Impact of deep learning-based multiorgan segmentation methods on patient-specific internal dosimetry in PET/CT imaging: A comparative study.

PURPOSE: Accurate and fast multiorgan segmentation is essential in image-based internal dosimetry in nuclear medicine. While conventional manual PET image segmentation is widely used, it suffers from both being time-consuming as well as subject to human error. This study exploited 2D and 3D deep learning (DL) models. Key organs in the trunk of the body were segmented and then used as a reference for networks. METHODS: The pre-trained p2p-U-Net-GAN and HighRes3D architectures were fine-tuned with PET-only images as inputs. Additionally, the HighRes3D model was alternatively trained with PET/CT images. Evaluation metrics such as sensitivity (SEN), specificity (SPC), intersection over union (IoU), and Dice scores were considered to assess the performance of the networks. The impact of DL-assisted PET image segmentation methods was further assessed using the Monte Carlo (MC)-derived S-values to be used for internal dosimetry. RESULTS: A fair comparison with manual low-dose CT-aided segmentation of the PET images was also conducted. Although both 2D and 3D models performed well, the HighRes3D offers superior performance with Dice scores higher than 0.90. Key evaluation metrics such as SEN, SPC, and IoU vary between 0.89-0.93, 0.98-0.99, and 0.87-0.89 intervals, respectively, indicating the encouraging performance of the models. The percentage differences between the manual and DL segmentation methods in the calculated S-values varied between 0.1% and 6% with a maximum attributed to the stomach. CONCLUSION: The findings prove while the incorporation of anatomical information provided by the CT data offers superior performance in terms of Dice score, the performance of HighRes3D remains comparable without the extra CT channel. It is concluded that both proposed DL-based methods provide automated and fast segmentation of whole-body PET/CT images with promising evaluation metrics. Between them, the HighRes3D is more pronounced by providing better performance and can therefore be the method of choice for 18F-FDG-PET image segmentation.

Deep learning in ovarian cancer diagnosis: a comprehensive review of various imaging modalities.

Ovarian cancer poses a major worldwide health issue, marked by high death rates and a deficiency in reliable diagnostic methods. The precise and prompt detection of ovarian cancer holds great importance in advancing patient outcomes and determining suitable treatment plans. Medical imaging techniques are vital in diagnosing ovarian cancer, but achieving accurate diagnoses remains challenging. Deep learning (DL), particularly convolutional neural networks (CNNs), has emerged as a promising solution to improve the accuracy of ovarian cancer detection. This systematic review explores the role of DL in improving the diagnostic accuracy for ovarian cancer. The methodology involved the establishment of research questions, inclusion and exclusion criteria, and a comprehensive search strategy across relevant databases. The selected studies focused on DL techniques applied to ovarian cancer diagnosis using medical imaging modalities, as well as tumour differentiation and radiomics. Data extraction, analysis, and synthesis were performed to summarize the characteristics and findings of the selected studies. The review emphasizes the potential of DL in enhancing the diagnosis of ovarian cancer by accelerating the diagnostic process and offering more precise and efficient solutions. DL models have demonstrated their effectiveness in categorizing ovarian tissues and achieving comparable diagnostic performance to that of experienced radiologists. The integration of DL into ovarian cancer diagnosis holds the promise of improving patient outcomes, refining treatment approaches, and supporting well-informed decision-making. Nevertheless, additional research and validation are necessary to ensure the dependability and applicability of DL models in everyday clinical settings.

The evaluation of protective and mitigating effects of vitamin C against side effects induced by radioiodine therapy.

