Precise assessment of Graves` orbitopathy (GO) predicts therapeutic strategies. Various imaging techniques and different measurement methods are used, but there is a lack of standardization. Traditionally, the Clinical Activity Score (CAS) has been used for assessing GO, especially for evaluating disease activity to predict response to glucocorticoid (GC) therapy, but technological developments have led to a shift towards more objective imaging methods that offer accuracy. Imaging methods for Graves' orbitopathy assessment include ultrasonography (USG), computed tomography (CT), magnetic resonance imaging (MRI), and single photon emission computed tomography (SPECT). These can be divided into those that assess disease activity (MRI, SPECT) and those that assess disease severity (USG, CT, MRI, SPECT). USG is the accessible first-aid tool that provides non-invasive imaging of orbital structures, with a short time of examination making it highly suitable for initial evaluation and monitoring of GO. It does have limitations, particularly in visualizing the apex of the orbit. Initially, orbital CT was thought to provide more accurate morphological information, particularly in extraocular muscles, and superior visualization of bone structures compared to MRI, making it the imaging modality of choice prior to planned orbital decompression; however, it has difficulty in accurately assessing the inflammatory activity stages of GO. Although CT offers a better view of deeper-lying tissue, it is limited by radiation exposure. MRI is best suited for follow-up examinations because it offers superior soft tissue visualization and precise tissue differentiation. However, it is not specific for orbital changes, the examination is very expensive, and it is rarely available. Recent literature proposes that nuclear medicine imaging techniques may be the best discipline for assessing GO. SPECT fused with low-dose CT scans is now used to increase the diagnostic value of the investigation. It provides functional information on top of the anatomical images. The use of cost-effective radioisotope - technetium-99m (99mTc)-DTPA - gives great diagnostic results with short examination time, low radiation exposure, and satisfactory spatial resolution. Nowadays, 36 years after CAS development and with technological improvement, researchers aim to integrate artificial intelligence tools with SPECT/CT imaging to diagnose and stage GO activity more effectively.

Current machine learning-based (ML) models usually attempt to utilize all available patient data to predict patient outcomes while ignoring the associated cost and time for data acquisition. The purpose of this study is to create a multi-stage ML model to predict cardiac resynchronization therapy (CRT) response for heart failure (HF) patients. This model exploits uncertainty quantification to recommend additional collection of single-photon emission computed tomography myocardial perfusion imaging (SPECT MPI) variables if baseline clinical variables and features from electrocardiogram (ECG) are not sufficient. Two hundred eighteen patients who underwent rest-gated SPECT MPI were enrolled in this study. CRT response was defined as an increase in left ventricular ejection fraction (LVEF) > 5% at a 6 ± 1 month follow-up. A multi-stage ML model was created by combining two ensemble models: Ensemble 1 was trained with clinical variables and ECG; Ensemble 2 included Ensemble 1 plus SPECT MPI features. Uncertainty quantification from Ensemble 1 allowed for multi-stage decision-making to determine if the acquisition of SPECT data for a patient is necessary. The performance of the multi-stage model was compared with that of Ensemble models 1 and 2. The response rate for CRT was 55.5% (n = 121) with overall male gender 61.0% (n = 133), an average age of 62.0 ± 11.8, and LVEF of 27.7 ± 11.0. The multi-stage model performed similarly to Ensemble 2 (which utilized the additional SPECT data) with AUC of 0.75 vs. 0.77, accuracy of 0.71 vs. 0.69, sensitivity of 0.70 vs. 0.72, and specificity 0.72 vs. 0.65, respectively. However, the multi-stage model only required SPECT MPI data for 52.7% of the patients across all folds. By using rule-based logic stemming from uncertainty quantification, the multi-stage model was able to reduce the need for additional SPECT MPI data acquisition without significantly sacrificing performance.

