Stability of radiomic features from positron emission tomography images: a phantom study comparing advanced reconstruction algorithms and ordered subset expectation maximization.

In this study, we compared the repeatability and reproducibility of radiomic features obtained from positron emission tomography (PET) images according to the reconstruction algorithm used-advanced reconstruction algorithms, such as HYPER iterative (IT), HYPER deep learning reconstruction (DLR), and HYPER deep progressive reconstruction (DPR), or traditional Ordered Subset Expectation Maximization (OSEM)-to understand the potential variations and implications of using advanced reconstruction techniques in PET-based radiomics. We used a heterogeneous phantom with acrylic spherical beads (4- or 8-mm diameter) filled with 18F. PET images were acquired and reconstructed using OSEM, IT, DLR, and DPR. Original and wavelet radiomic features were calculated using SlicerRadiomics. Radiomic feature repeatability was assessed using the Coefficient of Variance (COV) and intraclass correlation coefficient (ICC), and inter-acquisition time reproducibility was assessed using the concordance correlation coefficient (CCC). For the 4- and 8-mm diameter beads phantom, the proportion of radiomic features with a COV < 10% was equivocal or higher for the advanced reconstruction algorithm than for OSEM. ICC indicated that advanced methods generally outperformed OSEM in repeatability, except for the original features of the 8-mm beads phantom. In the inter-acquisition time reproducibility analysis, the combinations of 3 and 5 min exhibited the highest reproducibility in both phantoms, with IT and DPR showing the highest proportion of radiomic features with CCC > 0.8. Advanced reconstruction methods provided enhanced stability of radiomic features compared with OSEM, suggesting their potential for optimal image reconstruction in PET-based radiomics, offering potential benefits in clinical diagnostics and prognostics.

Verification of the effect of acquisition time for SwiftScan on quantitative bone single-photon emission computed tomography using an anthropomorphic phantom.

BACKGROUND: SwiftScan single-photon emission computed tomography (SPECT) is a recently released scanning technique with data acquired when the detector is stationary and when it moves from one view to the next. The influence of scan time for using SwiftScan on quantitative bone SPECT remains unclear. This study aimed to clarify the effect of the scan time for SwiftScan SPECT on the image quality and quantification of bone SPECT compared to step and shoot mode (SSM) using 99mTc-filled anthropomorphic phantom (SIM2 bone phantom). MATERIALS AND METHODS: Phantom SPECT/computed tomography (CT) images were acquired using Discovery NM/CT 860 (GE Healthcare) with a low-energy high-resolution sensitivity collimator. We used the fixed parameters (subsets 10 and iterations 5) for reconstruction. The coefficient of variation (CV), contrast-to-noise ratio (CNR), full width at half maximum (FWHM), and quantitative value of SwiftScan SPECT and SSM were compared at various acquisition times (5, 7, 17, and 32 min). RESULTS: In the short-time scan (< 7 min), the CV and CNR of SwiftScan SPECT were better than those of SSM, whereas in the longtime scan (> 17 min), the CV and CNR of SwiftScan SPECT were similar to those of SSM. The FWHMs for SwiftScan SPECT (13.6-14.8 mm) and SSM (13.5-14.4 mm) were similar. The mean absolute errors of quantitative values at 5, 7, 17, and 32 min were 38.8, 38.4, 48.8, and 48.1, respectively, for SwiftScan SPECT and 41.8, 40.8%, 47.2, and 49.8, respectively, for SSM. CONCLUSIONS: SwiftScan on quantitative bone SPECT provides improved image quality in the short-time scan with quantification similar to or better than SSM. Therefore, in clinical settings, using SwiftScan SPECT instead of the SSM scan protocol in the short-time scan might provide higher-quality diagnostic images than SSM. Our results could provide vital information on the use of SwiftScan SPECT.

Dopamine transporter single-photon emission computed tomography-derived radiomics signature for detecting Parkinson's disease.

BACKGROUND: We hypothesised that the radiomics signature, which includes texture information of dopamine transporter single-photon emission computed tomography (DAT-SPECT) images for Parkinson's disease (PD), may assist semi-quantitative indices. Herein, we constructed a radiomics signature using DAT-SPECT-derived radiomics features that effectively discriminated PD from healthy individuals and evaluated its classification performance. RESULTS: We analysed 413 cases of both normal control (NC, n = 101) and PD (n = 312) groups from the Parkinson's Progression Markers Initiative database. Data were divided into the training and two test datasets with different SPECT manufacturers. DAT-SPECT images were spatially normalised to the Montreal Neurologic Institute space. We calculated 930 radiomics features, including intensity- and texture-based features in the caudate, putamen, and pallidum volumes of interest. The striatum uptake ratios (SURs) of the caudate, putamen, and pallidum were also calculated as conventional semi-quantification indices. The least absolute shrinkage and selection operator was used for feature selection and construction of the radiomics signature. The four classification models were constructed using a radiomics signature and/or semi-quantitative indicator. Furthermore, we compared the classification performance of the semi-quantitative indicator alone and the combination with the radiomics signature for the classification models. The receiver operating characteristics (ROC) analysis was used to evaluate the classification performance. The classification performance of SURputamen was higher than that of other semi-quantitative indicators. The radiomics signature resulted in a slightly increased area under the ROC curve (AUC) compared to SURputamen in each test dataset. When combined with SURputamen and radiomics signature, all classification models showed slightly higher AUCs than that of SURputamen alone. CONCLUSION: We constructed a DAT-SPECT image-derived radiomics signature. Performance analysis showed that the current radiomics signature would be helpful for the diagnosis of PD and has the potential to provide robust diagnostic performance.

