Online citations, reference lists, and bibliographies.
← Back to Search

Interobserver Variability In Identification Of Breast Tumors In MRI And Its Implications For Prognostic Biomarkers And Radiogenomics.

Ashirbani Saha, L. Grimm, Michael R. Harowicz, S. Ghate, C. Kim, R. Walsh, M. Mazurowski
Published 2016 · Medicine, Physics

Cite This
Download PDF
Analyze on Scholarcy
PURPOSE To assess the interobserver variability of readers when outlining breast tumors in MRI, study the reasons behind the variability, and quantify the effect of the variability on algorithmic imaging features extracted from breast MRI. METHODS Four readers annotated breast tumors from the MRI examinations of 50 patients from one institution using a bounding box to indicate a tumor. All of the annotated tumors were biopsy proven cancers. The similarity of bounding boxes was analyzed using Dice coefficients. An automatic tumor segmentation algorithm was used to segment tumors from the readers' annotations. The segmented tumors were then compared between readers using Dice coefficients as the similarity metric. Cases showing high interobserver variability (average Dice coefficient <0.8) after segmentation were analyzed by a panel of radiologists to identify the reasons causing the low level of agreement. Furthermore, an imaging feature, quantifying tumor and breast tissue enhancement dynamics, was extracted from each segmented tumor for a patient. Pearson's correlation coefficients were computed between the features for each pair of readers to assess the effect of the annotation on the feature values. Finally, the authors quantified the extent of variation in feature values caused by each of the individual reasons for low agreement. RESULTS The average agreement between readers in terms of the overlap (Dice coefficient) of the bounding box was 0.60. Automatic segmentation of tumor improved the average Dice coefficient for 92% of the cases to the average value of 0.77. The mean agreement between readers expressed by the correlation coefficient for the imaging feature was 0.96. CONCLUSIONS There is a moderate variability between readers when identifying the rectangular outline of breast tumors on MRI. This variability is alleviated by the automatic segmentation of the tumors. Furthermore, the moderate interobserver variability in terms of the bounding box does not translate into a considerable variability in terms of assessment of enhancement dynamics. The authors propose some additional ways to further reduce the interobserver variability.
This paper references
Quantitative analysis of lesion morphology and texture features for diagnostic prediction in breast MRI.
K. Nie (2008)
Prognostic value of pre-treatment DCE-MRI parameters in predicting disease free and overall survival for breast cancer patients undergoing neoadjuvant chemotherapy.
M. Pickles (2009)
Identification of intrinsic imaging phenotypes for breast cancer tumors: preliminary associations with gene expression profiles.
A. Ashraf (2014)
Dynamic MR imaging of breast lesions: correlation with microvessel distribution pattern and histologic characteristics of prognosis.
A. Teifke (2006)
Dynamic contrast‐enhanced MRI in the differentiation of breast tumors: User‐defined versus semi‐automated region‐of‐interest analysis
G. Liney (1999)
Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk
Majid Mahrooghy (2015)
Lesion type and reader experience affect the diagnostic accuracy of breast MRI: a multiple reader ROC study.
P. Baltzer (2015)
Early Changes in Functional Dynamic Magnetic Resonance Imaging Predict for Pathologic Response to Neoadjuvant Chemotherapy in Primary Breast Cancer
M. Ah-See (2008)
Mammography, US, and MRI for Preoperative Prediction of Extensive Intraductal Component of Invasive Breast Cancer: Interobserver Variability and Performances.
Hye Rin Kim (2016)
Dynamic contrastenhanced MRI in the di ff erentiation of breast tumors : User - defined versus semi - automated regionofinterest analysis
H. K. Jung (1999)
Prediction of clinical phenotypes in invasive breast carcinomas from the integration of radiomics and genomics data
Wentian Guo (2015)
A feasible high spatiotemporal resolution breast DCE-MRI protocol for clinical settings.
L. A. Tudorica (2012)
Dynamic MR imaging of invasive breast cancer: correlation with tumour grade and other histological factors.
S. Mussurakis (1997)
Intratumoral heterogeneity of the distribution of kinetic parameters in breast cancer: comparison based on the molecular subtypes of invasive breast cancer
K. Yamaguchi (2014)
Evaluation of breast tumor response to neoadjuvant chemotherapy with tomographic diffuse optical spectroscopy: case studies of tumor region-of-interest changes.
S. Jiang (2009)
Breast cancer: early prediction of response to neoadjuvant chemotherapy using parametric response maps for MR imaging.
N. Cho (2014)
Identification of Intrinsic Imaging Phenotypes for Breast Cancer Tumors: Preliminary Associations with Gene Expression Profiles
K. Shin (2015)
Breast MR imaging for extent of disease assessment in patients with newly diagnosed breast cancer.
N. Brasic (2013)
Predicting local recurrence following breast-conserving treatment: parenchymal signal enhancement ratio (SER) around the tumor on preoperative MRI
M. Kim (2013)
Malignant lesion segmentation in contrast-enhanced breast MR images based on the marker-controlled watershed.
Y. Cui (2009)
ACR BIRADS ® Magnetic Resonance Imaging
M. L. Giger
Breast cancer molecular subtype classifier that incorporates MRI features
E. Sutton (2016)
Breast MRI: EUSOBI recommendations for women’s information
R. Mann (2015)
MRI measurements of breast tumor volume predict response to neoadjuvant chemotherapy and recurrence-free survival.
S. Partridge (2005)
A Multichannel Markov Random Field Framework for Tumor Segmentation With an Application to Classification of Gene Expression-Based Breast Cancer Recurrence Risk
A. Ashraf (2013)
Computational approach to radiogenomics of breast cancer: Luminal A and luminal B molecular subtypes are associated with imaging features on routine breast MRI extracted using computer vision algorithms
L. Grimm (2015)
Assessing heterogeneity of lesion enhancement kinetics in dynamic contrast-enhanced MRI for breast cancer diagnosis.
A. Karahaliou (2010)
Cancerous breast lesions on dynamic contrast-enhanced MR images: computerized characterization for image-based prognostic markers.
N. Bhooshan (2010)
Current clinical indications for magnetic resonance imaging of the breast
F. Knuttel (2014)
A new quantitative image analysis method for improving breast cancer diagnosis using DCE-MRI examinations.
Q. Yang (2015)
Magnetic resonance imaging of the breast: recommendations from the EUSOMA working group.
F. Sardanelli (2010)
Magnetic resonance imaging texture analysis classification of primary breast cancer
S. Waugh (2015)
Effect of Imaging Parameter Thresholds on MRI Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer Subtypes
Wei-Ching Lo (2016)
A Fuzzy C-Means (FCM)-Based Approach for Computerized Segmentation of Breast Lesions in Dynamic Contrast-Enhanced MR Images1
W. Chen (2006)
Recurrence-free survival in breast cancer is associated with MRI tumor enhancement dynamics quantified using computer algorithms.
M. Mazurowski (2015)
Radiogenomic analysis of breast cancer: luminal B molecular subtype is associated with enhancement dynamics at MR imaging.
M. Mazurowski (2014)
Computerized image analysis for identifying triple-negative breast cancers and differentiating them from other molecular subtypes of breast cancer on dynamic contrast-enhanced MR images: a feasibility study.
S. Agner (2014)
Breast parenchymal signal enhancement ratio at preoperative magnetic resonance imaging: association with early recurrence in triple-negative breast cancer patients
V. Park (2016)

