Effects of Respiratory Motion on Y-90 PET Dosimetry for SIRT

Respiratory motion degrades the quantification accuracy of PET imaging by blurring the radioactivity distribution. In the case of post-SIRT PET-CT verification imaging, respiratory motion can lead to inaccuracies in dosimetric measures. Using an anthropomorphic phantom filled with 90Y at a range of clinically relevant activities, together with a respiratory motion platform performing realistic motions (10–15 mm amplitude), we assessed the impact of respiratory motion on PET-derived post-SIRT dosimetry. Two PET scanners at two sites were included in the assessment. The phantom experiments showed that device-driven quiescent period respiratory motion correction improved the accuracy of the quantification with statistically significant increases in both the mean contrast recovery (+5%, p = 0.003) and the threshold activities corresponding to the dose to 80% of the volume of interest (+6%, p < 0.001). Although quiescent period gating also reduces the number of counts and hence increases the noise in the PET image, its use is encouraged where accurate quantification of the above metrics is desired.

Spleen Perfusion as an Index of Gender Impact on Sympathetic Nervous System Response to Exercise

Objective: Sympathetic nervous system (SNS) reaction to exercise is gender dependent. Nevertheless, clinically applicable methods to identify this difference are still missing. An organ largely sensitive to SNS is the spleen whose response to exercise can be easily evaluated, being included in the field of view of myocardial perfusion imaging (MPI). Here, we aimed to verify whether gender interferes with the spleen perfusion and its response to exercise.Methods: For this purpose, we evaluated 286 original scans of consecutive patients submitted to MPI in the course of 2019. Our standard procedure implies a single-day stress-rest sequence with a gap of ≥2 h between the administrations of 180 and 500 MBq of 99mTc-Sestamibi, respectively. Imaging is performed 30 min after radiotracer administration, with scan duration set at 25 and 35 s per view, respectively. Non-gated scans were reconstructed with the filtered back-projection method. A volume of interest was drawn on the spleen and heart to estimate the dose-normalized average counting rate that was expressed in normalized counts per seconds (NCPS).Results: In all subjects submitted to exercise MPI (n = 228), NCPS were higher during stress than at rest (3.52 ± 2.03 vs. 2.78 ± 2.07, respectively; p &lt; 0.01). This effect was not detected in the 58 patients submitted to dipyridamole-stress. The response to exercise selectively involved the spleen, since NCPS in heart were unchanged irrespective of the used stressor. This same response was dependent upon gender, indeed spleen NCPS during stress were significantly higher in the 75 women than in the 153 men (3.86 ± 1.8 vs. 3.23 ± 1.6, respectively, p &lt; 0.01). Again, this variance was not reproduced by heart. Finally, spleen NCPS were lower in the 173 patients with myocardial reversible perfusion defects (summed difference score ≥3) than in the remaining 55, despite similar values of rate pressure product at tracer injection.Conclusion: Thus, exercise interference on spleen perfusion can be detected during MPI. This effect is dependent upon gender and ischemia confirming the high sensitivity of this organ to SNS activation.

Prediction of Prostate Cancer Disease Aggressiveness Using Bi-Parametric Mri Radiomics

Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results. Thus, the main goal of this work was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method and machine learning algorithm. On a cohort of 281 lesions from 183 patients, it was found that (1) radiomic features extracted from the lesion volume of interest were less stable to segmentation than the equivalent extraction from the whole gland volume of interest; and (2) radiomic features extracted from the whole gland volume of interest produced higher performance and less overfitted classifiers than radiomic features extracted from the lesions volumes of interest. This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion.

Accurate Tumor Delineation vs. Rough Volume of Interest Analysis for 18F-FDG PET/CT Radiomics-Based Prognostic Modeling inNon-Small Cell Lung Cancer