Improvement of classification performance of Parkinson's disease using shape features for machine learning on dopamine transporter single photon emission computed tomography.

OBJECTIVE: To assess the classification performance between Parkinson's disease (PD) and normal control (NC) when semi-quantitative indicators and shape features obtained on dopamine transporter (DAT) single photon emission computed tomography (SPECT) are combined as a feature of machine learning (ML). METHODS: A total of 100 cases of both PD and normal control (NC) from the Parkinson's Progression Markers Initiative database were evaluated. A summed image was generated and regions of interests were set to the left and right striata. Area, equivalent diameter, major axis length, minor axis length, perimeter and circularity were calculated as shape features. Striatum binding ratios (SBRputamen and SBRcaudate) were used as comparison features. The classification performance of the PD and NC groups according to receiver operating characteristic analysis of the shape features was compared in terms of SBRs. Furthermore, we compared the classification performance of ML when shape features or SBRs were used alone and in combination. RESULTS: The shape features (except minor axis length) and SBRs indicated significant differences between the NC and PD groups (p < 0.05). The top five areas under the curves (AUC) were as follows: circularity (0.972), SBRputamen (0.972), major axis length (0.945), SBRcaudate (0.928) and perimeter (0.896). When classification was done using ML, AUC was as follows: circularity and SBRs (0.995), circularity alone (0.990), and SBRs (0.973). The classification performance was significantly improved by combining SBRs and circularity than by SBRs alone (p = 0.018). CONCLUSION: We found that the circularity obtained from DAT-SPECT images could help in distinguishing NC and PD. Furthermore, the classification performance of ML was significantly improved using circularity in SBRs together.

Evaluation of the accuracy of mono-energetic electron and beta-emitting isotope dose-point kernels using particle and heavy ion transport code system: PHITS.

We assessed the accuracy of mono-energetic electron and beta-emitting isotope dose-point kernels (DPKs) calculated using the particle and heavy ion transport code system (PHITS) for patient-specific dosimetry in targeted radionuclide treatment (TRT) and compared our data with published data. All mono-energetic and beta-emitting isotope DPKs calculated using PHITS, both in water and compact bone, were in good agreement with those in literature using other MC codes. PHITS provided reliable mono-energetic electron and beta-emitting isotope scaled DPKs for patient-specific dosimetry.

Assessment of the efficacy of early phase parameters by (123)I-MIBG dynamic imaging for distinguishing Lewy body-related diseases from Parkinson's syndrome.

OBJECTIVE: The aim of this study was to assess the efficacy of early phase washout rate (early WR) and area under the time-activity curve (AUTAC) by (123)I-metaiodobenzylguanidine (MIBG) dynamic chest imaging for distinguishing Lewy body-related diseases (LBRD) from Parkinson's syndrome (PS) and reducing examination time. METHODS: Sixty-two patients with suspected LBRD who underwent (123)I-MIBG dynamic imaging in early phase were retrospectively selected. The early WR and AUTAC were calculated from (123)I-MIBG dynamic data of the heart. We evaluated the relationships between proposed and conventional parameters by using Spearman's rank correlation coefficient. Differences in parameters between LBRD and PS groups were tested for statistical significance using the Mann-Whitney U test. The diagnostic performance of all parameters for distinguishing LBRD from PS was assessed in terms of receiver operating characteristic (ROC) analysis. Additionally, combination diagnostic performance and concordance rate between early phase parameters and late H/M ratio by kappa statistics were also assessed. RESULTS: The early WR and AUTAC showed a positive and negative correlation with conventional parameters. Both the early WR and AUTAC of LBRD group were significantly distinguishable from those of the PS group (p < 0.001). Area under the ROC curve of the early WR (0.98) was greater than that of AUTAC (0.91). The diagnostic performance of combination of the early phase parameters was 93 % sensitivity and 100 % specificity. Moreover, the early phase parameters showed excellent agreement with late H/M ratio (k = 0.93). CONCLUSIONS: The early WR and AUTAC showed high performance for distinguishing LBRD from PS, and the combination diagnosis with early H/M ratio and early WR contribute to improve the diagnostic performance. Thus, these parameters would be useful for reducing the examination time of myocardial (123)I-MIBG scintigraphy to diagnose LBRD.

Effects of ambient-light correction in luminance measurements of liquid-crystal display monitors by use of a telescopic-type luminance meter.

The quality control of liquid-crystal display (LCD) monitors has become one of the important topics for maintaining reliable soft-copy readings in the interpretation of diagnostic images. In this paper, the effects of correction in the luminance measurement of an LCD monitor by use of a telescopic-type luminance meter were investigated. The luminance of the LCD monitor in different ambient-lighting conditions was measured and compared to the results obtained with no ambient lighting (0 lux). The reproducibility of luminance measurements and luminance ratios without a baffled tube was lower than those measured with the baffled tube due to the effect of ambient light. These tendencies were obvious at a relatively low luminance. The correction method by subtraction of the reflected ambient light on the surface of the LCD monitor and the stray light of the telescopic-type luminance meter from the measured luminance was examined. We found that the correction was able to bring the luminance close to that measured with the baffled tube.