The primary endpoint of this study is to establish a reliable SUVR cutoff threshold to distinguish patients with Alzheimer’s disease (AD), excluding those with mild cognitive impairment (MCI), from normal control (NC) individuals using [18F]florapronol PET imaging and deep learning-based automated quantification software. The secondary endpoint is to evaluate whether combining partial volume correction (PVC) with SUVR analysis improves diagnostic accuracy in detecting AD. A total of 141 participants, including 55 AD patients (excluding MCI) and 86 NC controls, were enrolled. Each participant underwent [18F]florapronol PET imaging, and SUVR values were calculated for six amyloid-prone brain regions using deep learning-based software. SUVRs were computed with and without PVC, using the cerebellar cortex as the reference region. Receiver operating characteristic (ROC) analysis identified optimal SUVR thresholds for distinguishing AD (excluding MCI) from NC and for determining visual positivity. Age-matched subgroup analyses ensured consistent diagnostic performance across different age groups. In the full cohort (n = 141), visual analysis achieved a sensitivity of 90.9

Background This study aimed to evaluate the biodistribution of 64 Cu-DOTA-rituximab and its diagnostic feasibility for lymphoma using CD20-targeted 64 Cu-DOTA-rituximab PET/computed tomography (PET/CT). Methods A prospective study involving six patients diagnosed with lymphoma was conducted between January 2022 and January 2023. These patients underwent 18 F-fluorodeoxyglucose ( 18 F-FDG) and 64 Cu-DOTA-rituximab PET/CT scans. 64 Cu-DOTA-rituximab PET/CT images were acquired at 1, 24, and 48 h after administering 64 Cu-DOTA-rituximab to assess the biodistribution and dosimetry over time. The observed lymph nodes were categorized into specific regions, including cervical and supraclavicular, axillary and infraclavicular, mediastinal, hilar, abdominal paraaortic and retroperitoneal, iliac, mesenteric, and inguinal regions, to compare the diagnostic ability of 18 F-FDG and 64 Cu-DOTA-rituximab PET/CT in detecting lymphoma lesions. Furthermore, the tumor-to-background ratio was calculated and compared with the maximum standardized uptake (SUV max ) of the tumors and the mean standardized uptake (SUV mean ) of normal organs. Internal radiation dosimetry was determined using the OLINDA/EXM software. Results 64 Cu-DOTA-rituximab uptake in lymph nodes associated with lymphoma progressively increased from 1 to 48 h after injection. In contrast, 64 Cu-DOTA-rituximab uptake in normal organs, such as blood, lung, kidney, bladder, muscle, bone, and brain, decreased over time, whereas it increased in the liver and spleen. When it comes to the comparison between 64 Cu-DOTA-rituximab and 18 F-FDG, the SUV max of tumors was higher on 64 Cu-DOTA-rituximab PET/CT (18.1 ± 8.3) than on 18 F-FDG PET/CT (5.2 ± 1.5). Additionally, the tumor-to-background ratio, measured using the SUV mean of normal muscles, was higher on 64 Cu-DOTA-rituximab PET/CT (55.7 ± 31.0) than on 18 F-FDG PET/CT (8.6 ± 2.8). No adverse events related to 64 Cu-DOTA-rituximab injection were reported. Conclusion The results of this study demonstrate the feasibility of using 64 Cu-DOTA-rituximab PET/CT to evaluate the CD20 expression. The increased 64 Cu-DOTA-rituximab uptake in lymph nodes associated with tumors, higher SUV max , and tumor-to-muscle ratios observed with 64 Cu-DOTA-rituximab PET/CT compared with 18 F-FDG PET/CT, highlight the diagnostic potential of this imaging modality.

