Deep learning based correction of RF field induced inhomogeneities for T2w prostate imaging at 7 T

• Published in: NMR in biomedicine Vol. 36; no. 12; p. e5019
• Main Authors: Harrevelt, Seb D., Meliado, Ettore F. M., van Lier, Astrid L. H. M. W., Reesink, Daan, Meijer, Richard P., Pluim, Josien P. W., Raaijmakers, Alexander J. E.
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.12.2023
• Subjects: Algorithms; Arrays; Bias; Biological products; Datasets; Deep Learning; Homogeneity; Humans; Image contrast; Image Processing, Computer-Assisted - methods; Inhomogeneity; Machine learning; Male; Neural networks; Neural Networks, Computer; Performance evaluation; Prostate; Prostate - diagnostic imaging; Questionnaires; deep learning; 7 T; neural networks; bias field removal
• ISSN: 0952-3480; 1099-1492; 1099-1492
• DOI: 10.1002/nbm.5019

At ultrahigh field strengths images of the body are hampered by B 1 ‐field inhomogeneities. These present themselves as inhomogeneous signal intensity and contrast, which is regarded as a “bias field” to the ideal image. Current bias field correction methods, such as the N4 algorithm, assume a low frequency bias field, which is not sufficiently valid for T2w images at 7 T. In this work we propose a deep learning based bias field correction method to address this issue for T2w prostate images at 7 T. By combining simulated B 1 ‐field distributions of a multi‐transmit setup at 7 T with T2w prostate images at 1.5 T, we generated artificial 7 T images for which the homogeneous counterpart was available. Using these paired data, we trained a neural network to correct the bias field. We predicted either a homogeneous image (t‐Image neural network) or the bias field (t‐Biasf neural network). In addition, we experimented with the single‐channel images of the receive array and the corresponding sum of magnitudes of this array as the input image. Testing was carried out on four datasets: the test split of the synthetic training dataset, volunteer and patient images at 7 T, and patient images at 3 T. For the test split, the performance was evaluated using the structural similarity index measure, Wasserstein distance, and root mean squared error. For all other test data, the features Homogeneity and Energy derived from the gray level co‐occurrence matrix (GLCM) were used to quantify the improvement. For each test dataset, the proposed method was compared with the current gold standard: the N4 algorithm. Additionally, a questionnaire was filled out by two clinical experts to assess the homogeneity and contrast preservation of the 7 T datasets. All four proposed neural networks were able to substantially reduce the B 1 ‐field induced inhomogeneities in T2w 7 T prostate images. By visual inspection, the images clearly look more homogeneous, which is confirmed by the increase in Homogeneity and Energy in the GLCM, and the questionnaire scores from two clinical experts. Occasionally, changes in contrast within the prostate were observed, although much less for the t‐Biasf network than for the t‐Image network. Further, results on the 3 T dataset demonstrate that the proposed learning based approach is on par with the N4 algorithm. The results demonstrate that the trained networks were capable of reducing the B 1 ‐field induced inhomogeneities for prostate imaging at 7 T. The quantitative evaluation showed that all proposed learning based correction techniques outperformed the N4 algorithm. Of the investigated methods, the single‐channel t‐Biasf neural network proves most reliable for bias field correction.