BackgroundThe aim of this work was to investigate the ability of building prognostic models in non-small cell lung cancer (NSCLC) using radiomic features from positron emission tomography and computed tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose (18F-FDG PET/CT) images based on a “rough” volume of interest (VOI) containing the tumor instead of its accurate delineation, which is a significant time-consuming bottleneck of radiomics analyses.MethodsA cohort of 138 patients with stage II–III NSCLC treated with radiochemotherapy recruited retrospectively (n = 87) and prospectively (n = 51) was used. Two approaches were compared: firstly, the radiomic features were extracted from the delineated primary tumor volumes in both PET (using the automated fuzzy locally adaptive Bayesian, FLAB) and CT (using a semi-automated approach with 3D Slicer™) components. Both delineations were carried out within previously manually defined “rough” VOIs containing the tumor and the surrounding tissues, which were exploited for the second approach: the same features were extracted from this alternative VOI. Both sets for features were then combined with the clinical variables and processed through the same machine learning (ML) pipelines using the retrospectively recruited patients as the training set and the prospectively recruited patients as the testing set. Logistic regression (LR), random forest (RF), and support vector machine (SVM), as well as their consensus through averaging the output probabilities, were considered for feature selection and modeling for overall survival (OS) prediction as a binary classification (either median OS or 6 months OS). The resulting models were compared in terms of balanced accuracy, sensitivity, and specificity.ResultsOverall, better performance was achieved using the features from delineated tumor volumes. This was observed consistently across ML algorithms and for the two clinical endpoints. However, the loss of performance was not significant, especially when a consensus of the three ML algorithms was considered (0.89 vs. 0.88 and 0.78 vs. 0.77).ConclusionOur findings suggest that it is feasible to achieve similar levels of prognostic accuracy in radiomics-based modeling by relying on a faster and easier VOI definition, skipping a time-consuming tumor delineation step, thus facilitating automation of the whole radiomics workflow. The associated cost is a loss of performance in the resulting models, although this loss can be greatly mitigated when a consensus of several models is relied upon.

Decreased Thalamic Monoamine Availability in Drug-Induced Parkinsonism

Drug-induced parkinsonism (DIP) is caused by a dopamine receptor blockade and is a major cause of misleading diagnosis of Parkinson’s disease (PD). Striatal dopamine activity has been investigated widely in DIP; however, most studies with dopamine transporter imaging have focused on the clinical characteristics and prognosis. This study investigated differences in striatal subregional monoamine availability among patients with DIP, normal controls, and patients with early PD. Thirty-five DIP patients, the same number of age-matched PD patients, and 46 healthy controls were selected for this study. Parkinsonian motor status was examined. Brain magnetic resonance imaging and positron emission tomography with 18F-N-(3-fluoropropyl)-2beta-carbon ethoxy-3beta-(4-iodophenyl) nortropane were performed, and the regional standardized uptake values were analyzed with a volume-of-interest template and compared among the groups. Females were more predominant in the DIP group than in the PD group. Parkinsonian motor symptoms were similar in the DIP and PD groups. Monoamine availability in the thalamus of the DIP group was lower than that of the normal controls and similar to that of the PD group. In other subregions (putamen, globus pallidus, and ventral striatum), monoamine availability in the DIP group and normal controls did not differ and was higher than that in the PD group. These findings suggest that low monoamine availability in the thalamus could be an imaging biomarker of DIP.

The Reproducibility of Deep Learning-Based Segmentation of the Prostate Gland and Zones on T2-Weighted MR Images

Volume of interest segmentation is an essential step in computer-aided detection and diagnosis (CAD) systems. Deep learning (DL)-based methods provide good performance for prostate segmentation, but little is known about the reproducibility of these methods. In this work, an in-house collected dataset from 244 patients was used to investigate the intra-patient reproducibility of 14 shape features for DL-based segmentation methods of the whole prostate gland (WP), peripheral zone (PZ), and the remaining prostate zones (non-PZ) on T2-weighted (T2W) magnetic resonance (MR) images compared to manual segmentations. The DL-based segmentation was performed using three different convolutional neural networks (CNNs): V-Net, nnU-Net-2D, and nnU-Net-3D. The two-way random, single score intra-class correlation coefficient (ICC) was used to measure the inter-scan reproducibility of each feature for each CNN and the manual segmentation. We found that the reproducibility of the investigated methods is comparable to manual for all CNNs (14/14 features), except for V-Net in PZ (7/14 features). The ICC score for segmentation volume was found to be 0.888, 0.607, 0.819, and 0.903 in PZ; 0.988, 0.967, 0.986, and 0.983 in non-PZ; 0.982, 0.975, 0.973, and 0.984 in WP for manual, V-Net, nnU-Net-2D, and nnU-Net-3D, respectively. The results of this work show the feasibility of embedding DL-based segmentation in CAD systems, based on multiple T2W MR scans of the prostate, which is an important step towards the clinical implementation.

