Characterization of breast lesion using T1-perfusion magnetic resonance imaging: Qualitative vs. quantitative analysis

Thakran, Snekha; Gupta, Pradeep Kumar; Kabra, Vedant; Saha, Indrajit; Jain, Priti; Gupta, Rakesh K.; Singh, Anup

doi:10.1016/j.diii.2018.05.006

Cited by 10 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Voxel‐wise signal intensity time curves of perfusion MRI data were converted to concentration‐time curve C(t) using the methodology reported previously 22,31 . This conversion required voxel‐wise precontrast tissue parameter (T 1 ) estimation.…”

Section: Methodsmentioning

confidence: 99%

“…Voxel‐wise first‐pass analysis of C(t) was carried out for computing the hemodynamic parameters (BBV and BBF) using the methodology described previously 22 . These hemodynamic parameters do have contamination, due to the leakage effect in breast tissues.…”

Section: Methodsmentioning

confidence: 99%

“…Thakran et al reported an AUC of 0.89, 0.89, and 0.93 for the differentiation of grade I versus II, grade II versus III, and grade I versus III, respectively, using a hemodynamic feature (breast blood volume corrected [BBVcorr]) alone. BBVcorr yielded a sensitivity of 93% and a specificity of 80% for grade I versus II, a sensitivity of 91% and a specificity of 100% for grade I versus III, and a sensitivity of 91% and a specificity of 87% for grade II versus III 22 . Angiogenesis is an important marker for tumor aggressiveness and it increases with an increase in tumor grade.…”

Section: Introductionmentioning

confidence: 99%

“…Angiogenesis is an important marker for tumor aggressiveness and it increases with an increase in tumor grade. In a recently reported study, 22 quantitative parameters from T 1 perfusion MRI, particularly hemodynamic parameters (breast blood volume [BBV] and breast blood flow [BBF]), were shown to provide high accuracy in the classification of breast tumors compared with other quantitative parameters.…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies have reported the use of texture features extracted from mp-MRI data in breast tumor classification. 19,23 Multiple types of features have been reported in the literature to characterize breast tumors with varying sensitivity and specificity. 24,25 However, this can lead to a large number of features, and the task of classifier development can become computationally expensive and prone to overfitting, particularly for small data samples.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Characterization of breast tumors using machine learning based upon multiparametric magnetic resonance imaging features

2021

Self Cite

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) is playing an important role in the classification of breast tumors. MRI can be used to obtain multiparametric (mp) information, such as structural, hemodynamic, and physiological information. Quantitative analysis of mp‐MRI data has shown potential in improving the accuracy of breast tumor classification. In general, a large set of quantitative and texture features can be generated depending upon the type of methodology used. A suitable combination of selected quantitative and texture features can further improve the accuracy of tumor classification. Machine learning (ML) classifiers based upon features derived from MRI data have shown potential in tumor classification. There is a need for further research studies on selecting an appropriate combination of features and evaluating the performance of different ML classifiers for accurate classification of breast tumors. The objective of the current study was to develop and optimize an ML framework based upon mp‐MRI features for the characterization of breast tumors (malignant vs. benign and low‐ vs. high‐grade). This study included the breast mp‐MRI data of 60 female patients with histopathology results. A total of 128 features were extracted from the mp‐MRI tumor data followed by features selection. Five ML classifiers were evaluated for tumor classification using 10‐fold crossvalidation with 10 repetitions. The support vector machine (SVM) classifier based on optimum features selected using a wrapper method with an adaptive boosting (AdaBoost) technique provided the highest sensitivity (0.96 ± 0.03), specificity (0.92 ± 0.09), and accuracy (94% ± 2.91%) in the classification of malignant versus benign tumors. This method also provided the highest sensitivity (0.94 ± 0.07), specificity (0.80 ± 0.05), and accuracy (90% ± 5.48%) in the classification of low‐ versus high‐grade tumors. These findings suggest that the SVM classifier outperformed other ML methods in the binary classification of breast tumors.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%