Evaluating the impact of intensity normalization on MR image synthesis

Reinhold, Jacob C.; Dewey, Blake E.; Carass, Aaron; Prince, Jerry L.

doi:10.1117/12.2513089

Cited by 122 publications

(115 citation statements)

References 27 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…More details about intensity normalization methods can be found in the original papers [31][32][33] . The code used in this paper as well as details about the algorithm implementation 61 are available at https ://githu b.com/jcrei nhold /inten sity-norma lizat ion.…”

Section: Methodsmentioning

confidence: 99%

Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics

Carré

Klausner

Edjlali

et al. 2020

Sci Rep

171

162

View full text Add to dashboard Cite

Radiomics relies on the extraction of a wide variety of quantitative image-based features to provide decision support. Magnetic resonance imaging (MRI) contributes to the personalization of patient care but suffers from being highly dependent on acquisition and reconstruction parameters. Today, there are no guidelines regarding the optimal pre-processing of MR images in the context of radiomics, which is crucial for the generalization of published image-based signatures. This study aims to assess the impact of three different intensity normalization methods (Nyul, WhiteStripe, Z-Score) typically used in MRI together with two methods for intensity discretization (fixed bin size and fixed bin number). The impact of these methods was evaluated on first-and second-order radiomics features extracted from brain MRI, establishing a unified methodology for future radiomics studies. Two independent MRI datasets were used. The first one (DATASET1) included 20 institutional patients with WHO grade II and III gliomas who underwent post-contrast 3D axial T1-weighted (T1w-gd) and axial T2-weighted fluid attenuation inversion recovery (T2w-flair) sequences on two different MR devices (1.5 T and 3.0 T) with a 1-month delay. Jensen-Shannon divergence was used to compare pairs of intensity histograms before and after normalization. The stability of first-order and secondorder features across the two acquisitions was analysed using the concordance correlation coefficient and the intra-class correlation coefficient. The second dataset (DATASET2) was extracted from the public TCIA database and included 108 patients with WHO grade II and III gliomas and 135 patients with WHO grade IV glioblastomas. The impact of normalization and discretization methods was evaluated based on a tumour grade classification task (balanced accuracy measurement) using five well-established machine learning algorithms. Intensity normalization highly improved the robustness of first-order features and the performances of subsequent classification models. For the T1w-gd sequence, the mean balanced accuracy for tumour grade classification was increased from 0.67 (95% CI 0.61-0.73) to 0.82 (95% CI 0.79-0.84, P = .006), 0.79 (95% CI 0.76-0.82, P = .021) and 0.82 (95% CI 0.80-0.85, P = .005), respectively, using the Nyul, WhiteStripe and Z-Score normalization methods compared to no normalization. The relative discretization makes unnecessary the use of intensity normalization for the second-order radiomics features. Even if the bin number for the discretization had a small impact on classification performances, a good compromise was obtained

show abstract

Section: Methodsmentioning

confidence: 99%

Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics

Carré

Klausner

Edjlali

et al. 2020

Sci Rep

171

162

View full text Add to dashboard Cite

show abstract

“…The white matter peaks of the two images are far away. Thus, MR images normalization is needed to guarantee that the grey values of the same tissue among different MR images are close to each other [ 28 ].…”

Section: Methodsmentioning

confidence: 99%

Automatic Prediction of MGMT Status in Glioblastoma via Deep Learning-Based MR Image Analysis

Chen

Zeng

Tong

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

Methylation of the O6-methylguanine methyltransferase (MGMT) gene promoter is correlated with the effectiveness of the current standard of care in glioblastoma patients. In this study, a deep learning pipeline is designed for automatic prediction of MGMT status in 87 glioblastoma patients with contrast-enhanced T1W images and 66 with fluid-attenuated inversion recovery(FLAIR) images. The end-to-end pipeline completes both tumor segmentation and status classification. The better tumor segmentation performance comes from FLAIR images (Dice score, 0.897±0.007) compared to contrast-enhanced T1WI (Dice score, 0.828±0.108), and the better status prediction is also from the FLAIR images (accuracy, 0.827±0.056; recall, 0.852±0.080; precision, 0.821±0.022; and F1 score, 0.836±0.072). This proposed pipeline not only saves the time in tumor annotation and avoids interrater variability in glioma segmentation but also achieves good prediction of MGMT methylation status. It would help find molecular biomarkers from routine medical images and further facilitate treatment planning.

show abstract

“…To compensate for artifacts between scans, each MR and DW sequence were normalized across the patient set. Standard MR sequences were normalized using the RAVEL method [45] implemented with the intensity-normalization library [46]. The DW sequence was normalized using MRtrix’s dwiintensitynorm.…”

Section: Methodsmentioning

confidence: 99%

Biopsy Confirmed Glioma Recurrence Predicted by Multi-Modal Neuroimaging Metrics

Costabile

Thompson

Alaswad

et al. 2019

JCM

View full text Add to dashboard Cite

Histopathological verification is currently required to differentiate tumor recurrence from treatment effects related to adjuvant therapy in patients with glioma. To bypass the complications associated with collecting neural tissue samples, non-invasive classification methods are needed to alleviate the burden on patients while providing vital information to clinicians. However, uncertainty remains as to which tissue features on magnetic resonance imaging (MRI) are useful. The primary objective of this study was to quantitatively assess the reliability of combining MRI and diffusion tensor imaging metrics to discriminate between tumor recurrence and treatment effects in histopathologically identified biopsy samples. Additionally, this study investigates the noise adjuvant radiation therapy introduces when discriminating between tissue types. In a sample of 41 biopsy specimens, from a total of 10 patients, we derived region-of-interest samples from MRI data in the ipsilateral hemisphere that encompassed biopsies obtained during resective surgery. This study compares normalized intensity values across histopathology classifications and contralesional volumes reflected across the midline. Radiation makes noninvasive differentiation of abnormal-nontumor tissue to tumor recurrence much more difficult. This is because radiation exhibits opposing behavior on key MRI modalities: specifically, on post-contrast T1, FLAIR, and GFA. While radiation makes noninvasive differentiation of tumor recurrence more difficult, using a novel analysis of combined MRI metrics combined with clinical annotation and histopathological correlation, we observed that it is possible to successfully differentiate tumor tissue from other tissue types. Additional work will be required to expand upon these findings.

show abstract

Evaluating the impact of intensity normalization on MR image synthesis

Cited by 122 publications

References 27 publications

Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics

Standardization of brain MR images across machines and protocols: bridging the gap for MRI-based radiomics

Automatic Prediction of MGMT Status in Glioblastoma via Deep Learning-Based MR Image Analysis

Biopsy Confirmed Glioma Recurrence Predicted by Multi-Modal Neuroimaging Metrics

Contact Info

Product

Resources

About