This paper is referenced by
Deep Learning for identifying radiogenomic associations in breast cancer
Z. Zhu (2019)
Hierarchical Convolutional Neural Networks for Segmentation of Breast Tumors in MRI With Application to Radiogenomics
J. Zhang (2019)
Breast cancer molecular subtype classification using deep features: preliminary results
Z. Zhu (2018)
A study of association of Oncotype DX recurrence score with DCE-MRI characteristics using multivariate machine learning models
Ashirbani Saha (2018)
MRI-based radiomics in breast cancer: feature robustness with respect to inter-observer segmentation variability
R. Granzier (2020)
Breast cancer MRI radiomics: An overview of algorithmic features and impact of inter‐reader variability in annotating tumors
Ashirbani Saha (2018)
Radiomics and imaging genomics in precision medicine
G. Lee (2017)
Association of distant recurrence‐free survival with algorithmically extracted MRI characteristics in breast cancer
M. Mazurowski (2019)
Can algorithmically assessed MRI features predict which patients with a preoperative diagnosis of ductal carcinoma in situ are upstaged to invasive breast cancer?
Michael R. Harowicz (2017)
Performance evaluation of breast lesion detection systems with expert delineations: a comparative investigation on mammographic images
Bikesh Kumar Singh (2019)
Semantic Scholar Logo Some data provided by SemanticScholar