^{1}

^{2}

^{1}

^{2}

^{3}

^{1}

^{2}

^{1}

^{2}

^{*}

The authors have declared that no competing interests exist.

Conceived and designed the experiments: GEF JO. Performed the experiments: AB JO. Analyzed the data: ESM JO. Contributed reagents/materials/analysis tools: JS JO. Wrote the paper: ESM JO. Edited the manuscript: JS.

It is expected that both noise and activity distribution can have impact on the detectability of a myocardial defect in a cardiac PET study. In this work, we performed phantom studies to investigate the detectability of a defect in the myocardium for different noise levels and activity distributions. We evaluated the performance of three reconstruction schemes: Filtered Back-Projection (FBP), Ordinary Poisson Ordered Subset Expectation Maximization (OP–OSEM), and Point Spread Function corrected OSEM (PSF–OSEM). We used the Channelized Hotelling Observer (CHO) for the task of myocardial defect detection. We found that the detectability of a myocardial defect is almost entirely dependent on the noise level and the contrast between the defect and its surroundings.

The utility of ^{13}N-ammonia, ^{15}O-water, and ^{82}Rb as PET perfusion tracers has been well documented in the cardiac PET community ^{18}F-BMS-747158 ^{18}F-fluorodeoxyglucose (FDG) uptake in the myocardium has been well validated as an indicator of myocardial viability

Lesion detection is an important clinical task for medical imaging. In oncology, lesion detectability is critically important for early diagnosis and staging of patients. Typically, lesion detectability pertains to hot lesions (e.g., tumors, inflammation), where the uptake is higher within the lesions as compared to their surrounding background ^{82}Rb-PET Monte Carlo simulation. Other myocardial defect detection results are reported on SPECT imaging by Chen

In this paper, we propose a methodology to study myocardial defect detectability using phantom studies on a PET–CT scanner. We performed cardiac phantom studies to characterize myocardial defect detectability as a function of total number of counts, which is related to noise level, and variable activity distributions. We modeled defect-present and defect-absent studies and used the Channelized Hotelling Observer (CHO)

An anthropomorphic torso phantom (Data Spectrum, Hillsborough, NC) with a cardiac insert was used for all the acquisitions (See ^{18}F data were acquired for the following five data sets:

For all the acquisitions, the phantom was always placed at the same position on the bed of the scanner.

In order to combine ^{18}F-BMS747158 flow agent (see

Three reconstruction schemes were considered: FBP, OP-OSEM, and PSF-OSEM. The image reconstruction was performed using Siemens e7-tools, which incorporated attenuation and scatter corrections using the acquired CT map of the phantom. For both OP-OSEM and PSF-OSEM, we used 2 iterations and 8 subsets unless stated otherwise. No post-reconstruction filtering was applied. All the image reconstruction was performed using 168×168×81 matrix size and 4.07×4.07×2.02 mm voxel size.

The acquisition and processing schemes were assessed on the basis of performance of a model observer in detecting the presence of a defect of known position. The CHO, which has been shown to have a good agreement with human performance

Theoretically, a channel model is used to reduce the dimensionality of the data. In our study, we chose the above system of radially symmetric channels for simplification. This type of CHO reduces the dimensionality of the covariance matrix to the number of channels by the number of channels. For instance, in our case, for the image volume 168×168×81, the covariance matrix size is of 2.3 M×2.3 M. Using the three channel model, the covariance matrix reduces to 3×3×3. This massive reduction in dimensionality of the covariance matrix allows for the estimation problem to be tractable with a reasonable sized data set of images.

Overall,

^{+}-OSEM). The CHO SNRs for both OP-OSEM and PSF^{+}-OSEM are almost the same. PSF^{+}-OSEM was found to yield almost the same noise level in the background region as OP-OSEM. This implies that PSF^{+}-OSEM yields almost the same defect contrast as OP-OSEM. Although PSF modeling is expected to correct partial volume effect (PVE) and improve defect contrast, the improvement is negligible for the defect we used, which has relatively large size. The reason that PSF-OSEM yields higher SNR as compared to OP-OSEM is mostly due to the fact the noise level produced by PSF-OSEM is lower than OP-OSEM at the same iteration number because PSF-OSEM converges more slowly than OP-OSEM.

^{2}) for the least squares linear regression lines are: 0.978, 0.976, and 0.989 for FBP, OP-OSEM, and PSF-OSEM, respectively. The defect detectability increases as the defect/myocardium decreases. The SNR value vanishes as defect/myocardium approaches 1, i.e., defect-absent myocardium. ^{2} coefficients are: 0.926, 0.939, and 0.969 for FBP, OP-OSEM, and PSF-OSEM, respectively. Because we fixed defect/myocardium ratio to be 0.825 for this study, defect/background ratio increases as myocardium/background increases. That results in increased SNRs, which is partially determined by the contrast of the defect relative to its surrounding region, as myocardium/background increases.

The dashed lines were obtained using weighted least squares linear regression.

For all the studies, FBP always yields the lowest CHO SNRs. For the same iteration number and the same number of subsets, PSF-OSEM always yields the higher CHO SNR than OP-OSEM.

Defect detectability was assessed as a function of total number of background counts (noise level), defect/myocardium, myocardium/background, liver/background, and lung/background concentration ratios. As expected, the SNR increases as the noise level decreases. The SNR also increases as the defect/myocardium concentration ratio decreases. The results show that the SNR is relatively insensitive to the liver/background and lung/background concentration ratios. FBP yields the lowest CHO SNRs as compared to iterative reconstruction algorithms. Also, PSF-OSEM yields higher CHO SNRs than OP-OSEM for the same iteration number and same number of subsets. However, PSF-OSEM and OP-OSEM yield almost the same CHO SNR if noise levels are the same. This is mainly due to the fact that the defect size we used was relatively big.

Our phantom study shows that the detection SNR is dominated by the contrast of defect to its surrounding background and the noise level. The study of defect detection SNR as function of total number of coincidence counts can be useful to optimize injection dose and/or imaging time. The studies of defect detection versus various activity distributions in the lungs and liver prove that activity uptake in the liver and lungs will not have a major impact on the detection of a myocardial defect. In summary, this phantom study shows that the detectability of a myocardial defect is dominated by the noise level and the contrast between the defect and its surroundings. Therefore, accurate identification of a myocardial defect can be achieved using PET regardless of activity distribution.

We want to thank Zak Levin at Massachusetts General Hospital for his help with some of MATLAB programs used in the data analysis.