Rim sign and histogram analysis of apparent diffusion coefficient values on diffusion-weighted MRI in triple-negative breast cancer: Comparison with ER-positive subtype

Choi, Yangsean; Kim, Sung Hun; Youn, In Kyung; Kang, Bong Joo; Park, Woo Chan; Lee, Ahwon

doi:10.1371/journal.pone.0177903

Cited by 38 publications

(18 citation statements)

References 31 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DWI reflecting the microenvironment of tumor structures was introduced to be a complementary tool that provided additional tissue information (31). Most studies used the histogram or texture analysis on ADC maps with a mono-exponential fit (15, 32, 33). In addition, there is one study for which the authors performed histogram analysis on maps from mono-exponential DWI and biexponential intravoxel incoherent motion (IVIM) to predict the HER2 status in ER-positive breast cancer (33).…”

Section: Discussionmentioning

confidence: 99%

“…Agner et al used the morphologic and texture features extracted from the whole tumor on early postcontrast images in conjunction with an SVM classifier to identify TN cancer (14). Several studies have proposed the histogram or textural features extracted from DWI for subtype differentiation (15, 16). However, no study has attempted to investigate the texture analysis based radiomics of combining DCE imaging and DWI in the subtype classification of breast cancer.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-Based Analysis of MR Multiparametric Radiomics for the Subtype Classification of Breast Cancer

et al. 2019

View full text Add to dashboard Cite

Objective: To investigate whether machine learning analysis of multiparametric MR radiomics can help classify immunohistochemical (IHC) subtypes of breast cancer. Study design: One hundred and thirty-four consecutive patients with pathologically-proven invasive ductal carcinoma were retrospectively analyzed. A total of 2,498 features were extracted from the DCE and DWI images, together with the new calculated images, including DCE images changing over six time points (DCE sequential ) and DWI images changing over three b -values (DWI sequential ). We proposed a novel two-stage feature selection method combining traditional statistics and machine learning-based methods. The accuracies of the 4-IHC classification and triple negative (TN) vs. non-TN cancers were assessed. Results: For the 4-IHC classification task, the best accuracy of 72.4% was achieved based on linear discriminant analysis (LDA) or subspace discrimination of assembled learning in conjunction with 20 selected features, and only small dependent emphasis of Kendall-tau-b for sequential features, based on the DWI sequential with the LDA model, yielding an accuracy of 53.7%. The linear support vector machine (SVM) and medium k-nearest neighbor using eight features yielded the highest accuracy of 91.0% for comparing TN to non-TN cancers, and the maximum variance for DWI sequential alone, together with a linear SVM model, achieved an accuracy of 83.6%. Conclusions: Whole-tumor radiomics on MR multiparametric images, DCE images changing over time points, and DWI images changing over different b -values provide a non-invasive analytical approach for breast cancer subtype classification and TN cancer identification.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Analysis of MR Multiparametric Radiomics for the Subtype Classification of Breast Cancer

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The correlation between MRI enhancement and breast cancer genotyping can also be explained by histogram analysis. 9 In the present research, 13 histogram parameters were used to differentiate breast cancers with lymph node metastasis from those without lymph node metastasis. Energy exhibited the best diagnostic ability to distinguish between breast cancers with and without lymph node metastases.…”

Section: Discussionmentioning

confidence: 99%

“…In breast cancer research, histograms have been used to clarify the difference between triple-negative breast cancer and ER-positive breast cancer. 9 Histograms from DCE-MRI can also be utilized to evaluate the response of patients with advanced breast cancer to neoadjuvant chemotherapy. 10 Histogram analysis has been performed to examine the parameters derived from a MR function sequence, and the histogram metrics of the perfusion fraction and pseudo-diffusivity of an intravoxel incoherent motion sequence are related to molecular prognostic factors and breast cancer malignancy.…”

Section: Introductionmentioning

confidence: 99%

Differentiating the lymph node metastasis of breast cancer through dynamic contrast-enhanced magnetic resonance imaging