Improved precision of noise estimation in CT with a volume-based approach

Assessment of image noise is a relevant issue in computed tomography (CT). Noise is routinely measured by the standard deviation of density values (Hounsfield units, HU) within a circular region of interest (ROI). We explored the effect of a spherical volume of interest (VOI) on noise measurements. Forty-nine chronic obstructive pulmonary disease patients underwent CT with clinical protocol (regular dose [RD], volumetric CT dose index [CTDIvol] 3.04 mGy, 64-slice unit), and ultra-low dose (ULD) protocol (median CTDIvol 0.38 mGy, dual-source unit). Noise was measured in 27 1-cm2 ROIs and 27 0.75-cm3 VOIs inside the trachea. Median true noise was 21 HU (range 17-29) for RD-CT and 33 HU (26-39) for ULD-CT. The VOI approach resulted in a lower mean distance between limits of agreement compared to ROI: 5.9 versus 10.0 HU for RD-CT (−40%); 4.7 versus 9.9 HU for ULD-CT (−53%). Mean systematic bias barely changed: −1.6 versus −0.9HU for RD-CT; 0.0 to 0.4HU for ULD-CT. The average measurement time was 6.8 s (ROI) versus 9.7 (VOI), independent of dose level. For chest CT, measuring noise with a VOI-based instead of a ROI-based approach reduces variability by 40-53%, without a relevant effect on systematic bias and measurement time.

Machine learning-based CT radiomics model distinguishes COVID-19 from non-COVID-19 pneumonia

Background To develop a machine learning-based CT radiomics model is critical for the accurate diagnosis of the rapid spreading coronavirus disease 2019 (COVID-19). Methods In this retrospective study, a total of 326 chest CT exams from 134 patients (63 confirmed COVID-19 patients and 71 non-COVID-19 patients) were collected from January 20 to February 8, 2020. A semi-automatic segmentation procedure was used to delineate the volume of interest (VOI), and radiomic features were extracted. The Support Vector Machine (SVM) model was built on the combination of 4 groups of features, including radiomic features, traditional radiological features, quantifying features, and clinical features. By repeating cross-validation procedure, the performance on the time-independent testing cohort was evaluated by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Results For the SVM model built on the combination of 4 groups of features (integrated model), the per-exam AUC was 0.925 (95% CI 0.856 to 0.994) for differentiating COVID-19 on the testing cohort, and the sensitivity and specificity were 0.816 (95% CI 0.651 to 0.917) and 0.923 (95% CI 0.621 to 0.996), respectively. As for the SVM models built on radiomic features, radiological features, quantifying features, and clinical features, individually, the AUC on the testing cohort reached 0.765, 0.818, 0.607, and 0.739, respectively, significantly lower than the integrated model, except for the radiomic model. Conclusion The machine learning-based CT radiomics models may accurately classify COVID-19, helping clinicians and radiologists to identify COVID-19 positive cases.

Effect of Cerebrospinal Fluid Area Mask Correction on 123I-FP-CIT SPECT Images in Idiopathic Normal Pressure Hydrocephalus

Cerebrospinal fluid (CSF) mask correction has been developed to reduce the influence by CSF area dilatation for 123I-FP-CIT accumulation. In this study, we assessed the effect of CSF mask correction on the specific binding ratio (SBR) for 25 patients with idiopathic normal pressure hydrocephalus (iNPH). The SBRs with and without CSF mask correction were calculated, and changes in quantitative values were verified. Additionally, the volume removed from striatal and background (BG) volume of interest (VOI) by the CSF mask correction was calculated, the volumes removed were compared to verify their effect on SBR. Twenty and five patients had low and high SBRs, respectively, after CSF mask correction. The images of 20 and 5 patients with SBRs that were decreased and increased, respectively, by CSF mask correction showed that the volumes removed from the BG region VOI were higher and lower, respectively, than those in the striatal region. In conclusion, the SBR before and after CSF mask correction was associated with the ratio of the volume removed from the striatal and BG VOIs, and the SBR was high or low according to the ratio. The results may indicate that CSF mask correction is effective in patients with iNPH. This study was registered in the UMIN Clinical Trials Registry (UMIN-CTR) as UMIN study ID: UMIN000044826.