Statistical normalization techniques for magnetic resonance imaging

By Russell T. Shinohara, E. Sweeney, J. Goldsmith, Navid Shiee, F. Mateen, Peter A. Calabresi, S. Jarso, Dzung L. Pham, Daniel S. Reich, Ciprian M. Crainiceanu. NeuroImage: Clinical, 2014

406 citations recorded by the source corpus.

While computed tomography and other imaging techniques are measured in absolute units with physical meaning, magnetic resonance images are expressed in arbitrary units that are difficult to interpret and differ between study visits and subjects. Much work in the image processing literature on intensity normalization has focused on histogram matching and other histogram mapping techniques, with little emphasis on normalizing images to have biologically interpretable units. Furthermore, there are no formalized principles or goals for the crucial comparability of image intensities within and across subjects. To address this, we propose a set of criteria necessary for the normalization of images. We further propose simple and robust biologically motivated normalization techniques for multisequence brain imaging that have the same interpretation across acquisitions and satisfy the proposed criteria. We compare the performance of different normalization methods in thousands of images of patients with Alzheimer's disease, hundreds of patients with multiple sclerosis, and hundreds of healthy subjects obtained in several different studies at dozens of imaging centers.

Subfields: Biophysics, Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/776554b9b57bb1d1fafa00ed30f16b6f3c04b2f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biophysics

1. P. Heng
2. Heang-Ping Chan
3. Lequan Yu
4. Lubomir M. Hadjiiski
5. P. Cook
6. Ravi K. Samala
7. Qi-Yan Dou

In Computer Vision and Pattern Recognition

1. Qi-Yan Dou
2. P. Heng
3. Quande Liu
4. Lequan Yu
5. Russell T. Shinohara
6. Di Dong
7. Jie Tian
8. Heang-Ping Chan

Citations in the corpus

• Harmonization of cortical thickness measurements across scanners and sites (2017, methodology): “For instance, for WhiteStripe and RAVEL, control features in the WM and in the CSF are required, which do not make sense in the context of cortical thickness measurements in the GM.”
• Explainable AI for medical imaging: deep-learning CNN ensemble for classification of estrogen receptor status from breast MRI (2020, methodology): “The process involved applying Whitestripe normalization[7] on the DCE-MRI volumes at peak contrast to homogenize the data using the non-dense region of adipose tissue as a reference.”
• Harmonization of multi-site diffusion tensor imaging data (2017, methodology): “It is an extension of a previous intensity normalization, called White Stripe [Shinohara et al., 2014], developed to normalize white matter intensities in structural MRI.”
• MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data (2020, background): “…improve the effectiveness of utilizing multiple sites of data, in medical image analysis, a variety of image intensity normalization methods [12], [13] have been proposed to alleviate the inter-site appearance difference in the pre-processing step, and therefore to improve the performance on…”
• The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges (2019, background): “Moreover, some mature algorithms and tools could help to remove unwanted low-frequency intensity nonuniformity [41, 42] and perform image intensity normalization [43-45] in order to reduce the difference caused by different acquisition parameters of brain MRI.”