The cornerstone of ovarian cancer treatment is complete surgical cytoreduction. The gold-standard option in the absence of extra-abdominal metastases and intra-abdominal inoperable circumstances is primary cytoreductive surgery (CRS). However, achieving complete cytoreduction is challenging, and only possible in a selected patient population. Preoperative imaging modalities such as [¹⁸F]FDG PET/CT could be useful in patient selection for cytoreductive surgery. In our systematic review and meta-analysis, we aimed to evaluate the role of preoperative [¹⁸F]FDG PET/CT in predicting complete cytoreduction in primary and secondary debulking surgeries. Publications were pooled from two databases (PubMed, Mendeley) with predefined keywords “(ovarian cancer) AND (FDG OR PET) AND (cytoreductive surgery)”. The quality of the included studies was assessed with the Prediction model Risk Of Bias Assessment Tool (PROBAST). During statistical analysis, MetaDiSc 1.4 software and the DerSimonian–Laird method (random effects models) were used. Primary and secondary cytoreductive surgeries were evaluated. Pooled sensitivities, specificities, positive predictive values (PPVs), and negative predictive values (NPVs) were calculated and statistically analyzed. Results were presented in forest plot diagrams and summary receiver operating characteristic (SROC) curves. Overall, eight publications were included in our meta-analysis. Four publications presented results of primary, three presented results of secondary cytoreductions, and two presented data related to both primary and secondary surgery. Pooled sensitivities, specificities, and positive and negative predictive values were the following: in the case of primary surgeries: 0.65 (95% CI 0.60–0.71), 0.73 (95% CI 0.66–0.80), 0.82 (95% CI 0.77–0.87), 0.52 (95% CI 0.46–0.59); and in the case of secondary surgeries: 0.91 (95% CI 0.84–0.95), 0.48 (95% CI 0.30–0.67), 0.88 (95% CI 0.81–0.93), 0.56 (95% CI 0.35–0.75), respectively. The PPVs of [¹⁸F]FDG PET/CT proved to be higher in cases of secondary debulking surgeries; therefore, it can be a valuable predictor of complete successful secondary cytoreduction.

Background/Objectives: Artificial intelligence (AI) is a promising tool for the enhancement of physician workflow and serves to further improve the efficiency of their diagnostic evaluations. This study aimed to assess the performance of an AI-based bone scan noise-reduction filter on noisy, low-count images in a routine clinical environment. Methods: The performance of the AI bone-scan filter (BS-AI filter) in question was retrospectively evaluated on 47 different patients’ ^99mTc-MDP bone scintigraphy image pairs (anterior- and posterior-view images), which were obtained in such a manner as to represent the diverse characteristics of the general patient population. The BS-AI filter was tested on artificially degraded noisy images—75, 50, and 25% of total counts—which were generated by binominal sampling. The AI-filtered and unfiltered images were concurrently appraised for image quality and contrast by three nuclear medicine physicians. It was also determined whether there was any difference between the lesions seen on the unfiltered and filtered images. For quantitative analysis, an automatic lesion detector (BS-AI annotator) was utilized as a segmentation algorithm. The total number of lesions and their locations as detected by the BS-AI annotator in the BS-AI-filtered low-count images was compared to the total-count filtered images. The total number of pixels labeled as lesions in the filtered low-count images in relation to the number of pixels in the total-count filtered images was also compared to ensure the filtering process did not change lesion sizes significantly. The comparison of pixel numbers was performed using the reduced-count filtered images that contained only those lesions that were detected in the total-count images. Results: Based on visual assessment, observers agreed that image contrast and quality were better in the BS-AI-filtered images, increasing their diagnostic confidence. Similarities in lesion numbers and sites detected by the BS-AI annotator compared to filtered total-count images were 89%, 83%, and 75% for images degraded to counts of 75%, 50%, and 25%, respectively. No significant difference was found in the number of annotated pixels between filtered images with different counts (p > 0.05). Conclusions: Our findings indicate that the BS-AI noise-reduction filter enhances image quality and contrast without loss of vital information. The implementation of this filter in routine diagnostic procedures reliably improves diagnostic confidence in low-count images and elicits a reduction in the administered dose or acquisition time by a minimum of 50% relative to the original dose or acquisition time.

Purpose: Unilateral condylar hyperplasia (UCH) is a rare mandibular growth disorder in which accurate assessment of condylar metabolic activity is essential for surgical decision-making. Quantitative ^99m Tc-methylene diphosphonate (MDP) SPECT/CT is commonly used for this purpose; however, CT-based attenuation correction (CTAC) increases radiation exposure and may be affected by registration errors. Artificial intelligence (AI)-generated synthetic CT (SyCT) has been proposed as a CT-independent alternative. This study aimed to evaluate the agreement between SyCT-based attenuation correction (SyCTAC) and conventional CTAC in quantitative SPECT imaging of UCH. Methods: This retrospective study included 14 patients with UCH who underwent ^99m Tc-MDP SPECT/CT. SPECT images were reconstructed with identical parameters using either CTAC or AI-generated SyCTAC. Spherical volumes of interest were placed over both mandibular condyles and the clivus, and maximum and mean standardized uptake values were measured. Relative uptake fractions normalized to the summed condylar activity were calculated for the affected side, while condylar uptake normalized to the clivus was evaluated for both sides. Agreement between CTAC- and SyCTAC-derived indices was assessed using Bland–Altman analysis and linear mixed-effects models. Results: Visual evaluation revealed no relevant differences in image quality between the two reconstructions. Relative uptake fractions normalized to the summed condylar activity showed good agreement between methods. Clivus-normalized ratios demonstrated a small positive bias. Conclusion: AI-generated SyCT provides attenuation correction comparable to CTAC for clinically relevant relative condylar uptake assessment in UCH, supporting its use as a low-radiation alternative for quantitative mandibular SPECT imaging.