The goal of this study was to evaluate the protective and mitigative effect of vitamin C on oxidative stress in differentiated thyroid cancer (DTC) patients ablated with radioiodine. 58 DTC patients selected for radioactive iodine therapy (RAIT) with 5550 MBq 131Iodine were divided into four groups. Group 1 (control group) consisted of patients who underwent RAIT routinely. Other patients received 1500 mg vitamin C daily 2 days after (group 2), 2 days before to 2 days after (group 3) and 2 days before RAIT (group 4). Serum oxidative stress markers including malondialdehyde (MDA), glutathione (GSH), catalase (CAT), and superoxide dismutase (SOD) were measured immediately before and 2 days after RAIT. A significant increase in MDA after RAIT was observed in all groups (p < 0.05). The concentrations of MDA were significantly higher in the control group compared to the intervention groups (p < 0.05). A significant decrease in the control group (p < 0.05) and increase in group 4 (p < 0.05) were observed in GSH level after RAIT (p < 0.05). Mean variation of GSH was significant between control group with groups 3 (p < 0.01) and 4 (p < 0.01). The results indicate that activity of SOD remained unchanged in all groups (p > 0.05). A significant increase was observed in CAT activity after RAIT in all groups (p < 0.05), which was higher in control group than intervention groups. In groups 3 (p < 0.05) and 4 (p < 0.05), this increase in CAT activity was significantly lower than the control group. RAIT causes serum oxidative stress, which can be ameliorated using vitamin C as an antioxidant. These results indicate that radioprotective effect of vitamin C is preferable to its mitigative effect.

Evaluation of vascular graft infection following Bentall surgery using 18F-FDG PET/CT scan: A pediatric case report.

Key Clinical Message: After a Bentall surgery, there is a small chance of developing a serious complication called vascular graft infection. 18F-FDG PET/CT, a new and accurate diagnostic tool, can help detect it early, especially if the symptoms are unusual. Abstract: A 14-year-old boy who had undergone Bentall surgery 1 year prior presented with symptoms of fever, chills, loss of appetite, and weight loss over the course of a month. The initial Bentall surgery was performed due to an aneurysm of the thoracic aorta, along with severe aortic valve insufficiency and moderate aortic valve stenosis. The patient was referred to the PET/CT department for evaluation of possible endarteritis or infection of Dacron graft, which had been reported in trans-esophageal echocardiography as suspicious findings. Despite normal blood tests, blood cultures, and other imaging modalities, the 18F-FDG PET/CT confirmed the diagnosis of vascular graft infection. This diagnostic tool allowed for timely and appropriate treatment and prevention of possible complications.

PET/CT-based 3D multi-class semantic segmentation of ovarian cancer and the stability of the extracted radiomics features.

Accurate segmentation of ovarian cancer (OC) lesions in PET/CT images is essential for effective disease management, yet manual segmentation for radiomics analysis is labor-intensive and time-consuming. This study introduces the application of a 3D U-Net deep learning model, leveraging advanced 3D networks, for multi-class semantic segmentation of OC in PET/CT images and assesses the stability of the extracted radiomics features. Utilizing a dataset of 3120 PET/CT images from 39 OC patients, the dataset was divided into training (70%), validation (15%), and test (15%) subsets to optimize and evaluate the model's performance. The 3D U-Net model, especially with a VGG16 backbone, achieved notable segmentation accuracy with a Dice score of 0.74, Precision of 0.76, and Recall of 0.78. Additionally, the study demonstrated high stability in radiomics features, with over 85% of PET and 84% of CT image features showing high intraclass correlation coefficients (ICCs > 0.8). These results underscore the potential of automated 3D U-Net-based segmentation to significantly enhance OC diagnosis and treatment planning. The reliability of the extracted radiomics features from automated segmentation supports its application in clinical decision-making and personalized medicine. This research marks a significant advancement in oncology diagnostics, providing a robust and efficient method for segmenting OC lesions in PET/CT images. By addressing the challenges of manual segmentation and demonstrating the effectiveness of 3D networks, this study contributes to the growing body of evidence supporting the application of artificial intelligence in improving diagnostic accuracy and patient outcomes in oncology.

Protective effects of Panax Ginseng against 131I-induced genotoxicity in patients with differentiated thyroid cancer.

