Feasibility to virtually generate T2 fat-saturated breast MRI by convolutional neural networks
Authors:
- Andrzej LiebertALAndrzej Liebert
- Dominique HadlerDHDominique Hadler
- Chris EhringCEChris Ehring
- Hannes SchreiterHSHannes Schreiter
- Luise BrockLBLuise Brock
- Lorenz A. KapsnerLKLorenz A. Kapsner
- Jessica EberleJEJessica Eberle
- Ramona ErberRERamona Erber
- Frederik B. LaunFLFrederik B. Laun
- Michael UderMUMichael Uder
- Evelyn WenkelEWEvelyn Wenkel
Preprint
Abstract
Background Breast magnetic resonance imaging (MRI) protocols often include T2-weighted fat-saturated (T2w-FS) sequences, which are vital for tissue characterization but significantly increase scan time. Purpose This study aims to evaluate whether a 2D-U-Net neural network can generate virtual T2w-FS images from routine multiparametric breast MRI sequences. Materials and Methods This IRB approved, retrospective study included n=914 breast MRI examinations performed between January 2017 and June 2020. The dataset was divided into training (n=665), validation (n=74), and test sets (n=175). The U-Net was trained on T1-weighted (T1w), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) sequences to generate virtual T2w-FS images (VirtuT2). Quantitative metrics and a qualitative multi-reader assessment by two radiologists were used to evaluate the VirtuT2 images. Results VirtuT2 images demonstrated high structural similarity (SSIM=0.87) and peak signal-to-noise ratio (PSNR=24.90) compared to original T2w-FS images. High level of the frequency error norm (HFNE=0.87) indicates strong blurring presence in the VirtuT2 images, which was also confirmed in qualitative reading. Radiologists correctly identified VirtuT2 images with 92.3% and 94.2% accuracy, respectively. No significant difference in diagnostic image quality (DIQ) was noted for one reader (p=0.21), while the other reported significantly lower DIQ for VirtuT2 (p<=0.001). Moderate inter-reader agreement was observed for edema detection on T2w-FS images (ƙ=0.43), decreasing to fair on VirtuT2 images (ƙ=0.36). Conclusion The 2D-U-Net can technically generate virtual T2w-FS images with high similarity to real T2w-FS images, though blurring remains a limitation. Further investigation of other architectures and using larger datasets are needed to improve clinical applicability. Summary Statement Virtual T2-weighted fat-saturated images can be generated from routine breast MRI sequences using convolutional neural networks, showing high structural similarity but with notable blurring, necessitating further refinement for clinical use. Key Results Images with T2w-FS characteristics can be virtually generated from T1w and DWI images using deep learning Image blurring occurring in the VirtuT2 image limit clinical use for the current moment Further investigation of different architectures and with larger datasets are necessary in the future to improve the VirtuT2 performance.Keywords
This publication has 14 references indexed in Scilit:
- Synthesis of Contrast-Enhanced Breast MRI Using T1- and Multi-b-Value DWI-Based Hierarchical Fusion Network with Attention Mechanism2023
- Artificial Intelligence to Reduce or Eliminate the Need for Gadolinium-Based Contrast Agents in Brain and Cardiac MRIInvestigative Radiology, 2023
- Deep Multi-Scale U-Net Architecture and Label-Noise Robust Training Strategies for Histopathological Image Segmentation2022
- Synthesizing MR Image Contrast Enhancement Using 3D High-Resolution ConvNetsIEEE Transactions on Biomedical Engineering, 2022
- Multimodal MRI synthesis using unified generative adversarial networksMedical Physics, 2020
- Anthropogenic gadolinium in freshwater and drinking water systemsWater Research, 2020
- MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentationNeural Networks, 2020
- Comparison of Study Activity Times for “Full” versus “Fast MRI” for Breast Cancer ScreeningJournal of the American College of Radiology, 2019
- Is Ultrafast or Abbreviated Breast MRI Ready for Prime Time?Current Breast Cancer Reports, 2019
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004