Deep Learning k-Space-to-Image Reconstruction Facilitates High Spatial Resolution and Scan Time Reduction in Diffusion-Weighted Imaging Breast MRI.

BACKGROUND For time-consuming diffusion-weighted imaging (DWI) of the breast, deep learning-based imaging acceleration appears particularly promising. PURPOSE To investigate a combined k-space-to-image reconstruction approach for scan time reduction and improved spatial resolution in breast DWI. STUDY TYPE Retrospective. POPULATION 133 women (age 49.7 ± 12.1 years) underwent multiparametric breast MRI. FIELD STRENGTH/SEQUENCE 3.0T/T2 turbo spin echo, T1 3D gradient echo, DWI (800 and 1600 sec/mm2 ). ASSESSMENT DWI data were retrospectively processed using deep learning-based k-space-to-image reconstruction (DL-DWI) and an additional super-resolution algorithm (SRDL-DWI). In addition to signal-to-noise ratio and apparent diffusion coefficient (ADC) comparisons among standard, DL- and SRDL-DWI, a range of quantitative similarity (e.g., structural similarity index [SSIM]) and error metrics (e.g., normalized root mean square error [NRMSE], symmetric mean absolute percent error [SMAPE], log accuracy error [LOGAC]) was calculated to analyze structural variations. Subjective image evaluation was performed independently by three radiologists on a seven-point rating scale. STATISTICAL TESTS Friedman's rank-based analysis of variance with Bonferroni-corrected pairwise post-hoc tests. P < 0.05 was considered significant. RESULTS Both DL- and SRDL-DWI allowed for a 39% reduction in simulated scan time over standard DWI (5 vs. 3 minutes). The highest image quality ratings were assigned to SRDL-DWI with good interreader agreement (ICC 0.834; 95% confidence interval 0.818-0.848). Irrespective of b-value, both standard and DL-DWI produced superior SNR compared to SRDL-DWI. ADC values were slightly higher in SRDL-DWI (+0.5%) and DL-DWI (+3.4%) than in standard DWI. Structural similarity was excellent between DL-/SRDL-DWI and standard DWI for either b value (SSIM ≥ 0.86). Calculation of error metrics (NRMSE ≤ 0.05, SMAPE ≤ 0.02, and LOGAC ≤ 0.04) supported the assumption of low voxel-wise error. DATA CONCLUSION Deep learning-based k-space-to-image reconstruction reduces simulated scan time of breast DWI by 39% without influencing structural similarity. Additionally, super-resolution interpolation allows for substantial improvement of subjective image quality. EVIDENCE LEVEL 4 TECHNICAL EFFICACY: Stage 1.

[1]  M. Reisert,et al.  Accelerated Diffusion-Weighted Imaging in 3 T Breast MRI Using a Deep Learning Reconstruction Algorithm With Superresolution Processing , 2023, Investigative radiology.

[2]  E. Weiland,et al.  Novel deep-learning-based diffusion weighted imaging sequence in 1.5 T breast MRI. , 2023, European journal of radiology.

[3]  E. Weiland,et al.  Acquisition time reduction of diffusion-weighted liver imaging using deep learning image reconstruction. , 2022, Diagnostic and interventional imaging.

[4]  Amie Y Lee,et al.  Deep Learning to Simulate Contrast-enhanced Breast MRI of Invasive Breast Cancer. , 2022, Radiology.

[5]  Y. Chang,et al.  Feasibility of deep learning k-space-to-image reconstruction for diffusion weighted imaging in patients with breast cancers: Focus on image quality and reduced scan time. , 2022, European journal of radiology.

[6]  Daniel Wessling,et al.  Deep learning-based super-resolution gradient echo imaging of the pancreas: Improvement of image quality and reduction of acquisition time. , 2022, Diagnostic and interventional imaging.

[7]  T. Benkert,et al.  Clinical feasibility of accelerated diffusion weighted imaging of the abdomen with deep learning reconstruction: Comparison with conventional diffusion weighted imaging. , 2022, European journal of radiology.

[8]  S. Choe,et al.  Prospects of Structural Similarity Index for Medical Image Analysis , 2022, Applied Sciences.

[9]  D. Nickel,et al.  Feasibility of an accelerated 2D-multi-contrast knee MRI protocol using deep-learning image reconstruction: a prospective intraindividual comparison with a standard MRI protocol , 2022, European Radiology.

[10]  T. Helbich,et al.  Breast cancer screening in women with extremely dense breasts recommendations of the European Society of Breast Imaging (EUSOBI) , 2022, European Radiology.

[11]  Y. Ohno,et al.  Deep Learning Reconstruction of Diffusion-weighted MRI Improves Image Quality for Prostatic Imaging. , 2022, Radiology.

[12]  M. Helvie,et al.  Breast cancer screening in average and high-risk women. , 2021, Best practice & research. Clinical obstetrics & gynaecology.