Single photon emission computed tomography (SPECT) remains the most widely used modality for the assessment of coronary artery disease (CAD) owing to its diagnostic and prognostic value, cost-effectiveness, broad availability, and ability to be performed with exercise testing. However, major cardiology guidelines recommend positron emission tomography (PET) over SPECT when available, largely due to its superior accuracy and ability to provide absolute myocardial blood flow quantification. A key limitation of SPECT is its reliance on relative perfusion imaging, which may overlook diffuse flow reductions, such as those seen in balanced ischemia, diffuse atherosclerosis, and microvascular dysfunction. With the shifting paradigm of CAD toward non-obstructive disease, the need for absolute quantification has become increasingly critical. This review highlights the strengths and limitations of SPECT and explores strategies to preserve its clinical relevance in the PET era. These include the adoption of CZT-SPECT technology for quantification, the use of hybrid systems for attenuation correction and calcium scoring, the adoption of stress-only protocols, the integration of quantitative data and calcium scoring into reporting, and the emerging applications of artificial intelligence (AI) among others.

The aim of the study was to validate a new method for semiautomatic subtraction of [^99mTc]Tc-sestamibi and [^99mTc]NaTcO₄ SPECT 3-dimensional datasets using principal component analysis (PCA) against the results of parathyroid surgery and to compare its performance with an interactive method for visual comparison of images. We also sought to identify factors that affect the accuracy of lesion detection using the two methods. <b>Methods:</b> Scintigraphic data from [^99mTc]Tc-sestamibi and [^99mTc]NaTcO₄ SPECT were analyzed using semiautomatic subtraction of the 2 registered datasets based on PCA applied to the region of interest including the thyroid and an interactive method for visual comparison of the 2 image datasets. The findings of both methods were compared with those of surgery. Agreement with surgery was assessed with respect to the lesion quadrant, affected side of the neck, and the patient positivity regardless of location. <b>Results:</b> The results of parathyroid surgery and histology were available for 52 patients who underwent [^99mTc]Tc-sestamibi/[^99mTc]NaTcO₄ SPECT. Semiautomatic image subtraction identified the correct lesion quadrant in 46 patients (88%), the correct side of the neck in 51 patients (98%), and true pathologic lesions regardless of location in 51 patients (98%). Visual interactive analysis identified the correct lesion quadrant in 44 patients (85%), correct side of the neck in 49 patients (94%), and true pathologic lesions regardless of location in 50 patients (96%). There was no significant difference between the results of the 2 methods (<i>P</i> > 0.05). The factors supporting lesion detection were accurate positioning of the patient on the camera table, which facilitated subsequent image registration of the neck, and, after excluding ectopic parathyroid glands, focusing detection on the thyroid ROI. <b>Conclusion:</b> The results of semiautomatic subtraction of [^99mTc]Tc-sestamibi/[^99mTc]NaTcO₄ SPECT using PCA had good agreement with the findings from surgery as well as the visual interactive method, comparable to the high diagnostic accuracy of [^99mTc]Tc-sestamibi/[¹²³I]NaI subtraction scintigraphy and [¹⁸F]fluorocholine PET/CT reported in the literature. The main advantages of semiautomatic subtraction are minimum user interaction and automatic adjustment of the subtraction weight. Principal component images may serve as optimized input objects, potentially useful in machine-learning algorithms aimed at fully automated detection of hyperfunctioning parathyroid glands.