To assess the trends and disparities in the utilization of F-18 fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) in Korea between 2018 and 2022, with a focus on disease classification, patient demographics, and regional distribution. This national surveillance retrospective study uses data from the Health Insurance Review and Assessment Service (HIRA) database, which includes all FDG PET/CT examinations conducted in Korea from 2018 to 2022. Disease classifications, cancer types, age groups, gender, and geographic regions were analyzed using descriptive statistics. Utilization rates per 100,000 population were calculated for regional comparisons. FDG PET/CT utilization increased by 25.4

AIM:This study aimed to evaluate the safety and efficacy of 131 I-rituximab in patients with relapsed or refractory follicular or mantle cell lymphoma.METHODS:Twenty-four patients with relapsed or refractory follicular or mantle cell lymphoma were administered unlabeled rituximab (70 mg) immediately before receiving a therapeutic dose of 131 I-rituximab. Contrast-enhanced 18F-fluorodeoxyglucose positron emission tomography/computed tomography was used a month later to assess tumor response.RESULTS:This study enrolled 24 patients between June 2012 and 2022. Depending on how they responded to radioimmunotherapy (RIT), 131 I-rituximab was administered one to five times. Of the 24 patients, 9 achieved complete response after RIT and 8 achieved partial response. The median progression-free and overall survival was 5.9 and 37.9 months, respectively. During the follow-up period of 64.2 months, three patients were diagnosed with a secondary malignancy. Among treatment-related adverse events, hematologic toxicities were common, and grade 3-4 thrombocytopenia and neutropenia were reported in 66.6% of cases.CONCLUSION:131 I-rituximab has an effective and favorable safety profile in patients with relapsed or refractory follicular lymphoma and mantle cell lymphoma. This suggests that RIT may also be considered a treatment option for patients with relapsed or refractory follicular lymphoma and mantle cell lymphoma.

Background: Radioimmunotherapy (RIT) is a rare treatment option for relapsed or refractory B-cell non-Hodgkin’s lymphoma (NHL). We investigated the safety and efficacy of 131 I-rituximab in patients with relapsed or refractory marginal zone lymphomas. Methods: Patients with pathologically confirmed marginal zone lymphoma who relapsed or were resistant to prior therapy were enrolled. The patients received 250 mg/m 2 of unlabeled rituximab immediately before receiving a therapeutic 131 I-rituximab dose. The primary endpoint was the objective response rate (ORR), and the secondary endpoints were toxicity assessment, progression-free survival (PFS), and overall survival (OS). Results: Ten patients (median age = 57.5 years; range = 32-71) were included. Owing to poor enrollment, only 10 of the initially intended 25 patients were included in the study, rendering it unfeasible to perform the primary endpoint analysis. Before RIT, patients received chemotherapy, with 40% (n = 4) receiving rituximab therapy. Median PFS and OS were 18.9 months (95% confidence interval [CI]: 0.0-38.9) and 100.0 months (95% CI: 39.8-160.1), respectively. The ORR was 90%, and the duration of response was 29.7 months (95% CI: 0.0-61.3). Considering a median follow-up of 78.5 months (95% CI: 42.7-114.3), 4 patients (40%) were diagnosed with secondary malignancy. Hematological toxicities were common treatment-related adverse events, and 60% and 50% of the patients experienced grade 3 to 4 thrombocytopenia and neutropenia, respectively. Conclusions: 131 I-rituximab showed marked efficacy in patients with relapsed or refractory marginal zone lymphoma, with a considerable risk of secondary malignancies during long-term follow-up. Radioimmunotherapy is not a recommended treatment option for relapsed or refractory marginal zone lymphoma but may be considered when other treatment options are not feasible.

Purpose To evaluate the prognostic value of pretreatment 18F-FDG PET/CT after consolidation therapy of 131I-rituximab in patients with diffuse large B-cell lymphoma (DLBCL) who had acquired complete remission after receiving chemotherapy. Methods Patients who were diagnosed with DLBCL via histologic confirmation were retrospectively reviewed. All patients had achieved complete remission after 6 to 8 cycles of R-CHOP (rituximab, cyclophosphamide, vincristine, doxorubicin, and prednisolone) chemotherapy after which they underwent consolidation treatment with 131I-rituximab. 18F-FDG PET/CT scans were performed before R-CHOP for initial staging. The largest diameter of tumor, maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were obtained from pretreatment 18F-FDG PET/CT scans. Receiver-operating characteristic curves analysis was introduced for assessing the optimal criteria. Kaplan-Meier curve survival analysis was performed to evaluate both relapse free survival (RFS) and overall survival (OS). Results A total of 15 patients (12 males and 3 females) with a mean age of 56 (range, 30–73) years were enrolled. The median follow-up period of these patients was 73 months (range, 11–108 months). Four (27%) patients relapsed. Of them, three died during follow-up. Median values of the largest tumor size, highest SUVmax, MTV, and TLG were 5.3 cm (range, 2.0–16.4 cm), 20.2 (range, 11.1–67.4), 231.51 (range, 15–38.34), and 1277.95 (range, 238.37–10341.04), respectively. Patients with SUVmax less than or equal to 16.9 showed significantly worse RFS than patients with SUVmax greater than 16.9 (5-year RFS rate: 60% vs. 100%, p = 0.008). Patients with SUVmax less than or equal to 16.9 showed significantly worse OS than patients with SUVmax greater than 16.9 (5-year OS rate: 80% vs. 100% p = 0.042). Conclusion Higher SUVmax at pretreatment 18F-FDG PET/CT was associated with better relapse free survival and overall survival in DLBCL patients after consolidation therapy with 131I-rituximab. However, because this study has a small number of patients, a phase 3 study with a larger number of patients is needed for clinical application in the future.

