Novel deep-learning-based diffusion weighted imaging sequence in 1.5 T breast MRI

• Verfasst von: Wessling, Daniel [VerfasserIn]
• Verfasst von: Gassenmaier, Sebastian [VerfasserIn]
• Verfasst von: Olthof, Susann-Cathrin [VerfasserIn]
• Verfasst von: Benkert, Thomas [VerfasserIn]
• Verfasst von: Weiland, Elisabeth [VerfasserIn]
• Verfasst von: Afat, Saif [VerfasserIn]
• Verfasst von: Preibsch, Heike [VerfasserIn]
• Titel: Novel deep-learning-based diffusion weighted imaging sequence in 1.5 T breast MRI
• Verf.angabe: Daniel Wessling, Sebastian Gassenmaier, Susann-Cathrin Olthof, Thomas Benkert, Elisabeth Weiland, Saif Afat, Heike Preibsch
• E-Jahr: 2023
• Jahr: September 2023
• Umfang: 9 S.
• Illustrationen: Illustrationen
• Fussnoten: Online verfügbar: 25. Juni 2023 ; Gesehen am 25.10.1023
• Titel Quelle: Enthalten in: European journal of radiology
• Ort Quelle: Amsterdam [u.a.] : Elsevier Science, 1990
• Jahr Quelle: 2023
• Band/Heft Quelle: 166(2023) vom: Sept., Artikel-ID 110948, Seite 1-9
• ISSN Quelle: 1872-7727
• DOI: doi:10.1016/j.ejrad.2023.110948
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: artificial intelligence
• Sach-SW: breast cancer
• Sach-SW: deep learning
• Sach-SW: diffusion magnetic resonance imaging
• Sach-SW: female
• Sach-SW: humans
• Sach-SW: magnetic resonance imaging
• Sach-SW: MRI
• Sach-SW: reproducibility of results
• Sach-SW: retrospective studies
• Sach-SW: sexually transmitted diseases
• K10plus-PPN: 1867603675

Abstract

PURPOSE: This study aimed to assess the technical feasibility, the impact on image quality, and the acquisition time (TA) of a new deep-learning-based reconstruction algorithm in diffusion weighted imaging (DWI) of breast magnetic resonance imaging (MRI). METHODS: Retrospective analysis of 55 female patients who underwent breast DWI at 1.5 T. Raw data were reconstructed using a deep-learning (DL) reconstruction algorithm on a subset of the acquired averages, therefore a reduction of TA. Clinically used standard DWI sequence (DWIStd) and the DL-reconstructed images (DWIDL) were compared. Two radiologists rated the image quality of b800 and ADC images, using a Likert-scale from 1 to 5 with 5 being considered perfect image quality. Signal intensities were measured by placing a region of interest (ROI) at the same position in both sequences. RESULTS: TA was reduced by 40 % in DWIDL, compared to DWIStd, DWIDL improved noise and sharpness while maintaining contrast, the level of artifacts, and diagnostic confidence. There were no differences regarding the signal intensity values of the apparent diffusion coefficient (ADC), (p = 0.955), b50-values (p = 0.070) and b800-values (p = 0.415) comparing standard and DL-imaging. Lesion assessment showed no differences regarding the number of lesions in ADC and DWI (both p = 1.000) and regarding the lesion diameter in DWI (p = 0.961;0.972) and ADC (p = 0.961;0.972). CONCLUSIONS: The novel deep-learning-based reconstruction algorithm significantly reduces TA in breast DWI, while improving sharpness, reducing noise, and maintaining a comparable level of image quality, artifacts, contrast, and diagnostic confidence. DWIDL does not influence the quantifiable parameters.