<i>Background:</i> Neuroendocrine neoplasms (NENs) are a diverse group of malignancies in which somatostatin receptor expression can be crucial in guiding therapy. We aimed to evaluate the effectiveness of [^99mTc]Tc-EDDA/HYNIC-TOC SPECT/CT in differentiating neuroendocrine tumor histology, selecting candidates for radioligand therapy, and identifying correlations between somatostatin receptor expression and non-imaging parameters in metastatic NENs. <i>Methods:</i> This retrospective study included 65 patients (29 women, 36 men, mean age 61) with metastatic neuroendocrine neoplasms confirmed by histology, follow-up, or imaging, comprising 14 poorly differentiated carcinomas and 51 well-differentiated tumors. Somatostatin receptor SPECT/CT results were assessed visually and semiquantitatively, with mathematical models incorporating histological, oncological, immunohistochemical, and laboratory parameters, followed by biostatistical analysis. <i>Results:</i> Of 392 lesions evaluated, the majority were metastases in the liver, lymph nodes, and bones. Mathematical models estimated somatostatin receptor expression accurately (70-83%) based on clinical parameters alone. Key factors included tumor origin, oncological treatments, and the immunohistochemical marker CK7. Associations were found between age, grade, disease extent, and markers (CEA, CA19-9, AFP). <i>Conclusions:</i> Our findings suggest that [^99mTc]Tc-EDDA/HYNIC-TOC SPECT/CT effectively evaluates somatostatin receptor expression in NENs. Certain immunohistochemical and laboratory parameters, beyond recognized factors, show potential prognostic value, supporting individualized treatment strategies.

Internal vectorised therapies, particularly with [177Lu]-labelled agents, are increasingly used for metastatic prostate cancer and neuroendocrine tumours. However, routine dosimetry for organs-at-risk and tumours remains limited due to the complexity and time requirements of current protocols. We developed a Generative Adversarial Network (GAN) to transform rapid 6 s SPECT projections into synthetic 30 s-equivalent projections. SPECT data from twenty patients and phantom acquisitions were collected at multiple time-points. The GAN accurately predicted 30 s projections, enabling estimation of time-integrated activities in kidneys and liver with maximum errors below 6 % and 1 %, respectively, compared to standard acquisitions. For tumours and phantom spheres, results were more variable. On phantom data, GAN-inferred reconstructions showed lower biases for spheres of 20, 8, and 1 mL (8.2 %, 6.9 %, and 21.7 %) compared to direct 6 s acquisitions (12.4 %, 20.4 %, and 24.0 %). However, in patient lesions, 37 segmented tumours showed higher median discrepancies in cumulated activity for the GAN (15.4 %) than for the 6 s approach (4.1 %). Our preliminary results indicate that the GAN can provide reliable dosimetry for organs-at-risk, but further optimisation is needed for small lesion quantification. This approach could reduce SPECT acquisition time from 45 to 9 min for standard three-bed studies, potentially facilitating wider adoption of dosimetry in nuclear medicine and addressing challenges related to toxicity and cumulative absorbed doses in personalised radiopharmaceutical therapy.

Myocardial perfusion imaging using SPECT is widely utilized to diagnose coronary artery diseases, but image quality can be negatively affected in low-dose and few-view acquisition settings. Although various deep learning methods have been introduced to improve image quality from low-dose or few-view SPECT data, previous approaches often fail to generalize across different acquisition settings, limiting realistic applicability. This work introduced DiffSPECT-3D, a diffusion framework for 3D cardiac SPECT imaging that effectively adapts to different acquisition settings without requiring further network re-training or fine-tuning. Using both image and projection data, a consistency strategy is proposed to ensure that diffusion sampling at each step aligns with the low-dose/few-view projection measurements, the image data, and the scanner geometry, thus enabling generalization to different low-dose/few-view settings. Incorporating anatomical spatial information from CT and total variation constraint, we proposed a 2.5D conditional strategy to allow DiffSPECT-3D to observe 3D contextual information from the entire image volume, addressing the 3D memory/computational issues in diffusion model. We extensively evaluated the proposed method on 1,325 clinical ^99mTc tetrofosmin stress/rest studies from 795 patients. Each study was reconstructed into 5 different low-count levels and 5 different projection few-view levels for model evaluations, ranging from 1% to 50% and from 1 view to 9 view, respectively. Validated against cardiac catheterization results and diagnostic review from nuclear cardiologists, the presented results show the potential to achieve low-dose and few-view SPECT imaging without compromising clinical performance. Additionally, DiffSPECT-3D could be directly applied to full-dose SPECT images to further improve image quality, especially in a low-dose stress-first cardiac SPECT imaging protocol.

