Cancerous Breast Lesions on Dynamic Contrast-enhanced MR Images: Computerized Characterization for Image-based Prognostic Markers

Bhooshan, Neha; Giger, Maryellen L.; Jansen, Sanaz A.; Li, Hui; Li, Lan; Newstead, Gillian M.

doi:10.1148/radiol.09090838

Cited by 178 publications

(163 citation statements)

References 52 publications

Supporting

Mentioning

157

Contrasting

Unclassified

Order By: Relevance

“…Thirdly, more morphological features can be extracted around the tumor region to have more understanding of the relation between vascularity and the likelihood of tumor malignancy. Finally, our vascular features might also be used as prognostic markers to differentiate different histology [37,38].…”

Section: Discussionmentioning

confidence: 99%

Diagnosis of Solid Breast Tumors Using Vessel Analysis in Three-Dimensional Power Doppler Ultrasound Images

et al. 2013

View full text Add to dashboard Cite

This study aims to evaluate whether the distribution of vessels inside and adjacent to tumor region at threedimensional (3-D) power Doppler ultrasonography (US) can be used for the differentiation of benign and malignant breast tumors. 3-D power Doppler US images of 113 solid breast masses (60 benign and 53 malignant) were used in this study. Blood vessels within and adjacent to tumor were estimated individually in 3-D power Doppler US images for differential diagnosis. Six features including volume of vessels, vascularity index, volume of tumor, vascularity index in tumor, vascularity index in normal tissue, and vascularity index in surrounding region of tumor within 2 cm were evaluated. Neural network was then used to classify tumors by using these vascular features. The receiver operating characteristic (ROC) curve analysis and Student's t test were used to estimate the performance. All the six proposed vascular features are statistically significant (p<0.001) for classifying the breast tumors as benign or malignant. The A Z (area under ROC curve) values for the classification result were 0.9138. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis performance based on all six proposed features were 82.30 (93/113), 86.79 (46/53), 78.33 (47/60), 77.97 (46/59), and 87.04 % (47/54), respectively. The p value of A Z values between the proposed method and conventional vascularity index method using z test was 0.04.

show abstract

Section: Discussionmentioning

confidence: 99%

Diagnosis of Solid Breast Tumors Using Vessel Analysis in Three-Dimensional Power Doppler Ultrasound Images

et al. 2013

View full text Add to dashboard Cite

show abstract

“…In the last two decades, several experimental studies have demonstrated that quantitative methods (based on tracer kinetics modelling) can be more specific in distinguishing benign from malignant breast disease, because of the capability to derive parameters strictly related to tissue microvasculature without any operator dependency [19,[20][21][22][23][24][28][29][30][31][32][33][34][35][36][37][38][39][40][41]. However, as there is not yet sufficient standardisation of quantitative methods, semi-quantitative approaches have been used because they could represent a compromise between qualitative and quantitative approaches.…”

Section: Discussionmentioning

confidence: 99%

Can semi-quantitative evaluation of uncertain (type II) time-intensity curves improve diagnosis in breast DCE-MRI?

Fusco¹,

Filice²,

Granata³

et al. 2013

JBiSE

View full text Add to dashboard Cite

Objective/Background: Qualitative assessment of uncertain (type II) time-intensity curves (TICs) in breast DCE-MRI is problematic and operator dependent. The aim of this work is to evaluate if a semi-quantitative assessment of uncertain TICs could improve overall diagnostic performance. Methods: In this study 49 lesions from 44 patients were retrospectively analysed. Per each lesion one region-of-interest (ROI)-averaged TIC was qualitatively evaluated by two radiologists in consensus: all the ROIs resulted in type II (uncertain) TIC. The same TICs were semi-quantitatively re-classified on the basis of the difference between the signal intensities of the last-time-point and of the peak: this difference was classified according to two different cut-off ranges (±5% and ±3%). All patients were cytological or histological biopsy proven. Fisher test and McNemar test were performed to evaluate if results were statistically significant (p < 0.05). Results: Using ±5% cut-off 16 TICs were reclassified as type III and 12 as type I while 21 were reclassified again as type II. Using ±3% 22 TICs were reclassified as type III and 16 as type I while 11 were reclassified again as type II. The semi-quantitative classification was compared to the histologicalcytological results: the sensitivity, specificity, positive and negative predictive values obtained with ±3% were 77%, 91%, 91% and 78% respectively while using ±5% were 58%, 96%, 94% and 68% respectively. Using the ±5% cut-off 26/28 (93%) TICs were correctly reclassified while using the ±3% cut-off 34/38 (90%) TICs were correctly reclassified (p < 0.05). Conclusions: Semi-quantitative methods in kinetic curve assessment on DCE-MRI could improve classification of qualitatively uncertain TICs, leading to a more accurate classification of suspicious breast lesions.

