Tristan Rauhut

First, artifacts arising from AHRs can substantially affect cancer detection. Nakai et al. [1] report a detection rate of only 76% in patients with moderate to severe artifacts compared to matched controls. Identifying these artifacts enables adjustments to sequence parameters. While single-shot EPI DWI sequences exhibit more prominent, readout-segmented EPI (RESOLVE) and TGSE-BLADE EPI sequences show reduced artifact severity [2]. Building on these observations, this work develops two AI models designed to detect AHRs in axial T2W sequences.

Second, manual creation of a three-dimensional FOV for the prostate on localizer sequences, required for subsequent diagnostic scans, is both time-consuming and prone to human error. To address this, this work proposes an automatic approach for estimating the prostate’s position based on localizer sequences, ensuring accurate centering of the gland in the FOV. An additional challenge in this context is achieving complete slice coverage while minimizing redundant slices, thereby optimizing scan time.

Lastly, the third topic addresses the automatic determination of slice angulation for oblique axial scans, based on sagittal localizer and sagittal T2-w sequences. This approach follows the alignment strategy described by Franiel et al. [3], which aligns the prostate perpendicular to the anterior rectal wall, offering a more anatomically natural orientation. This results in a reproducible alignment planning strategy that is independent of radiological technologists’ expertise.

References

[1] Nakai, M., et al. “Decreased prostate MRI cancer detection rate due to moderate to severe susceptibility artifacts from hip prosthesis”. In: European Radiology, 34(5):3387–3399, 2023.

[2] Okuchi, T., et al. “Comparison of TGSE-BLADE DWI, RESOLVE DWI, and SS-EPI DWI in healthy volunteers and patients after cerebral aneurysm clipping”. In: Scientific Reports, 12(1), 2022.

[3] Franiel, T., et al. ” mpMRI of the Prostate (MR-Prostatography): Updated Recommendations of the DRG and BDR on Patient Preparation and Scanning Protocol”. In: RöFo – Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren:a–1406–8477, 2021.