A 45-year-old woman diagnosed with breast cancer reported disease progression in the form of metastatic lung and recurrent breast lesions following chemotherapy and human epidermal growth factor receptor 2 (HER2)-targeted therapy. The patient underwent 64Cu-tetra-azacyclododecanetetra-acetic acid (DOTA)-trastuzumab positron emission tomography/computed tomography (PET/CT) to evaluate the HER2 expression status. 64Cu-DOTA-trastuzumab accumulated in the left breast and lymph nodes but not in the lung lesions. Following trastuzumab emtansine treatment, there was a significant improvement in the lesions with 64Cu-DOTA-trastuzumab accumulation. However, the lesions that did not accumulate 64Cu-DOTA-trastuzumab aggravated. Therefore, it was concluded that 64Cu-DOTA-trastuzumab PET/CT can be used to predict the outcome of HER2-targeted treatment by evaluating HER2 expression in breast cancer patients.

Background: The goal of this article was to investigate the feasibility of Cu-64 labeling in prostate-specific membrane antigen imaging and therapy (PSMA I&T) for PSMA positron emission tomography (PET) imaging and biodistribution evaluation. Materials and Methods: PSMA I&T was labeled with Cu-64, and stability in human and mouse sera was evaluated. Prostate cancer cell lines were used for specific uptake assays (22RV1 for PSMA-positive, PC-3 for -negative). Both PC-3 and 22RV1 cells were transplanted into the left and right thighs in a mouse for PET/computed tomography (CT) imaging. Biodistribution was performed using 22RV1 tumor models. Results: Labeling yield (decay corrected) of Cu-64-PSMA I&T was more than 95% compared to the free Cu-64 peak. The serum stability of Cu-64-PSMA I&T was maintained at more than 90% until 60 h. Regarding the specific binding of Cu-64-PSMA I&T, 22RV1 cells showed 7.5-fold higher than PC-3 cells (p < 0.001). On PET/CT imaging, more specific Cu-64-PSMA I&T uptake was observed in 22RV1 tumors than in PC-3 tumors. In the PSMA blocking study using 2-phosphonomethoxypropyl adenine (2-PMPA), the Cu-64-PSMA I&T signal significantly decreased in the 22RV1 tumor region. In the biodistribution study, the kidney uptake was the highest among all organs at 2 h (52.6 +/- 20.8%ID/g) but sharply decreased at 24 and 48 h. Also, the liver showed similar uptake over time (range, 10-12%ID/g). On the contrary, Cu-64-PSMA I&T uptake of the tumors increased with time and peaked at 48 h (5.6 +/- 0.1%ID/g). Conclusions: PSMA I&T labeled with Cu-64 showed the feasibility of the PSMA specific PET imaging through in vitro and in vivo studies. Furthermore, Cu-64-PSMA I&T might be considered as the candidate of future clinical trial.

