Fractional Flow Reserve (FFR), the ratio of arterial pressure distal to a coronary lesion to the proximal pressure, is indicative of its hemodynamic significance. This quantity can be determined from invasive measurements made with a catheter, or by using computational methods incorporating models of the the coronary vasculature. One of the inputs needed by a model-based approach for estimating FFR from Computed Tomography Angiography (CTA) images (denoted FFR-CT) is the geometry of the coronary arteries, which requires segmentation of the coronary lumen. Several algorithms have been proposed for coronary lumen segmentation, including the recent application of machine learning techniques. For evaluating these algorithms or for training machine learning algorithms, manual segmentation of the lumen has been considered as ground truth. However, since there is inter-subject variability in manual segmentation, it would be useful to first assess the extent to which this variability affects the predicted FFR values. In the current study, we evaluated the impact of inter-subject variability in manual segmentation on computed FFR, using datasets with three different manual segmentations provided as part of the Rotterdam Coronary Artery Evaluation Framework. FFR was computed using a coronary blood flow model. Our results indicate that variability in manual segmentations on FFR estimates depend on the FFR value. For FFR ≥ 0.97, variability in manual segmentations does not impact FFR estimates, while, for lower FFR values, the variability in manual segmentations leads to significant variability in FFR. The results of this study indicate that researchers should exercise caution when treating manual segmentations as ground truth for estimating FFR from CTA images.
Positron emission tomography (PET) using uorodeoxyglucose (18F-FDG) is commonly used in the assessment of breast lesions by computing voxel-wise standardized uptake value (SUV) maps. Simple metrics derived from ensemble properties of SUVs within each identified breast lesion are routinely used for disease diagnosis. The maximum SUV within the lesion (SUVmax) is the most popular of these metrics. However these simple metrics are known to be error-prone and are susceptible to image noise. Finding reliable SUV map-based features that correlate to established molecular phenotypes of breast cancer (viz. estrogen receptor (ER), progesterone receptor (PR) and human epidermal growth factor receptor 2 (HER2) expression) will enable non-invasive disease management. This study investigated 36 SUV features based on first and second order statistics, local histograms and texture of segmented lesions to predict ER and PR expression in 51 breast cancer patients. True ER and PR expression was obtained via immunohistochemistry (IHC) of tissue samples from each lesion. A supervised learning, adaptive boosting-support vector machine (AdaBoost-SVM), framework was used to select a subset of features to classify breast lesions into distinct phenotypes. Performance of the trained multi-feature classifier was compared against the baseline single-feature SUVmax classifier using receiver operating characteristic (ROC) curves. Results show that texture features encoding local lesion homogeneity extracted from gray-level co-occurrence matrices are the strongest discriminator of lesion ER expression. In particular, classifiers including these features increased prediction accuracy from 0.75 (baseline) to 0.82 and the area under the ROC curve from 0.64 (baseline) to 0.75.
Robust point matching (RPM) jointly estimates correspondences and non-rigid warps between unstructured
point-clouds. RPM does not, however, utilize information of the topological structure or group memberships of
the data it is matching. In numerous medical imaging applications, each extracted point can be assigned group
membership attributes or labels based on segmentation, partitioning, or clustering operations. For example,
points on the cortical surface of the brain can be grouped according to the four lobes. Estimated warps should
enforce the topological structure of such point-sets, e.g. points belonging to the temporal lobe in the two
point-sets should be mapped onto each other.
We extend the RPM objective function to incorporate group membership labels by including a Label Entropy
(LE) term. LE discourages mappings that transform points within a single group in one point-set onto points
from multiple distinct groups in the other point-set. The resulting Labeled Point Matching (LPM) algorithm
requires a very simple modification to the standard RPM update rules.
We demonstrate the performance of LPM on coronary trees extracted from cardiac CT images. We partitioned
the point sets into coronary sections without a priori anatomical context, yielding potentially disparate labelings
(e.g. [1,2,3] → [a,b,c,d]). LPM simultaneously estimated label correspondences, point correspondences, and a
non-linear warp. Non-matching branches were treated wholly through the standard RPM outlier process akin to
non-matching points. Results show LPM produces warps that are more physically meaningful than RPM alone.
In particular, LPM mitigates unrealistic branch crossings and results in more robust non-rigid warp estimates.
Functional MRI (fMRI) time-series studies are plagued by varying degrees of subject head motion. Faithful head
motion correction is essential to accurately detect brain activation using statistical analyses of these time-series.
Mutual information (MI) based slice-to-volume (SV) registration is used for motion estimation when the rate of
change of head position is large. SV registration accounts for head motion between slice acquisitions by estimating
an independent rigid transformation for each slice in the time-series. Consequently each MI optimization uses
intensity counts from a single time-series slice, making the algorithm susceptible to noise for low complexity endslices
(i.e., slices near the top of the head scans). This work focuses on improving the accuracy of MI-based SV
registration of end-slices by using joint probability density priors derived from registered high complexity centerslices
(i.e., slices near the middle of the head scans). Results show that the use of such priors can significantly
improve SV registration accuracy.