Automatic and accurate segmentation of lesions in images of metastatic castration-resistant prostate cancer has the potential to enable personalized radiopharmaceutical therapy and advanced treatment response monitoring. The aim of this study is to develop a convolutional neural networks-based framework for fully-automated detection and segmentation of metastatic prostate cancer lesions in whole-body PET/CT images. 525 whole-body PET/CT images of patients with metastatic prostate cancer were available for the study, acquired with the [¹⁸F]DCFPyL radiotracer that targets prostate-specific membrane antigen (PSMA). U-Net (1)-based convolutional neural networks (CNNs) were trained to identify lesions on paired axial PET/CT slices. Baseline models were trained using batch-wise dice loss, as well as the proposed weighted batch-wise dice loss (wDice), and the lesion detection performance was quantified, with a particular emphasis on lesion size, intensity, and location. We used 418 images for model training, 30 for model validation, and 77 for model testing. In addition, we allowed our model to take n = 0,2, …, 12 neighboring axial slices to examine how incorporating greater amounts of 3D context influences model performance. We selected the optimal number of neighboring axial slices that maximized the detection rate on the 30 validation images, and trained five neural networks with different architectures. Model performance was evaluated using the detection rate, Dice similarity coefficient (DSC) and sensitivity. We found that the proposed wDice loss significantly improved the lesion detection rate, lesion-wise DSC and lesion-wise sensitivity compared to the baseline, with corresponding average increases of 0.07 (p-value = 0.01), 0.03 (p-value = 0.01) and 0.04 (p-value = 0.01), respectively. The inclusion of the first two neighboring axial slices in the input likewise increased the detection rate by 0.17, lesion-wise DSC by 0.05, and lesion-wise mean sensitivity by 0.16. However, there was a minimal effect from including more distant neighboring slices. We ultimately chose to use a number of neighboring slices equal to 2 and the wDice loss function to train our final model. To evaluate the model's performance, we trained three models using identical hyperparameters on three different data splits. The results showed that, on average, the model was able to detect 80% of all testing lesions, with a detection rate of 93% for lesions with maximum standardized uptake values (SUVmax) greater than 5.0. In addition, the average median lesion-wise DSC was 0.51 and 0.60 for all the lesions and lesions with SUVmax>5.0, respectively, on the testing set. Four additional neural networks with different architectures were trained, and they both yielded stronger performance of segmenting lesions whose SUVmax>5.0 compared to the rest of lesions. Our results demonstrate that prostate cancer metastases in PSMA PET/CT images can be detected and segmented using CNNs. The segmentation performance strongly depends on the intensity, size, and the location of lesions, and can be improved by using specialized loss functions. Specifically, the models performed best in detection of lesions with SUVmax>5.0. Another challenge was to accurately segment lesions close to the bladder. Future work will focus on improving the detection of lesions with lower SUV values by designing custom loss functions that take into account the lesion intensity, using additional data augmentation techniques, and reducing the number of false lesions by developing methods to better separate signal from noise.

