functional networks has not been investigated. In order to
[30]
neural network model of SCV; this tool allows clinicians to study the whole-brain influence of carotid stenosis, Chang
identify those patients who have a high risk for SCV and et al. recruited 27 patients with unilateral carotid stenosis
thus should be prophylactically treated. According to the (≥60%) and 20 controls. The study showed that FC was
result, this tool has excellent negative predictive value and indeed disrupted in patients with carotid stenosis but not in
acceptable positive predictive value . a global pattern, affecting only hemodynamically impaired
[31]
Cerebral amyloid angiopathy (CAA) has been regions. The indicators in the study, including global
recognized as one of the accompanying lesions of efficiency, characteristic path length, and modularity, have
Alzheimer’s disease (AD). Its pathogenesis is related to the been found to be highly associated with neuropsychological
cerebrovascular deposition of amyloid-β, which may cause performance, and thus could be potential predictors of
spontaneous intracerebral hemorrhage (ICH) and age- cognitive deficit in patients with carotid stenosis so as to
[40]
related cognitive decline . Recent studies have indicated improve the accuracy of diagnosis .
[32]
that CAA is not only a specific cerebrovascular pathological In the context of MMD, several case reports have
feature, but also a clinical syndrome and a set of clinical concluded that this disease not just disrupts the blood
imaging diagnostic criteria (the Boston criteria) . vessels that supply brain regions, but also affects the brain
[33]
Arvanitakis et al. and Boyle et al. have discovered that CAA networks interaction of specific brain regions; therefore,
appears to cause cognitive deficit and is independent of AD the reorganization of brain networks interaction may have
or other accompanying pathologies, including ICH. In a a role in the recovery of patients with MMD [41,42] .
subsequent community-based cohort study, individuals
harboring CAA not only had an increased risk of dementia, 3. New strategies in cerebrovascular
but also a decline in both global and domain-specific disease treatment
cognition [34,35] . Scientists have proposed that CAA-related
cognitive impairment is associated with CMBs and altered 3.1. Protection of hubs in brain networks
structural connectivity. In order to verify this hypothesis, Ever since it has been discovered that the brain performs
Reijmer et al., in their study, examined brain networks its functions based on a complex network, a plethora of
as a surrogate measure of global small-vessel pathology relative concepts have progressively come into view .
[5]
in CAA; the result showed that lower global network With advanced medical imaging technologies, functional
efficiency leads to a dismal performance of processing MRI (fMRI) or diffusion-weighted imaging has been used

Volume 1 Issue 1 (2023) 4 https://doi.org/10.36922/bh.v1i1.223