Limits...
Breast DCE-MRI Kinetic Heterogeneity Tumor Markers: Preliminary Associations With Neoadjuvant Chemotherapy Response.

Ashraf A, Gaonkar B, Mies C, DeMichele A, Rosen M, Davatzikos C, Kontos D - Transl Oncol (2015)

Bottom Line: We propose a set of kinetic statistic descriptors and present preliminary results showing the discriminatory capacity of the proposed descriptors for predicting complete and non-complete responders as assessed from pre-treatment imaging exams.We compare the predictive value of our features against commonly used MRI features including kinetics of the characteristic kinetic curve (CKC), maximum peak enhancement (MPE), hotspot signal enhancement ratio (SER), and longest tumor diameter that give lower AUCs of 0.71, 0.66, 0.64, and 0.54, respectively.Our proposed kinetic statistics thus outperform the conventional kinetic descriptors as well as the classifier using a combination of all the conventional descriptors (i.e., CKC, MPE, SER, and longest diameter), which gives an AUC of 0.74.

View Article: PubMed Central - PubMed

Affiliation: Department of Radiology, University of Pennsylvania School of Medicine, Philadelphia, PA, USA. Electronic address: ahmed.bilal@alumni.cmu.edu.

No MeSH data available.


Related in: MedlinePlus

(A) Illustration of basic kinetic features for a single pixel. (B) Pixel-wise maps.
© Copyright Policy - CC BY-NC-ND
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4487265&req=5

f0005: (A) Illustration of basic kinetic features for a single pixel. (B) Pixel-wise maps.

Mentions: A common way to quantify the enhancement pattern is to compute the relative enhancement as compared to the pre-contrast image [44,43]. By computing the relative enhancement on a pixel-by-pixel basis, we can construct pixel-wise maps of the relative contrast enhancement as follows:(1)Euvt=Iuvt−Iuvt0Iuvt0where I(u, v, t) represents the intensity of pixel (u, v) captured at time t and t0 is the pre-contrast time instant. For a particular pixel, the relative enhancement plotted as a function of time is defined as the kinetic curve [43]. In the literature (e.g., [44,43]), a number of basic features can be computed from this kinetic curve as illustrated in Figure 1A. On the basis of these features, we can derive a rich kinetic feature set by computing the pixel-wise map for each feature as follows:•


Breast DCE-MRI Kinetic Heterogeneity Tumor Markers: Preliminary Associations With Neoadjuvant Chemotherapy Response.

Ashraf A, Gaonkar B, Mies C, DeMichele A, Rosen M, Davatzikos C, Kontos D - Transl Oncol (2015)

(A) Illustration of basic kinetic features for a single pixel. (B) Pixel-wise maps.
© Copyright Policy - CC BY-NC-ND
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4487265&req=5

f0005: (A) Illustration of basic kinetic features for a single pixel. (B) Pixel-wise maps.
Mentions: A common way to quantify the enhancement pattern is to compute the relative enhancement as compared to the pre-contrast image [44,43]. By computing the relative enhancement on a pixel-by-pixel basis, we can construct pixel-wise maps of the relative contrast enhancement as follows:(1)Euvt=Iuvt−Iuvt0Iuvt0where I(u, v, t) represents the intensity of pixel (u, v) captured at time t and t0 is the pre-contrast time instant. For a particular pixel, the relative enhancement plotted as a function of time is defined as the kinetic curve [43]. In the literature (e.g., [44,43]), a number of basic features can be computed from this kinetic curve as illustrated in Figure 1A. On the basis of these features, we can derive a rich kinetic feature set by computing the pixel-wise map for each feature as follows:•

Bottom Line: We propose a set of kinetic statistic descriptors and present preliminary results showing the discriminatory capacity of the proposed descriptors for predicting complete and non-complete responders as assessed from pre-treatment imaging exams.We compare the predictive value of our features against commonly used MRI features including kinetics of the characteristic kinetic curve (CKC), maximum peak enhancement (MPE), hotspot signal enhancement ratio (SER), and longest tumor diameter that give lower AUCs of 0.71, 0.66, 0.64, and 0.54, respectively.Our proposed kinetic statistics thus outperform the conventional kinetic descriptors as well as the classifier using a combination of all the conventional descriptors (i.e., CKC, MPE, SER, and longest diameter), which gives an AUC of 0.74.

View Article: PubMed Central - PubMed

Affiliation: Department of Radiology, University of Pennsylvania School of Medicine, Philadelphia, PA, USA. Electronic address: ahmed.bilal@alumni.cmu.edu.

No MeSH data available.


Related in: MedlinePlus