Another concept for AI in challenging neurological developments

Intracranial aneurysms (IAs) are abnormal bulges in a blood vessel in
the brain that have a potential to rupture and even causing a stroke,
which can lead to lasting brain damage, long-term disability, or even
loss of life. It has been widely acknowledged that hemodynamic
factors, e.g., instantaneous wall shear stress, time-averaged wall shear
stress, wall shear stress gradient, gradient oscillatory number,
oscillatory shear index, pulsatile blood flow waveform (flow rate
magnitude and shape, physical flow period), relative residence
time/turnover time, blood pressure, and vortex (i.e., size, location,
and numbers), have a close relationship with the pathobiology (i.e.,
initiation, growth, and rupture) of IAs [1–9], apart from the
ambiguous family history and genetic factors, and other
non-modifiable factors (e.g., gender, age, at-risk disorders) [10]

Inspired by rapid developments in artificial intelligence-driven and
big data-supported scientific computing, physics-informed DL and
deep hidden physics models [19–22] have a growing potential to be
employed to predict hemodynamic characteristics in IAs and assess
rupture risks using preclinical images (i.e., magnetic resonance
angiography (MRA) and computed tomography angiography (CTA))
and CFD modeling

access article under the CC-BY license. (https://creativecommons.org/licenses/by/4.0/).

---