Purpose The aim of the present study was to obtain information about distribution, radiation dosimetry, toxicity, and pharmacokinetics of O-[F-18]fluoromethyl-d-tyrosine (d-F-18-FMT), an amino acid PET tracer, in patients with brain tumors. Patients and Methods A total of 6 healthy controls (age = 19-25 years, 3 males and 3 females) with brain PET images and radiation dosimetry and 12 patients (median age = 60 years, 6 males and 6 females) with primary (n = 5) or metastatic brain tumor (n = 7) were enrolled. We acquired 60-minute dynamic brain PET images after injecting 370 MBq of d-F-18-FMT. Time-activity curves of d-F-18-FMT uptake in normal brain versus brain tumors and tumor-to-background ratio were analyzed for each PET data set. Results Normal cerebral uptake of d-F-18-FMT decreased from 0 to 5 minutes after injection, but gradually increased from 10 to 60 minutes. Tumoral uptake of d-F-18-FMT reached a peak before 30 minutes. Tumor-to-background ratio peaked at less than 15 minutes for 8 patients and more than 15 minutes for 4 patients. The mean effective dose was calculated to be 13.2 mu Sv/MBq. Conclusions Using d-F-18-FMT as a PET radiotracer is safe. It can distinguish brain tumor from surrounding normal brain tissues with a high contrast. Early-time PET images of brain tumors should be acquired because the tumor-to-background ratio tended to reach a peak within 15 minutes after injection.

Background: The purpose of this study was to evaluate both the biodistribution and safety of 64 Cu-1,4,7-triazacyclononane-1,4,7-triacetic acid (NOTA)-Trastuzumab, a novel 64 Cu-labelled positron emission tomography (PET) tracer for human epidermal growth factor receptor 2 (HER2) in patients with breast cancer. Methods: PET images at 1, 24, and 48 h after 296 MBq of 64 Cu-NOTA-Trastuzumab injection were obtained from seven patients with breast cancer. Both the primary tumors’ and metastatic lesions’ maximum standardized uptake value (SUV max ) was evaluated. The mean SUV max (SUV mean ) was evaluated in the other organs, including the blood pool, liver, kidney, muscle, spleen, bladder, and the lungs, as well as the bones. Moreover, the internal radiation dosimetry was calculated using the OLINDA/EXM software. Safety was assessed based on feedback regarding adverse reactions and safety-related issues within 1 month after 64 Cu-NOTA-Trastuzumab administration. Results: 64 Cu-NOTA-Trastuzumab PET images showed that the overall SUV mean values in each organ negatively correlated with time. The liver’s average SUV mean values were measured at 5.3 ± 0.7, 4.8 ± 0.6, and 4.4 ± 0.5 on 1 h, 24 h, and 48 h after injection, respectively. The average SUV mean blood values were measured at 13.1 ± 0.9, 9.1 ± 1.2, and 7.1 ± 1.9 on 1 h, 24 h, and 48 h after injection, respectively. The SUV max of HER2-positive tumors were relatively higher than HER2-negative tumors (8.6 ± 5.1 and 5.2 ± 2.8 on 48 h after injection, respectively). Tumor-to-background ratios were higher in the HER2-positive tumors than in the HER2-negative tumors. No adverse events related to 64 Cu-NOTA-Trastuzumab were reported. The calculated effective dose with a 296 MBq injection of 64 Cu-NOTA-Trastuzumab was 2.96 mSv. The highest absorbed dose was observed in the liver (0.076 mGy/MBq), followed by the spleen (0.063 mGy/MBq), kidney (0.044 mGy/MBq), and heart wall (0.044 mGy/MBq). Conclusions: 64 Cu-NOTA-Trastuzumab showed a specific uptake at the HER2-expressing tumors, thus making it a feasible and safe monitoring tool of HER2 tumor status in patients with breast cancer. Trial registration : CRIS, KCT0002790. Registered 02 February 2018, https://cris.nih.go.kr

To evaluate the biodistribution of [18F]Florastamin, a novel 18F-labelled positron emission tomography (PET) tracer for prostate-specific membrane antigen (PSMA) for the diagnosis of prostate cancer. PET was performed for five healthy controls and 10 patients with prostate cancer at 0, 10, 30, 70, and 120 mins after injecting 370 MBq of [18F]Florastamin. The maximum standardised uptake value (SUVmax) was evaluated in the primary tumour. The mean SUVmax (SUVmean) was evaluated in normal organs. Furthermore, the residence time was evaluated by assessing radioactivity in each organ. The internal radiation dosimetry was calculated using the OLINDA/EXM software. The SUVmax in primary tumours increased with time. A favourable tumour to background ratio was also observed over time. Multiple lymph nodes and bone metastases were also evaluated and showed a similar pattern to SUVmax in the primary tumour. In one patient, a tiny lymph node metastasis was identified using [18F]Florastamin PET, which was not observed using other modalities, and was histologically confirmed. The highest absorbed dose was observed in the kidney (0.062 ± 0.015 mGy/MBq), followed by the bladder (0.032 ± 0.013 mGy/MBq), liver (0.022 ± 0.006 mGy/MBq), and salivary gland (0.018 ± 0.006 mGy/MBq). The effective dose with a 370 MBq injection of [18F]Florastamin was 1.81 mSv. No adverse events related to [18F]Florastamin were reported. We identified a novel PSMA-targeted PET ligand, [18F]Florastamin, for imaging prostate cancer. [18F]Florastamin showed a high SUVmax and relatively high tumour to background ratio in both primary tumour and metastatic lesions, which suggests its high sensitivity to detect tumours without any adverse events. KCT0003924 registered at https://cris.nih.go.kr/ .

