Balancing Bias and Variance in Deep Learning‐Based Tumor Microstructural Parameter Mapping
We demonstrated and explained the low bias-high variance of NLLS and the low variance-high bias of MSE-Net. The proposed B2V-Net can balance bias and variance. Our work provided insights and methods to guide the design of customized loss functions tailored to specific clinical imaging needs.
Authors
- Yue Cao (ORCID: https://orcid.org/0000-0003-3910-3261)
- Jiaren Zou (ORCID: https://orcid.org/0000-0002-8356-1967)
Institutions
- University of Michigan (US)
Publication Details
- Journal
- Magnetic Resonance in Medicine
- Published
- 2025-10-22
- DOI
- https://doi.org/10.1002/mrm.70154
- Primary Topic
- Advanced Neuroimaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00