BACKGROUND: Radioiodine (131I) therapy (RAIT) is associated with oxidative stress (OS)-induced DNA damage in patients with differentiated thyroid cancer (DTC). The goal of this study was to evaluate the possible ameliorating effects of Panax Ginseng (PG) on RAIT-induced genotoxicity in patients with DTC. MATERIALS AND METHODS: Forty DTC patients who had received 131I (100 to 175 mCi) were enrolled in this study. The patients were randomly classified (n = 10) into control, placebo, PG1 groups (receiving 500 mg/day of PG for 2 days before RAIT), and PG2 group (receiving 500 mg/day of PG for 2 days before to 1 day after RAIT). Blood samples were collected before and 2 days after RAIT. Lymphocyte micronuclei (MN) frequency was measured using the MN assay. Serum total antioxidant capacity (TAC) and ischemia-modified albumin (IMA) were measured using colorimetric assays. Serum albumin, blood urea nitrogen (BUN), creatinine, aspartate aminotransferase (AST), and alanine aminotransferase (ALT) were measured using commercial kits. RESULTS: The mean of baseline MN frequency was the same in the four groups. RAIT increased the MN frequencies to at least three times the baseline values in the control (39 ± 5) and placebo groups (38 ± 6) (P < 0.001). PG caused a significant decrease in the MN frequencies in the treated groups compared to the control and placebo groups (P < 0.001). RAIT and PG administration had no significant effects on the serum IMA, TAC, and markers of liver and kidney toxicity. CONCLUSION: PG could be considered a useful remedy for the protection against RAIT-induced chromosomal damage in DCT patients.

18F-FDG PET/CT imaging of several asymptomatic skeletal muscle metastases of mixed germ cell ovarian cancer.

Metastasis to muscles caused by ovarian cancer is very rare and has a poor prognosis. Performing a whole-body F18-FDG PET/CT scan makes it possible to examine the whole body in one study and detected lesions in unexpected places.

The OCDA-Net: a 3D convolutional neural network-based system for classification and staging of ovarian cancer patients using [18F]FDG PET/CT examinations.

OBJECTIVE: To create the 3D convolutional neural network (CNN)-based system that can use whole-body [18F]FDG PET for recurrence/post-therapy surveillance in ovarian cancer (OC). METHODS: In this study, 1224 image sets from OC patients who underwent whole-body [18F]FDG PET/CT at Kowsar Hospital between April 2019 and May 2022 were investigated. For recurrence/post-therapy surveillance, diagnostic classification as cancerous, and non-cancerous and staging as stage III, and stage IV were determined by pathological diagnosis and specialists' interpretation. New deep neural network algorithms, the OCDAc-Net, and the OCDAs-Net were developed for diagnostic classification and staging of OC patients using [18F]FDG PET/CT images. Examinations were divided into independent training (75%), validation (10%), and testing (15%) subsets. RESULTS: This study included 37 women (mean age 56.3 years; age range 36-83 years). Data augmentation techniques were applied to the images in two phases. There were 1224 image sets for diagnostic classification and staging. For the test set, 170 image sets were considered for diagnostic classification and staging. The OCDAc-Net areas under the receiver operating characteristic curve (AUCs) and overall accuracy for diagnostic classification were 0.990 and 0.92, respectively. The OCDAs-Net achieved areas under the receiver operating characteristic curve (AUCs) of 0.995 and overall accuracy of 0.94 for staging. CONCLUSIONS: The proposed 3D CNN-based models provide potential tools for recurrence/post-therapy surveillance in OC. The OCDAc-Net and the OCDAs-Net model provide a new prognostic analysis method that can utilize PET images without pathological findings for diagnostic classification and staging.

COVID-19 pneumonia detected by parathyroid scintigraphy.

We report a case of incidental diagnosis of COVID-19 pneumonia by parathyroid scintigraphy. A 53-year-old woman who had severe fatigue, and mild dyspnea underwent parathyroid scintigraphy due to increased serum parathyroid hormone (PTH) and serum calcium levels. Parathyroid scan was negative for abnormal parathyroid tissue. Although the patient had three negative results of COVID-19 PCR tests, significant 99m Tchexakis-2-methoxyisobutylisonitrile ([99mTc]MIBI) uptake is noticed in both lungs that was suspicious for Covid-19 pneumonia. The patient underwent CT scan of the chest for further evaluation. Diffuse groundglass opacities were identified in both lungs which were interpreted as typical feature for COVID-19 pneumonia.