[13]  E. Wenkel,et al.  Ultra-High b-Value Diffusion-Weighted Imaging-Based Abbreviated Protocols for Breast Cancer Detection , 2021, Investigative radiology.

[14]  Jin Joo Kim,et al.  Fusion of high b-value diffusion-weighted and unenhanced T1-weighted images to diagnose invasive breast cancer: factors associated with false-negative results , 2021, European Radiology.

[15]  D. Nickel,et al.  Diagnostic Confidence and Feasibility of a Deep Learning Accelerated HASTE Sequence of the Abdomen in a Single Breath-Hold. , 2020, Investigative radiology.

[16]  W. Moon,et al.  Simultaneous Multislice Readout‐Segmented Echo Planar Imaging for Diffusion‐Weighted MRI in Patients With Invasive Breast Cancers , 2020, Journal of magnetic resonance imaging : JMRI.

[17]  M. Uder,et al.  A Multicentric Comparison of Apparent Diffusion Coefficient Mapping and the Kaiser Score in the Assessment of Breast Lesions. , 2020, Investigative radiology.

[18]  D. Le Bihan,et al.  Diffusion-weighted imaging of the breast—a consensus and mission statement from the EUSOBI International Breast Diffusion-Weighted Imaging working group , 2019, European Radiology.

[19]  P. V. van Diest,et al.  Supplemental MRI Screening for Women with Extremely Dense Breast Tissue. , 2019, The New England journal of medicine.

[20]  R. Mann,et al.  Breast MRI: State of the Art. , 2019, Radiology.

[21]  T. Helbich,et al.  Diffusion‐Weighted MRI of Breast Cancer: Improved Lesion Visibility and Image Quality Using Synthetic b‐Values , 2019, Journal of magnetic resonance imaging : JMRI.

[22]  F. Gilbert,et al.  A Meta-analysis of the Diagnostic Performance of Diffusion MRI for Breast Lesion Characterization. , 2019, Radiology.

[23]  Shandong Wu,et al.  Automated deep learning method for whole‐breast segmentation in diffusion‐weighted breast MRI , 2019, Medical Imaging.

[24]  Michael Golatta,et al.  High-risk breast cancer surveillance with MRI: 10-year experience from the German consortium for hereditary breast and ovarian cancer , 2019, Breast Cancer Research and Treatment.

[25]  T. Helbich,et al.  Diffusion-Weighted Imaging With Apparent Diffusion Coefficient Mapping for Breast Cancer Detection as a Stand-Alone Parameter: Comparison With Dynamic Contrast-Enhanced and Multiparametric Magnetic Resonance Imaging , 2018, Investigative radiology.

[26]  M. Dietzel,et al.  How to use the Kaiser score as a clinical decision rule for diagnosis in multiparametric breast MRI: a pictorial essay , 2018, Insights into Imaging.

[27]  T. Helbich,et al.  Multiparametric MRI of the breast: A review , 2018, Journal of magnetic resonance imaging : JMRI.

[28]  S. Morley,et al.  Measures of Model Performance Based On the Log Accuracy Ratio , 2018 .

[29]  T. Helbich,et al.  Potential of Noncontrast Magnetic Resonance Imaging With Diffusion-Weighted Imaging in Characterization of Breast Lesions: Intraindividual Comparison With Dynamic Contrast-Enhanced Magnetic Resonance Imaging , 2017, Investigative radiology.

[30]  Michael Götz,et al.  Prediction of malignancy by a radiomic signature from contrast agent‐free diffusion MRI in suspicious breast lesions found on screening mammography. , 2017, Journal of magnetic resonance imaging : JMRI.

[31]  Li Guo,et al.  Quantitative susceptibility mapping: Report from the 2016 reconstruction challenge , 2017, Magnetic resonance in medicine.

[32]  Thomas Pock,et al.  Learning a variational network for reconstruction of accelerated MRI data , 2017, Magnetic resonance in medicine.

[33]  Daniel Rueckert,et al.  Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  F. Laun,et al.  Fast and Noninvasive Characterization of Suspicious Lesions Detected at Breast Cancer X-Ray Screening: Capability of Diffusion-weighted MR Imaging with MIPs. , 2016, Radiology.

[35]  T. Helbich,et al.  Triple-modality screening trial for familial breast cancer underlines the importance of magnetic resonance imaging and questions the role of mammography and ultrasound regardless of patient mutation status, age, and breast density. , 2015, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[36]  Updated Recommendations for MRI of the Breast , 2014, Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren.

[37]  C. Kuhl,et al.  Prospective multicenter cohort study to refine management recommendations for women at elevated familial risk of breast cancer: the EVA trial. , 2010, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[38]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[39]  Wei Liu,et al.  Simultaneous multi-slice readout-segmented echo planar imaging for accelerated diffusion-weighted imaging of the breast. , 2016, European journal of radiology.

[40]  C. Boetes,et al.  Breast MRI: guidelines from the European Society of Breast Imaging , 2008, European Radiology.