DL respiratory-triggered 3D MRCP cuts scanning time by 68% vs conventional triggered sequence

Deep learning (DL)-based respiratory-triggered 3D MRCP required 68% fewer effective respiratory cycles than conventional triggered MRCP (19 vs 60 cycles) while yielding similar qualitative image quality and superior peripheral duct visibility over breath-hold compressed sensing…

• Retrospective study in 116 patients comparing DL-triggered, conventional triggered, and breath-hold compressed sensing 3D MRCP sequences.
• Relative contrast of the common bile duct was higher with DL (0.87±0.07) than conventional (0.83±0.08; p<0.01); both triggered methods provided better visibility of peripheral intrahepatic and pancreatic ducts than breath-hold CS (all p<0.01).

Retrospective single-center study; vendor-specific DL-triggered sequence has not been externally validated.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.