Purpose: Orbital [^99mTc]TcDTPA orbital single-photon emission computed tomography (SPECT)/CT is an important method for assessing inflammatory activity in patients with Graves’ orbitopathy (GO). However, interpreting the results requires substantial physician workload. We aim to propose an automated method called GO-Net to detect inflammatory activity in patients with GO. Materials and methods: GO-Net had two stages: (1) a semantic V-Net segmentation network (SV-Net) that extracts extraocular muscles (EOMs) in orbital CT images and (2) a convolutional neural network (CNN) that uses SPECT/CT images and the segmentation results to classify inflammatory activity. A total of 956 eyes from 478 patients with GO (active: 475; inactive: 481) at Xiangya Hospital of Central South University were investigated. For the segmentation task, five-fold cross-validation with 194 eyes was used for training and internal validation. For the classification task, 80% of the eye data were used for training and internal fivefold cross-validation, and the remaining 20% of the eye data were used for testing. The EOM regions of interest (ROIs) were manually drawn by two readers and reviewed by an experienced physician as ground truth for segmentation GO activity was diagnosed according to clinical activity scores (CASs) and the SPECT/CT images. Furthermore, results are interpreted and visualized using gradient-weighted class activation mapping (Grad-CAM). Results: The GO-Net model combining CT, SPECT, and EOM masks achieved a sensitivity of 84.63%, a specificity of 83.87%, and an area under the receiver operating curve (AUC) of 0.89 (p < 0.01) on the test set for distinguishing active and inactive GO. Compared with the CT-only model, the GO-Net model showed superior diagnostic performance. Moreover, Grad-CAM demonstrated that the GO-Net model placed focus on the GO-active regions. For EOM segmentation, our segmentation model achieved a mean intersection over union (IOU) of 0.82. Conclusion: The proposed Go-Net model accurately detected GO activity and has great potential in the diagnosis of GO.

Objective: To investigate single-photon emission computed tomography/computed tomography (SPECT/CT) for assessing inflammation in the extraocular muscles (EOMs) and predicting the therapeutic efficacy of periocular glucocorticoid therapy (PGT) for Grave's ophthalmopathy (GO).Materials and Methods: A total of 412 eyes from 206 patients with GO referred for ^99mTc-DTPA orbital SPECT/CT were enrolled. Fourteen age- and gender-matched healthy controls (28 eyes) were included. The thickness and uptake ratio (UR) of four EOMs were derived from SPECT/CT. Eighty-six eyes from patients with GO patients received PGT. Changes in SPECT/CT parameters were evaluated between the pre- and post-treatment.Results: 195 eyes and 217 eyes were classified as active and inactive stages by clinical activity score (CAS). Values of the thickness and UR of each EOM, T_max, and U_max were all significantly higher in the active GO than in the inactive GO and controls (p < 0.01). Among the 86 eyes (48 GO patients) included in the efficacy analysis, 56 eyes and 30 eyes were classified as responders and non-responders. Values of thicknesses and UR of each EOM, the maximum thickness (T_max), and the maximum UR (U_max) all dropped following PGT in the responders (p < 0.01). Logistic regression analysis identified the U_max as an independent predictor for the responders (p < 0.01). Moreover, the U_max demonstrated incremental predictive value over clinical characters and CAS, as evidenced by the improved area under the curve (0.85 vs. 0.78) and global chi-square (34.12 vs. 18.1).Conclusion:^99mTc-DTPA SPECT/CT has the potential to assess inflammatory activity by detecting the involvement of EOMs in GO. Pre-treatment UR provides independent and incremental values for the prediction of PGT treatment response.

To explore the performance of ^99mTc-diethylene triaminepentaacetic acid (DTPA) SPECT/CT texture analysis in evaluating the activity of thyroid-associated ophthalmopathy (TAO) . This retrospective study examined 115 TAO patients from a single institution as an internal cohort and 58 TAO patients from another institution as an external validation set. Patients in the internal cohort were randomly divided into training (n = 81) and internal validation sets (n = 34). Radiomics signatures were constructed with the minimal redundancy maximal relevance and least absolute shrinkage and selection operator algorithms in training set. Multivariate logistic regression analysis was used to develop a clinical model and a combined clinical–radiomics model. Diagnostic performance of models was evaluated using receiver operating characteristic curve analysis, calibration curves and decision curve analysis. Compared with CT and SPECT radiomics models, Rad-score_SPECT/CT demonstrated the best performance with areas under the receiver operating characteristic curve of 0.94 and 0.91 in the training and test sets, respectively. The combined clinical-radiomics model exhibited significantly better performance in evaluating TAO activity. Our results demonstrate the validity of a multimodal radiomic model of ^99mTc-DTPA-SPECT/CT to assess TAO activity. The combined clinical-radiomics model exhibited significantly better diagnostic performance than the clinical model.

Background: Sentinel lymph node (SLN) mapping-guided biopsy is crucial for cancer staging and treatment. Optical/nuclide dual-modality imaging agents for mapping SLN are ideal for preoperative planning and intraoperative biopsy, which are enabled by penetration-depth unlimited nuclide imaging and dynamic real-time optical imaging, respectively. However, commonly reported dual-modality imaging agents are composed of novel but safety-unproven materials, making their quick clinical translation challenging. Herein, we report a novel nanoparticle composed of facile hospital-available drugs and isotope for single-photon emission computed tomography (SPECT)/near-infrared (NIR) fluorescence imaging to detect SLNs. Methods: Indocyanine green-human serum albumin (ICG-HSA) nanoparticles (NPs) were synthesized by ICG-induced HSA self-assembly and further ^99mTc-labeling via a one-step, facile hospital-available method. After injecting ^99mTc-ICG-HSA into the rats’ forepaw pads, the rats’ draining axillary lymph nodes were visualized by preoperative mapping with SPECT/CT and intraoperative biopsy with NIR fluorescence. The axillary lymph nodes of rats were identified by pathology and fluorescent staining after execution. Additionally, its toxicity testing and comparison with ^99mTc-sulfur colloid imaging were also explored. Results: The study reported a self-assembled ^99mTc-ICG-HSA with a high radiochemical yield (85.6 ± 3.8%). Compared with conventional ^99mTc-sulfur colloid, ^99mTc-ICG-HSA NPs showed faster SLN identification, higher renal clearance, and lower hepatic retention. Furthermore, NIRF imaging allowed for the accurate visualization of the SLN and guided SLN biopsy intraoperatively. Notably, the ^99mTc-ICG-HSA NPs were composed of hospital-available drugs and isotope, which are safe for acute toxicity evaluation by a certified institute. Conclusion: The proposed ^99mTc-ICG-HSA NPs are safe and capable of noninvasive SLN identification and biopsy guidance with multi-modal imaging strategies and could be a promising tool for clinically assisted SLN biopsy.