The prostate-specific membrane antigen (PSMA) is an excellent target for theranostic applications in prostate cancer (PCa). However, PSMA-targeted radioligand therapy can cause undesirable effects due to high accumulation of PSMA radiotracers in salivary glands and kidneys. This study assessed orally administered monosodium glutamate (MSG) as a potential means of reducing kidney and salivary gland radiation exposure using a PSMA targeting radiotracer. Methods: This prospective, double-blind, placebo-controlled study enrolled 10 biochemically recurrent PCa patients. Each subject served as his own control. [¹⁸F]DCFPyl PET/CT imaging sessions were performed 3 – 7 days apart, following oral administration of either 12.7 g of MSG or placebo. Data from the two sets of images were analyzed by placing regions of interest on lacrimal, parotid and submandibular glands, left ventricle, liver, spleen, kidneys, bowel, urinary bladder, gluteus muscle and malignant lesions. The results from MSG and placebo scans were compared by paired analysis of the ROI data. Results: A total of 142 pathological lesions along with normal tissues were analyzed. As hypothesized a priori, there was a significant decrease in maximal standardized uptake values corrected for lean body mass (SULmax) on images obtained following MSG administration in the parotids (24 ± 14%, P = 0.001), submandibular glands (35 ± 11%, P<0.001) and kidneys (23 ± 26%, P = 0.014). Significant decreases were also observed in lacrimal glands (49 ± 13%, P<0.001), liver (15 ± 6%, P<0.001), spleen (28 ± 13%, P = 0.001) and bowel (44 ± 13%, P<0.001). Mildly lower blood pool SULmean was observed after MSG administration (decrease of 11 ± 13%, P = 0.021). However, significantly lower radiotracer uptake in terms of SULmean, SULpeak, and SULmax was observed in malignant lesions on scans performed after MSG administration compared to the placebo studies (SULmax median decrease 33%, range -1 to 75%, P<0.001). No significant adverse events occurred and vital signs were stable following placebo or MSG administration. Conclusion: Orally administered MSG significantly decreased salivary gland, kidney and other normal organ PSMA radiotracer uptake in human subjects, using [¹⁸F]DCFPyL as an exemplar. However, MSG caused a corresponding reduction in tumor uptake, which may limit the benefits of this approach for diagnostic and therapeutic applications.

Juvenile systemic lupus erythematosus (JSLE) is a polygenic, autoimmune disorder of unknown origin. As proinflammatory cytokines, including interleukin-6 (IL-6) and the interleukin-1 (IL-1) family, seem to contribute to the pathogenesis of JSLE, this investigation was performed to assess the associations of particular single nucleotide polymorphisms (SNPs) of IL-6 and IL-1 genes in a case-control study. Fifty nine JSLE cases were recruited for this study as the patient group, and were compared against 140 healthy, unrelated, control subjects. Using the polymerase chain reaction with the sequence-specific primer method, genotyping was carried out for the IL-6 gene at positions -174 and nt565, as well as the IL-1α gene at position -889, the IL-1β gene at positions -511 and +3962, the interleukin-1 receptor (IL-1R) gene at position Pst-I 1970, and the interleukin-1 receptor antagonist (IL-1Ra) gene at position Mspa-I 11100. RESULTS of the analyzed data revealed a remarkable, positive association for the promoter sequence of the IL-1β gene at position -511 for T/T in the patient group compared with healthy controls (P value, 0.03). Furthermore, a significant negative association was found between the T/C genotype at the same position on the IL-1β gene in juvenile SLE (P value, 0.03). cytokine gene polymorphisms might play a role in the pathophysiology of JSLE. Particular IL-1 gene variants could affect individual susceptibility to JSLE.

Juvenile-onset systemic lupus erythematosus (JSLE) is a multisystem autoimmune disease in which both the genetic and environmental factors seem to be involved in the etiopathogenesis of the disease. The aim of this study was to evaluate the association of programmed cell death 1 (PDCD1, also called PD-1) gene polymorphisms with JSLE susceptibility in Iranian population. In this case-control association study, three PDCD1 SNPs, including PD-1.1 G/A, PD-1.3 G/A and PD-1.9 C/T were genotyped in 50 Iranian patients with JSLE and 202 healthy unrelated controls, using PCR-RFLP method. The PD-1.1 A allele was found to be more frequent in the case group compared with controls (6% vs. 1.5%, p = 0.024). Moreover, the GG genotype was less frequent in cases than in controls (88% vs. 97%, p = 0.021). The other PDCD1 SNPs did not show association. At the haplotypic level, no significant differences was recognized between the two groups of case and control neither for the GAC (PD-1.1 G, PD-1.3 A, PD-1.9 C) nor for the GGC haplotype (PD-1.1 G, PD-1.3 G, PD-1.9 C). Our findings support the influence of the PD1.1 A SNP on the development of JSLE in Iranian population.