Abstract Background To propose a personalized therapeutic approach in osteosarcoma treatment, we assessed whether sequential [18F]FDG PET/CT (PET/CT) could predict the outcome of patients with osteosarcoma of the extremities after one cycle and two cycles of neoadjuvant chemotherapy. Methods A total of 73 patients with AJCC stage II extremity osteosarcoma treated with 2 cycles of neoadjuvant chemotherapy, surgery, and adjuvant chemotherapy were retrospectively analyzed in this study. All patients underwent PET/CT before (PET0), after 1 cycle (PET1), and after the completion of neoadjuvant chemotherapy (PET2), respectively. Maximum standardized uptake value (SUVmax) (corrected for body weight) and the % changes of SUVmax were calculated, and histological responses were evaluated after surgery. Receiver-operating characteristic (ROC) curve analyses and the Cox proportional hazards models were used to analyze whether imaging and clinicopathologic parameters could predict event-free survival (EFS). Results A total of 36 patients (49.3%) exhibited a poor histologic response and 17 patients (23.3%) showed events (metastasis in 15 and local recurrence in 2). SUVmax on PET2 (SUV2), the percentage change of SUVmax between PET0 and PET1 (Δ%SUV01), and between PET0 and PET2 (Δ%SUV02) most accurately predicted events using the ROC curve analysis. SUV2 (relative risk, 8.86; 95% CI, 2.25–34.93), Δ%SUV01 (relative risk, 5.97; 95% CI, 1.47–24.25), and Δ%SUV02 (relative risk, 6.00; 95% CI, 1.16–30.91) were independent predicting factors for EFS with multivariate analysis. Patients with SUV2 over 5.9 or Δ%SUV01 over − 39.8% or Δ%SUV02 over − 54.1% showed worse EFS rates than others (p < 0.05). Conclusions PET evaluation after 1 cycle of presurgical chemotherapy can predict the clinical outcome of extremity osteosarcoma. [18F]FDG PET, which shows a potential role in the early evaluation of the modification of timing of local control, can be a useful modality for early response monitoring of neoadjuvant chemotherapy.

This study aimed to investigate the predictive efficacy of positron emission tomography/computed tomography (PET/CT) and magnetic resonance imaging (MRI) for the pathological response of advanced breast cancer to neoadjuvant chemotherapy (NAC). The breast PET/MRI image deep learning model was introduced and compared with the conventional methods. PET/CT and MRI parameters were evaluated before and after the first NAC cycle in patients with advanced breast cancer [n = 56; all women; median age, 49 (range 26–66) years]. The maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were obtained with the corresponding baseline values (SUV0, MTV0, and TLG0, respectively) and interim PET images (SUV1, MTV1, and TLG1, respectively). Mean apparent diffusion coefficients were obtained from baseline and interim diffusion MR images (ADC0 and ADC1, respectively). The differences between the baseline and interim parameters were measured (ΔSUV, ΔMTV, ΔTLG, and ΔADC). Subgroup analysis was performed for the HER2-negative and triple-negative groups. Datasets for convolutional neural network (CNN), assigned as training (80%) and test datasets (20%), were cropped from the baseline (PET0, MRI0) and interim (PET1, MRI1) images. Histopathologic responses were assessed using the Miller and Payne system, after three cycles of chemotherapy. Receiver operating characteristic curve analysis was used to assess the performance of the differentiating responders and non-responders. There were six responders (11%) and 50 non-responders (89%). The area under the curve (AUC) was the highest for ΔSUV at 0.805 (95% CI 0.677–0.899). The AUC was the highest for ΔSUV at 0.879 (95% CI 0.722–0.965) for the HER2-negative subtype. AUC improved following CNN application (SUV0:PET0 = 0.652:0.886, SUV1:PET1 = 0.687:0.980, and ADC1:MRI1 = 0.537:0.701), except for ADC0 (ADC0:MRI0 = 0.703:0.602). PET/MRI image deep learning model can predict pathological responses to NAC in patients with advanced breast cancer.