Xu¹,

Chunrong²,

Hou³

et al. 2019

BJR|Open

View full text Add to dashboard Cite

Objective: Lymph node metastasis is an important trait of breast cancer, and tumors with different lymph node statuses require various clinical treatments. This study was designed to evaluate the lymph node metastasis of breast cancer through pharmacokinetic and histogram analysis via dynamic contrast-enhanced (DCE) MRI. Methods and materials: A retrospective analysis was conducted to quantitatively evaluate the lymph node statuses of patients with breast cancer. A total of 75 patients, i.e. 34 patients with lymph node metastasis and 41 patients without lymph node metastasis, were involved in this research. Of the patients with lymph node metastases, 19 had sentinel lymph node metastasis, and 15 had axillary lymph node metastasis. MRI was conducted using a 3.0 T imaging device. Segmentation was carried out on the regions of interest (ROIs) in breast tumors under DCE-MRI, and pharmacokinetic and histogram parameters were calculated from the same ROIs. Mann–Whitney U test was performed, and receiver operating characteristic curves for the parameters of the two groups were constructed to determine their diagnostic values. Results: Pharmacokinetic parameters, including Ktrans, Kep, area under the curve of time–concentration, and time to peak, which were derived from the extended Tofts linear model for DCE-MRI, could highlight the tumor areas in the breast and reveal the increased perfusion. Conversely, the pharmacokinetic parameters showed no significant difference between the patients with and without lymph node metastases. By contrast, the parameters from the histogram analysis yielded promising results. The entropy of the ROIs exhibited the best diagnostic ability between patients with and without lymph node metastases (p < 0.01, area under the curve of receiver operating characteristic = 0.765, specificity = 0.706, sensitivity = 0.780). Conclusion: In comparison with the pharmacokinetic parameters, the histogram analysis of the MR images could reveal the differences between patients with and without lymph node metastases. The entropy from the histogram indicated that the diagnostic ability was highly sensitive and specific. Advances in knowledge: This research gave out a promising result on the differentiating lymph node metastases through histogram analysis on tumors in DCE-MR images. Histogram could reveal the tumors heterogenicity between patients with different lymph node status.

show abstract

“…Small ROI placed over the most hypointense area of the b = 800 s/mm 2 image may provide more accurate measures in heterogeneous lesions while placing the ROI over the whole lesion may provide more reproducible results. 13–15 Semiautomated ROI selection methods may allow for more consistent results 16 and lately some authors claim histogram analysis 17–19 might be an even more accurate way of assessing intra tumoral heterogeneity.…”

Section: The Development and Validation Of Diffusion-mri As An Imaginmentioning

confidence: 99%

Diffusion-weighted imaging of the breast: current status as an imaging biomarker and future role

Herrero

2019

BJR|Open

View full text Add to dashboard Cite

Diffusion-weighted imaging (DWI) of the breast is a MRI sequence that shows several advantages when compared to the dynamic contrast-enhanced sequence: it does not need intravenous contrast, it is relatively quick and easy to implement (artifacts notwithstanding). In this review, the current applications of DWI for lesion characterization and prognosis as well as for response evaluation are analyzed from the point of view of the necessary steps to become a useful surrogate of underlying biological processes (tissue architecture and cellularity): from the proof of concept, to the proof of mechanism, the proof of principle and finally the proof of effectiveness. Future applications of DWI in screening, DWI modeling and radiomics are also discussed.

show abstract

Rim sign and histogram analysis of apparent diffusion coefficient values on diffusion-weighted MRI in triple-negative breast cancer: Comparison with ER-positive subtype

Cited by 38 publications

References 31 publications

Machine Learning-Based Analysis of MR Multiparametric Radiomics for the Subtype Classification of Breast Cancer

Machine Learning-Based Analysis of MR Multiparametric Radiomics for the Subtype Classification of Breast Cancer

Differentiating the lymph node metastasis of breast cancer through dynamic contrast-enhanced magnetic resonance imaging

Diffusion-weighted imaging of the breast: current status as an imaging biomarker and future role

Contact Info

Product

Resources

About