This study explores an artificial intelligence-based approach to perform CT-free quantitative SPECT for kidney imaging using Tc-99 m DTPA, aiming to estimate glomerular filtration rate (GFR) without relying on CT. A total of 1000 SPECT/CT scans were used to train and test a deep-learning model that segments kidneys automatically based on synthetic attenuation maps (µ-maps) derived from SPECT alone. The model employed a residual U-Net with edge attention and was optimized using windowing-maximum normalization and a generalized Dice similarity loss function. Performance evaluation showed strong agreement with manual CT-based segmentation, achieving a Dice score of 0.818 ± 0.056 and minimal volume differences of 17.9 ± 43.6 mL (mean ± standard deviation). An additional set of 50 scans confirmed that GFR calculated from the AI-based CT-free SPECT (109.3 ± 17.3 mL/min) was nearly identical to the conventional SPECT/CT method (109.2 ± 18.4 mL/min, p = 0.9396). This CT-free method reduced radiation exposure by up to 78.8% and shortened segmentation time from 40 min to under 1 min. The findings suggest that AI can effectively replace CT in kidney SPECT imaging, maintaining quantitative accuracy while improving safety and efficiency.

Single-photon emission computed tomography (SPECT) plays a crucial role in detecting bone metastases from lung cancer. However, its low spatial resolution and lesion similarity to benign structures present significant challenges for accurate segmentation, especially for lesions of varying sizes. We propose a deep learning-based segmentation framework that integrates conditional adversarial learning with a multi-scale feature extraction generator. The generator employs cascade dilated convolutions, multi-scale modules, and deep supervision, while the discriminator utilizes multi-scale L1 loss computed on image-mask pairs to guide segmentation learning. The proposed model was evaluated on a dataset of 286 clinically annotated SPECT scintigrams. It achieved a Dice Similarity Coefficient (DSC) of 0.6671, precision of 0.7228, and recall of 0.6196 - outperforming both classical and recent adversarial segmentation models in multi-scale lesion detection, especially for small and clustered lesions. Our results demonstrate that the integration of multi-scale feature learning with adversarial supervision significantly improves the segmentation of bone metastasis in SPECT imaging. This approach shows potential for clinical decision support in the management of lung cancer.

This study aims to enhance the dosimetry accuracy in ¹³¹I planar imaging by utilizing a single oblique view and Monte Carlo (MC) validated dose point kernels (DPKs) alongside the integration of artificial intelligence (AI) for accurate dose prediction within planar imaging. Forty patients with thyroid cancers post-thyroidectomy surgery and 30 with neuroendocrine tumors underwent planar and SPECT/CT imaging. Using whole-body (WB) planar images with an additional oblique view, organ thicknesses were estimated. DPKs and organ-specific S-values were used to estimate the absorbed doses. Four AI algorithms- multilayer perceptron (MLP), linear regression, support vector regression model, decision tree, convolution neural network, and U-Net were used for dose estimation. Planar image counts, body thickness, patient BMI, age, S-values, and tissue attenuation coefficients were imported as input into the AI algorithm. To provide the ground truth, the CT-based segmentation generated binary masks for each organ, and the corresponding SPECT images were used for GATE MC dosimetry. The MLP-predicted dose values across all organs represented superior performance with the lowest mean absolute error in the liver but higher in the spleen and salivary glands. Notably, MLP-based dose estimations closely matched ground truth data with < 15% differences in most tissues. The MLP-estimated dose values present a robust patient-specific dosimetry approach capable of swiftly predicting absorbed doses in different organs using WB planar images and a single oblique view. This approach facilitates the implementation of 2D planar imaging as a pre-therapeutic technique for a more accurate assessment of the administrated activity.