show abstract

“…41,42 FCM is a data clustering scheme similar to k-means in that data are clustered around a prescribed number of centroids. However, unlike k-means, the resulting class membership is a fuzzy membership to each cluster.…”

Section: Vic1 Fuzzy C-meansmentioning

confidence: 99%

Spectral embedding based active contour (SEAC) for lesion segmentation on breast dynamic contrast enhanced magnetic resonance imaging

Agner

Madabhushi

2013

Medical Physics

View full text Add to dashboard Cite

Purpose: Segmentation of breast lesions on dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) is the first step in lesion diagnosis in a computer-aided diagnosis framework. Because manual segmentation of such lesions is both time consuming and highly susceptible to human error and issues of reproducibility, an automated lesion segmentation method is highly desirable. Traditional automated image segmentation methods such as boundary-based active contour (AC) models require a strong gradient at the lesion boundary. Even when region-based terms are introduced to an AC model, grayscale image intensities often do not allow for clear definition of foreground and background region statistics. Thus, there is a need to find alternative image representations that might provide (1) strong gradients at the margin of the object of interest (OOI); and (2) larger separation between intensity distributions and region statistics for the foreground and background, which are necessary to halt evolution of the AC model upon reaching the border of the OOI. Methods: In this paper, the authors introduce a spectral embedding (SE) based AC (SEAC) for lesion segmentation on breast DCE-MRI. SE, a nonlinear dimensionality reduction scheme, is applied to the DCE time series in a voxelwise fashion to reduce several time point images to a single parametric image where every voxel is characterized by the three dominant eigenvectors. This parametric eigenvector image (PrEIm) representation allows for better capture of image region statistics and stronger gradients for use with a hybrid AC model, which is driven by both boundary and region information. They compare SEAC to ACs that employ fuzzy c-means (FCM) and principal component analysis (PCA) as alternative image representations. Segmentation performance was evaluated by boundary and region metrics as well as comparing lesion classification using morphological features from SEAC, PCA+AC, and FCM+AC. Results: On a cohort of 50 breast DCE-MRI studies, PrEIm yielded overall better region and boundary-based statistics compared to the original DCE-MR image, FCM, and PCA based image representations. Additionally, SEAC outperformed a hybrid AC applied to both PCA and FCM image representations. Mean dice similarity coefficient (DSC) for SEAC was significantly better (DSC = 0.74 ± 0.21) than FCM+AC (DSC = 0.50 ± 0.32) and similar to PCA+AC (DSC = 0.73 ± 0.22). Boundary-based metrics of mean absolute difference and Hausdorff distance followed the same trends. Of the automated segmentation methods, breast lesion classification based on morphologic features derived from SEAC segmentation using a support vector machine classifier also performed better (AUC = 0.67 ± 0.05; p < 0.05) than FCM+AC (AUC = 0.50 ± 0.07), and PCA+AC (AUC = 0.49 ± 0.07). Conclusions: In this work, we presented SEAC, an accurate, general purpose AC segmentation tool that could be applied to any imaging domain that employs time series data. SE allows for projection of time series data into a PrEIm representation so tha...

show abstract

Cancerous Breast Lesions on Dynamic Contrast-enhanced MR Images: Computerized Characterization for Image-based Prognostic Markers

Cited by 178 publications

References 52 publications

Diagnosis of Solid Breast Tumors Using Vessel Analysis in Three-Dimensional Power Doppler Ultrasound Images

Diagnosis of Solid Breast Tumors Using Vessel Analysis in Three-Dimensional Power Doppler Ultrasound Images

Can semi-quantitative evaluation of uncertain (type II) time-intensity curves improve diagnosis in breast DCE-MRI?

Spectral embedding based active contour (SEAC) for lesion segmentation on breast dynamic contrast enhanced magnetic resonance imaging

Contact Info

Product

Resources

About