Clinical Impact of Deep Learning Reconstruction in MRI Knee and Patient Throughput

Motivation: To quantify the impact of Deep Resolve Sharp and Gain (DRSG) Artificial Intelligence (AI) software (Siemens Healthineers) on knee MRI exams at 3.0 Tesla. Goal(s): To study the clinical effects of DRSG on image quality and examination time. Approach: One hundred patients underwent examinations pre and post deep learning reconstruction software (DLR) implementation. Two attending musculoskeletal radiologists blindly reviewed exams and the quality of structures was assessed in routine diagnostic planes. Exam times were recorded. Results: Knee structures showed no meaningful difference in image quality. Meanwhile, a statistically significant reduction in mean exam time was observed with DLR-enabled protocols of 24% (p<0.001). Impact: Deep Resolve Sharp & Gain deep learning reconstruction software is a clinically useful tool to significantly reduce MR knee exams times without compromising image quality at 3.0 Tesla.