Systemic cystic angiomatosis mimicking metastatic cancer.

BACKGROUND: Cystic angiomatosis is a rare benign disease presents with multiple lytic and sclerotic bone lesions mimicking a metastatic malignant neoplasia with less than 50 cases have been reported in literature so far. CASE PRESENTATION: We reported a case of a 48-year-old woman who presented to an oncology clinic with multiple lytic and sclerotic bone lesions. Oncologic investigation for metastatic malignant neoplasia started. After that the negative results were obtained by evaluating the primary tumor site, a final diagnosis of cystic angiomatosis was made according to bone biopsy results. CONCLUSIONS: Cystic angiomatosis is a rare disease with unpredictable prognosis. It can mimic metastatic malignancy especially when it presents at old age.

Immunomodulatory Effects of Omega-3 Fatty Acids in Patients with Differentiated Thyroid Cancer Before or After Radioiodine Ablation.

BACKGROUND: Thyroid cancer and radioactive iodine (RAI) ablation for postsurgical management may lead to uncontrolled inflammation. OBJECTIVE: This study was intended to assess the prophylactic and therapeutic immunomodulatory effects of omega-3 fatty acids in patients with differentiated thyroid cancer (DTC). METHODS: A total of 85 patients with DTC were allocated into two groups based on RAI dosage after thyroidectomy. Patients in each group were randomly distributed into three subgroups: G1 with RAI ablation only, G2 treated with omega-3 for 30 days before RAI ablation, and G3 treated with omega-3 for 30 days after RAI ablation. Fifteen healthy individuals were included as controls. Serum cytokine levels including IL-2, IL-4, IL-5, IL-6, IL-9, IL-10, IL-13, IL-17A, IL-17F, IL-21, IL-22, TNF-α and IFN-γ were determined by cytometric bead assay. RESULTS: IL-4, IL-6, IL-21 and IL-22 levels in patients with DTC were higher than in the healthy controls. Regardless of RAI dosage, IL-6 showed an increasing trend after RAI ablation. IL-4, IL-22, and IL-17A remained at considerably higher levels than in the healthy controls after RAI ablation. Within-group comparisons showed a significant reduction in Th1+Th17/Th2+Th22 ratio in G2 patients 1 week after RAI ablation. Between-group comparisons showed increased IL-10 levels in G3 compared with G1 patients one week after high-dose RAI ablation. In G3, Th1+Th17/Th2+Th22 and Th1+Th17/Th2+Th9+Th22 ratios were remarkably lesser than in G2 patients 1 month after intermediate-dose RAI ablation. CONCLUSION: Our results showed better anti-inflammatory effects of omega-3 when it was used therapeutically after RAI ablation in patients with DTC than when it was used prophylactically before RAI.

DESIGN AND FABRICATION OF A PEDIATRIC THYROID PHANTOM FOR USE IN RADIO-IODINE UPTAKE MEASUREMENT, IMAGE QUALITY CONTROL AND DOSIMETRY.

Estimating internal contamination from 131I for children in nuclear accidents is a crucial subject in the radiation protection field. Throughout this paper, an urgent and simple method was proposed for measuring 131I inside the pediatric thyroid gland by constructing a neck and thyroid phantom. For this purpose, CT scan images of healthy child's thyroids were obtained, and the sizes of different parts were determined by a 3D slicer image processing software. Girls with the body surface area between 0.95 and 1.05 were involved in this study. The fabricated phantom is composed of 5 cylindrical slabs of 2-cm thickness, and several small holes were constructed for TLD dosemeters near the thyroid gland and all other parts of the neck. The phantom was constructed utilizing a 3D printer with acrylonitrile butadiene styrene plastic. The thyroid phantom was filled with radioiodine-131, and calibration curves were plotted for contamination estimation. A nodular thyroid phantom was also constructed. The nodular phantom or the resolution phantom has 4 removable parts containing cylindrical holes with diameters of 3, 6, 9 and 12 mm. These holes on the thyroid glands can be filled with different activities of radionuclides to serve as hot and cold spots for quality control of nuclear medicine images. The results show that the designed phantom is applicable in different fields such as nuclear image quality and resolution tests, dosimetry and iodine thyroid uptake estimation in nuclear medicine departments, and nuclear emergency monitoring.

