Artificial Intelligence Algorithm-Based CTA Imaging for Diagnosing Ischemic Type Biliary Lesions after Orthotopic...

Area of Science:

• Radiology
• Medical Imaging
• Artificial Intelligence

Background:

• Ischemic type biliary lesions (ITBL) are a complication after orthotopic liver transplantation (OLT).
• Accurate and early diagnosis of ITBL is crucial for patient outcomes.
• Computed tomography angiography (CTA) is a key imaging modality in OLT follow-up.

Purpose of the Study:

• To evaluate the clinical utility of artificial intelligence (AI)-based CTA for diagnosing ITBL post-OLT.
• To assess the impact of AI algorithms on CTA image quality and diagnostic performance.

Main Methods:

• A convolutional neural network (CNN) algorithm was employed to denoise and enhance CTA images from 66 OLT patients.
• Image quality was objectively and subjectively assessed.
• AI-enhanced CTA diagnostic performance was compared against digital subtraction angiography (DSA).

Main Results:

• AI processing notably improved CTA image quality, highlighting lesions and thrombosis.
• AI-enhanced CTA demonstrated high sensitivity (72.22%) and specificity (87.44%) for ITBL detection.
• Early abnormal CTA findings were strongly associated with ITBL development.

Conclusions:

• AI-based CTA offers significant clinical value in the early diagnosis of ITBL after OLT.
• AI algorithms enhance diagnostic accuracy by improving image clarity and lesion visualization.
• This technology can aid in timely intervention and management of post-transplant biliary complications.