Background and Purpose The aim of this study was to determine the diagnostic performance and safety of a new F-18-labeled amyloid tracer, F-18-FC119S. Methods This study prospectively recruited 105 participants, comprising 53 with Alzheimer's disease (AD) patients, 16 patients with dementia other than AD (non-AD), and 36 healthy controls (HCs). In the first screening visit, the Seoul Neuropsychological Screening Battery cognitive function test was given to the dementia group, while HC subjects completed the Korean version of the Mini Mental State Examination. Individuals underwent F-18-FC119S PET, F-18-fluorodeoxyglucose (FDG) PET, and brain MRI. The diagnostic performance of F-18-FC119S PET for AD was compared to a historical control (comprising previously reported and currently used amyloid-beta PET agents), F-18-FDG PET, and MRI. The standardized uptake value (SUV) ratio (ratio of the cerebral cortical SUV to the cerebellar SUV) was measured for each PET data set to provide semiquantitative analysis. All adverse effects during the clinical trial periods were monitored. Results Visual assessments of the F-18-FC119S PET data revealed a sensitivity of 92% and a specificity of 84% in detecting AD. F-18-FC119S PET demonstrated equivalent or better diagnostic performance for AD detection than the historical control, F-18-FDG PET (sensitivity of 80.0% and specificity of 76.0%), and MRI (sensitivity of 98.0% and specificity of 50.0%). The SUV ratios differed significantly between AD patients and the other groups, at 1.44 +/- 0.17 (mean +/- SD) for AD, 1.24 +/- 0.09 for non-AD, and 1.21 +/- 0.08 for HC. No clinically significant adverse effects occurred during the trial periods. Conclusions F-18-FC119S PET provides high sensitivity and specificity in detecting AD and therefore may be considered a useful diagnostic tool for AD.

1267 Purpose: Several methods of imaging analyses, including texture analysis and machine learning analysis, have been attempted to predict the prognosis of cancer patients. In particular, many studies have reported that several volumetric or texture features of baseline 18F-FDG PET are associated with the prognosis of cancer patients. In this study, we evaluated the performance of a deep learning algorithm using a convolutional neural network of baseline 18F-FDG PET to predict disease-free survival of soft tissue sarcoma. Methods: We analyzed a total of forty-eight patients with soft tissue sarcoma, whose clinical and imaging data were from the Cancer Imaging Archive (TCIA: http://doi.org/10.7937/K9/TCIA.2015.7GO2GSKS). The baseline 18F-FDG PET images were used and divided into the training and test sets for predicting disease-free survival. The number of the training and test sets were 40 and 8, respectively. The deep learning algorithm was based on the convolutional neural network (CNN). The input data for CNNs were PET images, which were cropped manually including the primary tumor. The results were categorized either as recurrence or metastasis or as disease-free state. The sensitivity, specificity, and accuracy in predicting disease-free survival were used to evaluate deep learning performance. A 5-fold cross-validation method was employed. Results: The sensitivity, specificity, and accuracy for predicting disease-free survival from the 5-fold cross-validation are as follows: for fold 0, 89.20%, 79.31%, and 90.47%; for fold 1, 94.20%, 75.29%, and 85.93%; for fold 2, 93.75%, 66.09%, and 81.66%; for fold 3, 91.07%, 84.48%, and 88.19%; for fold 4, 87.50%, 90.23%, and 88.69%, respectively. Cross-fold sensitivity was 92.68 ± 3.55%, specificity was 79.08 ± 9.17% and accuracy was 86.73 ± 3.10%. Conclusions: The deep learning method using baseline 18F-FDG PET showed good performance in predicting disease-free survival in patients with soft tissue sarcoma. The deep learning method also has the advantage of convenience because there are few considerations for the researchers in the analysis compared to other imaging analysis methods. Therefore, the deep learning method can be a useful tool in predicting the prognosis of cancers.