No abstract

We developed machine learning methods to identify fibrolipidic and fibrocalcific A-lines in intravascular optical coherence tomography (IVOCT) images using a comprehensive set of handcrafted features. We incorporated features developed in previous studies (e.g., optical attenuation and A-line peaks). In addition, we included vascular lumen morphology and three-dimensional (3-D) digital edge and texture features. Classification methods were developed using expansive datasets (∼7000 images), consisting of both clinical in-vivo images and an ex-vivo dataset, which was validated using 3-D cryo-imaging/histology. Conditional random field was used to perform 3-D classification noise cleaning of classification results. We tested various multiclass approaches, classifiers, and feature selection schemes and found that a three-class support vector machine with minimal-redundancy-maximal-relevance feature selection gave the best performance. We found that inclusion of our morphological and 3-D features improved overall classification accuracy. On a held-out test set consisting of >1700 images, we obtained an overall accuracy of 81.58%, with the following (sensitivity/ specificity) for each class: other (81.43/89.59), fibrolipidic (94.48/87.32), and fibrocalcific (74.82/95.28). The en-face views of classification results showed that automated classification easily captured the preponderance of a disease segment (e.g., a calcified segment had large regions of fibrocalcific classifications). Finally, we demonstrated proof-of-concept for streamlining A-line classification output with existing fibrolipidic and fibrocalcific boundary segmentation methods, to enable fully automated plaque quantification. The results suggest that our classification approach is a viable step toward fully automated IVOCT plaque classification and segmentation for live-time treatment planning and for offline assessment of drug and biologic therapeutics.

No abstract

In this work, we clarified the role of acquisition parameters and quantification methods in myocardial blood flow (MBF) estimability for myocardial perfusion imaging using CT (MPI-CT). We used a physiologic model with a CT simulator to generate time-attenuation curves across a range of imaging conditions, i.e. tube current-time product, imaging duration, and temporal sampling, and physiologic conditions, i.e. MBF and arterial input function width. We assessed MBF estimability by precision (interquartile range of MBF estimates) and bias (difference between median MBF estimate and reference MBF) for multiple quantification methods. Methods included: six existing model-based deconvolution models, such as the plug-flow tissue uptake model (PTU), Fermi function model, and single-compartment model (SCM); two proposed robust physiologic models (RPM1, RPM2); model-independent singular value decomposition with Tikhonov regularization determined by the L-curve criterion (LSVD); and maximum upslope (MUP). Simulations show that MBF estimability is most affected by changes in imaging duration for model-based methods and by changes in tube current-time product and sampling interval for model-independent methods. Models with three parameters, i.e. RPM1, RPM2, and SCM, gave least biased and most precise MBF estimates. The average relative bias (precision) for RPM1, RPM2, and SCM was  ⩽11% (⩽10%) and the models produced high-quality MBF maps in CT simulated phantom data as well as in a porcine model of coronary artery stenosis. In terms of precision, the methods ranked best-to-worst are: RPM1 > RPM2 > Fermi > SCM > LSVD > MUP [Formula: see text] other methods. In terms of bias, the models ranked best-to-worst are: SCM > RPM2 > RPM1 > PTU > LSVD [Formula: see text] other methods. Models with four or more parameters, particularly five-parameter models, had very poor precision (as much as 310% uncertainty) and/or significant bias (as much as 493%) and were sensitive to parameter initialization, thus suggesting the presence of multiple local minima. For improved estimates of MBF from MPI-CT, it is recommended to use reduced models that incorporate prior knowledge of physiology and contrast agent uptake, such as the proposed RPM1 and RPM2 models.

No abstract

No abstract

No abstract

Myocardial CT perfusion (CTP) imaging is an application that should greatly benefit from spectral CT through the significant reduction of beam hardening (BH) artifacts using mono-energetic (monoE) image reconstructions. We used a prototype spectral detector CT (SDCT) scanner (Philips Healthcare) and developed advanced processing tools (registration, segmentation, and deconvolution-based flow estimation) for quantitative myocardial CTP in a porcine ischemia model with different degrees of coronary occlusion using a balloon catheter. The occlusion severity was adjusted with fractional flow reserve (FFR) measurements. The SDCT scanner is a single source, dual-layer detector system, which allows simultaneous acquisitions of low and high energy projections, hence enabling accurate projection-based material decomposition and effective reduction of BH-artifacts. In addition, the SDCT scanner eliminates partial scan artifacts with fast (0.27s), full gantry rotation acquisitions. We acquired CTP data under different hemodynamic conditions and reconstructed conventional 120kVp images and projection-based monoenergetic (monoE) images for energies ranging from 55keV-to-120keV. We computed and compared myocardial blood flow (MBF) between different reconstructions. With balloon completely deflated (FFR=1), we compared the mean attenuation in a myocardial region of interest before iodine arrival and at peak iodine enhancement in the left ventricle (LV), and we found that monoE images at 70keV effectively minimized the difference in attenuation, due to BH, to less than 1 HU compared to 14 HU with conventional 120kVp images. Flow maps under baseline condition (FFR=1) were more uniform throughout the myocardial wall at 70keV, whereas with 120kVp data about 12% reduction in blood flow was noticed on BH-hypoattenuated areas compared to other myocardial regions. We compared MBF maps at different keVs under an ischemic condition (FFR < 0.7), and we found that flow-contrast-to-noise-ratio (CNR f) between LAD ischemic and remote healthy territories attains its maximum (2.87 ± 0.7) at 70keV. As energies diverge from 70keV, we