Incidental detection of COVID-19 associated pneumonia by thyroid scintigraphy.

This report presents a case of a 49-year-old woman with complaint of sore throat and front neck pain, who referred to a hospital for thyroid scan due to suppressed TSH level (0.005 mU/L). Diffuse and bilateral lungs uptake in the scan was noticed incidentally. The patient had positive history of COVID-19 symptoms. Multifocal and bilateral ground-glass opacities (GGOs) in both lungs were compatible with typical features of lung involvement in COVID-19-associated pneumonia.

Incidental detection of COVID-19 associated pneumonia by [99mTc]UBI scintigraphy.

A 31-year-old woman who had multiple orthopedic surgeries on the left lower limb and recently suffered from pain and redness in the lateral left lower thigh was referred to the hospital to rule out osteomyelitis by [99mTc]UBI scintigraphy. Except soft tissue inflammation in the mentioned region, the scan showed significant and diffuse both lungs uptake incidentally. The patient had experienced symptoms of COVID-19 disease recently. Chest HRCT scan also revealed multiple segmental ground-glass opacities (GGOs) which were typical features for lung involvement of COVID-19 associated pneumonia.

Tumor volume-adapted SUVN as an alternative to SUVpeak for quantification of small lesions in PET/CT imaging: a proof-of-concept study.

PURPOSE: SUVpeak is a recommended quantification metric except for small lesions. We aimed to assess the averaged standard uptake value (SUVN) as an alternative to SUVpeak for small-lesion quantification. MATERIALS AND METHODS: NEMA-like phantom images were reconstructed using OSEM, OSEM + PSF, OSEM + TOF and OSEM + TOF + PSF with two post-smoothing Gaussian filters for different background activity levels. SUVmax, SUVN (N = 5, 10, 15, 20, 25, 30, 35 or 40 hottest voxels), and SUVpeak, relative percent error, contrast recovery, and volume recovery coefficients were quantified and assessed. RESULTS: SUVN did not have the limitations of SUVpeak for smaller lesions. In the smallest insert at 2.68 kBq/ml, optimum N values for OSEM, OSEM + PSF, OSEM + TOF and OSEM + TOF + PSF were 10, 5, 15, and 10 for SUVN, respectively. The same N values were obtained for metabolic tumor volumes (MTVs) for all reconstruction algorithms. At 5.30 kBq/ml, N = 5 was optimum for SUVN and MTVs. For the larger inserts, the optimum N increased and tended towards the maximum (similar to SUVpeak). CONCLUSIONS: SUVN is more accurate than SUVmax or SUVpeak for small lesions, while being as accurate in larger ones. This harmonizing capacity of SUVN can be beneficial for the quantitative analysis of small tumor volumes.

177Lu/153Sm-Ethylenediamine Tetramethylene Phosphonic Acid Cocktail: A Novel Palliative Treatment for Patients with Bone Metastases.

Background: Production of effective, low-cost, and efficient radiopharmaceuticals is an important task and requires further research and clinical studies. In this clinical trial, safety and efficacy of 177Lu/153Sm-ethylenediamine tetramethylene phosphonic acid (EDTMP) cocktail has been evaluated for pain relief of bone metastases. Materials and Methods: Twenty-five patients with the mean age of 55.5 ± 15.8 years participated in this study. Patients received a total dose of 37 MBq/kg. Pain and performance assessments were followed using a Brief Pain Inventory form. Complete blood count and renal and liver function tests were also performed up to 12 weeks postadministration. Results: Eighteen patients (72%) demonstrated complete pain relief (relief = 100%) and approximately all patients (96%) experienced significant improvement in their quality of life. No grade IV hematological toxicity was observed during the 12-week follow-up period, and grade III toxicity was seen in 1 patient only. In addition, no abnormalities were seen in renal and liver function during the follow-up period. Conclusions: There were no considerable complications after administration of 177Lu/153Sm EDTMP; this cocktail seems to be a safe and effective treatment for bone pain palliation in patients with skeletal metastases and improves the quality of life.

Unusual Displacement of Urinary Bladder by a Dilated Rectosigmoid Colon on Bone Scintigraphy.

A 7-year-old boy with chief complaint of chronic pelvic pain was referred to our nuclear medicine department for bone scintigraphy. The images showed a focus of radiotracer activity in the right side of pelvic cavity, which is further confirmed as urinary bladder by single-photon emission computed tomography (SPECT) and delayed images. Because of high possibility of mass effect in pelvic cavity, pelvic magnetic resonance imaging (MRI) was performed, and it revealed an unusual dilatation of rectosigmoid colon with no evidence of pelvic mass.

Metastatic Bone Pain Palliation using (177)Lu-Ethylenediaminetetramethylene Phosphonic Acid.

(177)Lu-ethylenediaminetetramethylene phosphonic acid (EDTMP) is presently suggested as an excellent bone seeking radionuclide for developing metastatic bone pain (MBP) palliation agent owing to its suitable nuclear decay characteristics. To find the exact dosage and its efficiency, this clinical study was performed on the human being, using (177)Lu-EDTMP for MBP palliation. (177)Lu-EDTMP was prepared by Iran, atomic energy organization. Thirty consecutive patients with determined tumors, incontrollable MBP, and positive bone scan at 4 weeks before the beginning of the study participated in this study in the nuclear medicine ward. (177)Lu-EDTMP in the form of sterile slow IV injection was administered with a dose of 29.6 MBq/kg. Short form of brief pain inventory questionnaire was used to evaluate the efficiency of the intervention. Questionnaires were filled out by an expert nuclear physician every 2 weeks while the cell blood count was also checked every 2 weeks up to 12 weeks for evaluation of bone marrow suppression and hematological toxicity. Furthermore, whole body scan was done at days 1, 3, and 7. Twenty-five patients showed a significant pain relief since 2 weeks after the injection, and continued until the end of the follow up period (12 weeks). There were no significant early complications such as bone marrow suppression, hematological toxicity, and no systemic adverse effects. No complication was observed in renal function. Twenty one patients showed flare phenomenon that was started after the 12.2 ± 1.78 h lasting for 38.4 ± 23.08. Sixteen patients (53%) were completely treated; nine patients (30%) showed a partial response, and five patients (17%) had no response to treatment. Total response to treatment was achieved in 25 patients (83%). At the end of the evaluation, no bone marrow suppression or hematologic toxicity was observed. (177)Lu-EDTMP has shown suitable physical and biological properties with good results in long term bone pain relief for patients with bone metastasis.

The effect of a new impregnated gauze containing bentonite and halloysite minerals on blood coagulation and wound healing.

In recent years, a wide variety of research has been carried out in the field of novel technologies to stop severe bleeding. In several studies, coagulation properties of minerals such as zeolite, bentonite and halloysite have been proven. In this study, the effect of a new impregnated sterile gauze containing bentonite and halloysite minerals was studied on blood coagulation and wound healing rate in male Wistar rats. Initially, impregnated sterile gauze was prepared from the mixture of bentonite and halloysite minerals and petroleum jelly (Vaseline). Then, the effect of gauze was studied on the blood coagulation time and wound healing process in 40 Wistar rats. SPSS software was used for data analysis and P values less than 0.05 were considered significant. The coagulation time of 81.10 ± 2.532 s in the control group and 33.00 ± 1.214 s in the study group (bentonite-halloysite treated) were reported (P < 0.0005). Time for complete wound healing in the group, which is treated with impregnated sterile pads, was calculated approximately from 10 to 12 days. However, in the control group, there was no complete wound healing (P < 0.0005). According to the results of the present study, topical application of the bentonite-halloysite impregnated sterile gauze significantly decreases the clotting time and increase the wound healing rate.