Deep learning reconstruction-applied PROPELLER diffusion-weighted imaging in uterine malignancies: a comparison study...

Area of Science:

• Radiology
• Medical Imaging
• Oncology

Background:

• Diffusion-weighted imaging (DWI) is crucial for diagnosing and monitoring uterine malignancies.
• Traditional DWI techniques like MUltiplexed Sensitivity Encoding (MUSE) can be limited by artifacts and conspicuity.
• Deep learning reconstruction (DLR) techniques offer potential improvements in MRI image quality.

Purpose of the Study:

• To compare the image quality of DWI between DLR-applied Periodically Rotated Overlapping ParallEL Lines with Enhanced Reconstruction (PROPELLER) and MUSE sequences.
• To evaluate qualitative and quantitative differences in MRI of uterine malignancies using these two DWI techniques.

Main Methods:

• Retrospective analysis of 66 MRI examinations from 48 patients with uterine malignancies (cervical cancer, endometrial cancer, endometrial stromal sarcoma).
• DWI performed using both DLR-applied PROPELLER and MUSE sequences at b-values of 0 and 800 s/mm².
• Qualitative assessment by two reviewers (image quality, artifacts, sharpness, lesion conspicuity) and quantitative measurements (ADC, aSNR, aCNR).

Main Results:

• DLR-applied PROPELLER-DWI demonstrated significantly fewer artifacts and better lesion conspicuity compared to MUSE-DWI.
• No significant difference in overall image quality or sharpness between the two sequences.
• Quantitative analysis revealed significantly higher apparent signal-to-noise ratio (aSNR) and apparent contrast-to-noise ratio (aCNR) with DLR-applied PROPELLER-DWI.
• Mean apparent diffusion coefficient (ADC) values were significantly higher with DLR-applied PROPELLER-DWI.

Conclusions:

• DLR-applied PROPELLER-DWI provides superior image quality in uterine malignancies due to reduced artifacts and enhanced lesion conspicuity.
• Higher aSNR and aCNR values further support the improved performance of DLR-applied PROPELLER-DWI.
• The significant difference in ADC values warrants consideration in clinical interpretation.