Dataset Information

High-Spatial-Resolution Multishot Multiplexed Sensitivity-encoding Diffusion-weighted Imaging for Improved Quality of Breast Images and Differentiation of Breast Lesions: A Feasibility Study.

ABSTRACT: Multishot multiplexed sensitivity-encoding diffusion-weighted imaging is a feasible and easily implementable routine breast MRI protocol that yields high-quality diffusion-weighted breast images.Purpose: To compare multiplexed sensitivity-encoding (MUSE) diffusion-weighted imaging (DWI) and single-shot DWI for lesion visibility and differentiation of malignant and benign lesions within the breast.Materials and Methods: In this prospective institutional review board-approved study, both MUSE DWI and single-shot DWI sequences were first optimized in breast phantoms and then performed in a group of patients. Thirty women (mean age, 51.1 years ± 10.1 [standard deviation]; age range, 27-70 years) with 37 lesions were included in this study and underwent scanning using both techniques. Visual qualitative analysis of diffusion-weighted images was accomplished by two independent readers; images were assessed for lesion visibility, adequate fat suppression, and the presence of artifacts. Quantitative analysis was performed by calculating apparent diffusion coefficient (ADC) values and image quality parameters (signal-to-noise ratio [SNR] for lesions and fibroglandular tissue; contrast-to-noise ratio) by manually drawing regions of interest within the phantoms and breast tumor tissue. Interreader variability was determined using the Cohen κ coefficient, and quantitative differences between MUSE DWI and single-shot DWI were assessed using the Mann-Whitney U test; significance was defined at P < .05.Results: MUSE DWI yielded significantly improved image quality compared with single-shot DWI in phantoms (SNR, P = .001) and participants (lesion SNR, P = .009; fibroglandular tissue SNR, P = .05; contrast-to-noise ratio, P = .008). MUSE DWI ADC values showed a significant difference between malignant and benign lesions (P < .001). No significant differences were found between MUSE DWI and single-shot DWI in the mean, maximum, and minimum ADC values (P = .96, P = .28, and P = .49, respectively). Visual qualitative analysis resulted in better lesion visibility for MUSE DWI over single-shot DWI (κ = 0.70).Conclusion: MUSE DWI is a promising high-spatial-resolution technique that may enhance breast MRI protocols without the need for contrast material administration in breast screening.Keywords: Breast, MR-Diffusion Weighted Imaging, OncologySupplemental material is available for this article.© RSNA, 2020.

SUBMITTER: Daimiel Naranjo I

PROVIDER: S-EPMC7983772 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeTo compare the segmentation and detection performance of a deep learning model trained on a database of human-labeled clinical stroke lesions on diffusion-weighted (DW) images to a model trained on the same database enhanced with synthetic stroke lesions.Materials and methodsIn this institutional review board-approved study, a stroke database of 962 cases (mean patient age ± standard deviation, 65 years ± 17; 255 male patients; 449 scans with DW positive stroke lesions) and a normal database of 2027 patients (mean age, 38 years ± 24; 1088 female patients) were used. Brain volumes with synthetic stroke lesions on DW images were produced by warping the relative signal increase of real strokes to normal brain volumes. A generic three-dimensional (3D) U-Net was trained on four different databases to generate four different models: (a) 375 neuroradiologist-labeled clinical DW positive stroke cases (CDB); (b) 2000 synthetic cases (S2DB); (c) CDB plus 2000 synthetic cases (CS2DB); and (d) CDB plus 40 000 synthetic cases (CS40DB). The models were tested on 20% (n = 192) of the cases of the stroke database, which were excluded from the training set. Segmentation accuracy was characterized using Dice score and lesion volume of the stroke segmentation, and statistical significance was tested using a paired two-tailed Student t test. Detection sensitivity and specificity were compared with labeling done by three neuroradiologists.ResultsThe performance of the 3D U-Net model trained on the CS40DB (mean Dice score, 0.72) was better than models trained on the CS2DB (Dice score, 0.70; P < .001) or the CDB (Dice score, 0.65; P < .001). The deep learning model (CS40DB) was also more sensitive (91% [95% confidence interval {CI}: 89%, 93%]) than each of the three human readers (human reader 3, 84% [95% CI: 81%, 87%]; human reader 1, 78% [95% CI: 75%, 81%]; human reader 2, 79% [95% CI: 76%, 82%]), but was less specific (75% [95% CI: 72%, 78%]) than each of the three human readers (human reader 3, 96% [95% CI: 94%, 98%]; human reader 1, 92% [95% CI: 90%, 94%]; human reader 2, 89% [95% CI: 86%, 91%]).ConclusionDeep learning training for segmentation and detection of stroke lesions on DW images was significantly improved by enhancing the training set with synthetic lesions.Supplemental material is available for this article.© RSNA, 2020.

Dataset Information

High-Spatial-Resolution Multishot Multiplexed Sensitivity-encoding Diffusion-weighted Imaging for Improved Quality of Breast Images and Differentiation of Breast Lesions: A Feasibility Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets