This observational study aimed to determine whether individuals with fibromyalgia (FM) exhibit higher levels of neuroinflammation than healthy controls (HCs), as measured with positron emission tomography using [¹⁸F]DPA-714, a second-generation radioligand for the translocator protein (TSPO). Fifteen women with FM and 10 HCs underwent neuroimaging. Distribution volume (V_T) was calculated for in 28 regions of interest (ROIs) using Logan graphical analysis and compared between groups using multiple linear regressions. Group (FM vs HC) was the main predictor of interest and TSPO binding status (high- vs mixed-affinity) was added as a covariate. The FM group had higher V_T in the right postcentral gyrus (b = 0.477, P = 0.033), right occipital gray matter (GM; b = 0.438, P = 0.039), and the right temporal GM (b = 0.466, P = 0.042). The FM group also had lower V_T than HCs in the left isthmus of the cingulate gyrus (b = −0.553, P = 0.014). In the subgroup of high-affinity binders, the FM group had higher V_T in the bilateral precuneus, postcentral gyrus, parietal GM, occipital GM, and supramarginal gyrus. Group differences in the right parietal GM were associated with decreased quality of life, higher pain severity and interference, and cognitive problems. In support of our hypothesis, we found increased radioligand binding (V_T) in the FM group compared with HCs in several brain regions regardless of participants' TSPO binding status. The ROIs overlapped with prior reports of increased TSPO binding in FM. Overall, increasing evidence supports the hypothesis that FM involves microglia-mediated neuroinflammation in the brain.

In this study, we modified the previously proposed X2CT-GAN to build a 2Dto3D-GAN of the spine. This study also incorporated the radiologist’s perspective in the adjustment of input signals to prove the feasibility of the automatic production of three-dimensional (3D) structures of the spine from simulated bi-planar two-dimensional (2D) X-ray images. Data from 1012 computed tomography (CT) studies of 984 patients were retrospectively collected. We tested this model under different dataset sizes (333, 666, and 1012) with different bone signal conditions to observe the training performance. A 10-fold cross-validation and five metrics—Dice similarity coefficient (DSC) value, Jaccard similarity coefficient (JSC), overlap volume (OV), and structural similarity index (SSIM)—were applied for model evaluation. The optimal mean values for DSC, JSC, OV, SSIM_anteroposterior (AP), and SSIM_Lateral (Lat) were 0.8192, 0.6984, 0.8624, 0.9261, and 0.9242, respectively. There was a significant improvement in the training performance under empirically enhanced bone signal conditions and with increasing training dataset sizes. These results demonstrate the potential of the clinical implantation of GAN for automatic production of 3D spine images from 2D images. This prototype model can serve as a foundation in future studies applying transfer learning for the development of advanced medical diagnostic techniques.

The unidentified presence of uterine smooth muscle malignancies poses a tremendous risk in women planning surgery for presumed benign leiomyomas. We sought to investigate whether preoperative FDG PET may be useful to identify leiomyosarcomas (LMS) and smooth muscle tumors of uncertain malignant potential (STUMP). Methods. We investigated patients with rapidly growing uterine masses which were suspected of being malignant on ultrasound or MRI. Among the 21 patients who underwent FDG PET, we identified 7 LMS, 1 STUMP, and 13 leiomyomas. PET-derived parameters and FDG uptake patterns were analyzed retrospectively. Results. The SUV_max values of LMS/STUMP (range: 3.7–11.8) were significantly higher than those observed in leiomyomas (range: 2.0–9.4; P=0.003) despite a significant overlap. The metabolic tumor/necrosis ratio was significantly higher in LMS/STUMP than in leiomyomas (P<0.001), with no significant intergroup overlaps. All LMS/STUMP revealed a characteristic pattern of FDG uptake, identifying a specific “hollow ball” sign (corresponding to areas of coagulative tumor necrosis). In contrast, this sign was invariably absent in patients with leiomyomas. Conclusion. The characteristic FDG uptake pattern instead of SUV on PET images allows identifying LMS/STUMP in patients with rapidly growing uterine masses, avoiding the deleterious consequences of regular surgery for presumed benign leiomyomas.

There is a growing interest in using ¹⁸F-DPA-714 PET to study neuroinflammation and microglial activation through imaging the 18-kDa translocator protein (TSPO). Although quantification of ¹⁸F-DPA-714 binding can be achieved through kinetic modeling analysis with an arterial input function (AIF) measured with blood sampling procedures, the invasiveness of such procedures has been an obstacle for wide application. To address these challenges, we developed an image-derived input function (IDIF) that noninvasively estimates the arterial input function from the images acquired for ¹⁸F-DPA-714 quantification. Methods: The method entails three fully automatic steps to extract the IDIF, including a segmentation of voxels with highest likelihood of being the arterial blood over the carotid artery, a model-based matrix factorization to extract the arterial blood signal, and a scaling optimization procedure to scale the extracted arterial blood signal into the activity concentration unit. Two cohorts of human subjects were used to evaluate the extracted IDIF. In the first cohort of five subjects, arterial blood sampling was performed, and the calculated IDIF was validated against the measured AIF through the comparison of distribution volumes from AIF (V_T,AIF) and IDIF (V_T,IDIF). In the second cohort, PET studies from twenty-eight healthy controls without arterial blood sampling were used to compare V_T,IDIF with V_T,REF measured using a reference region-based analysis to evaluate whether it can distinguish high-affinity (HAB) and mixed-affinity (MAB) binders. Results: In the arterial blood-sampling cohort, V_T derived from IDIF was found to be an accurate surrogate of the V_T from AIF. The bias of V_{T, IDIF} was −5.8 ± 7.8% when compared to V_T,AIF, and the linear mixed effect model showed a high correlation between V_T,AIF and V_{T, IDIF} (p < 0.001). In the nonblood-sampling cohort, V_{T, IDIF} showed a significance difference between the HAB and MAB healthy controls. V_{T, IDIF} and standard uptake values (SUV) showed superior results in distinguishing HAB from MAB subjects than V_T,REF. Conclusions: A novel IDIF method for ¹⁸F-DPA-714 PET quantification was developed and evaluated in this study. This IDIF provides a noninvasive alternative measurement of V_T to quantify the TSPO binding of ¹⁸F-DPA-714 in the human brain through dynamic PET scans.

We aimed to evaluate whether the hyperemic myocardial blood flow (MBF) can be estimated using cadmium zinc telluride (CZT)-based single-photon emission computed tomography (SPECT) cameras with a single, rapid rest/stress dynamic scan. Dynamic contrast-enhanced (DCE) cardiac magnetic resonance imaging (MRI) was used as a reference modality for flow measurement. The proposed protocol included both the rest and stress acquisitions within a 24-min scan. Patients were first injected with 99mTc-Sestamibi at the resting state. Sixty minutes after the first injection, the subject was positioned via scintigraphy, after which the list-mode data acquisition was initiated and continued for 24 minutes. Five minutes after data acquisition was initiated, a stressed state was induced via dipyridamole infusion, after which a second dose of 99mTc-Sestamibi was injected. Dynamic SPECT images were reconstructed for all subjects, who also underwent T1-weighted cardiac DCE-MRI performed on days other than those of the SPECT studies. MBF values were estimated for the rest and stress MRI studies, and for the stress portion of the SPECT study. The SPECT-measured hyperemic MBF was compared with the MR-measured hyperemic MBF and coronary flow reserve (CFR), based on the regions of interest. A total of 30 subjects were included in this study. The hyperemic MBF estimated from SPECT showed a strong correlation with the MR-measured hyperemic MBF (r² = 0.76) and a modest correlation with the MR-measured CFR (r² = 0.56). Using MR-measured CFR <1.3 as a cutoff for coronary stenosis, we found that the SPECT-measured hyperemic MBF served as a useful clinical index with 94% sensitivity, 90% specificity, and 93% accuracy. Hyperemic MBF can be measured with a rapid, single-scan rest/stress study with CZT-based SPECT cameras.

Objectives: Predicting intensive care unit (ICU) admissions during pandemic outbreaks such as COVID-19 can assist clinicians in early intervention and the better allocation of medical resources. Artificial intelligence (AI) tools are promising for this task, but their development can be hindered by the limited availability of training data. This study aims to explore model development strategies in data-limited scenarios, specifically in detecting the need for ICU admission using chest X-rays of COVID-19 patients by leveraging transfer learning and data extension to improve model performance. Methods: We explored convolutional neural networks (CNNs) pre-trained on either natural images or chest X-rays, fine-tuning them on a relatively limited dataset (COVID-19-NY-SBU, n = 899) of lung-segmented X-ray images for ICU admission classification. To further address data scarcity, we introduced a dataset extension strategy that integrates an additional dataset (MIDRC-RICORD-1c, n = 417) with different but clinically relevant labels. Results: The TorchX-SBU-RSNA and ELIXR-SBU-RSNA models, leveraging X-ray-pre-trained models with our training data extension approach, enhanced ICU admission classification performance from a baseline AUC of 0.66 (56% sensitivity and 68% specificity) to AUCs of 0.77–0.78 (58–62% sensitivity and 78–80% specificity). The gradient-weighted class activation mapping (Grad-CAM) analysis demonstrated that the TorchX-SBU-RSNA model focused more precisely on the relevant lung regions and reduced the distractions from non-relevant areas compared to the natural image-pre-trained model without data expansion. Conclusions: This study demonstrates the benefits of medical image-specific pre-training and strategic dataset expansion in enhancing the model performance of imaging AI models. Moreover, this approach demonstrates the potential of using diverse but limited data sources to alleviate the limitations of model development for medical imaging AI. The developed AI models and training strategies may facilitate more effective and efficient patient management and resource allocation in future outbreaks of infectious respiratory diseases.