BACKGROUND: At present, biopsy is essential for the diagnosis of prostate cancer (PCa) before radical prostatectomy (RP). However, with the development of prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA PET/CT) and multiparametric magnetic resonance imaging (mpMRI), it might be feasible to avoid biopsy before RP. Herein, we aimed to explore the feasibility of avoiding biopsy before RP in patients highly suspected of having PCa after assessment of PSMA PET/CT and mpMRI. METHODS: Between December 2017 and April 2022, 56 patients with maximum standardized uptake value (SUVmax) of ≥4 and Prostate Imaging Reporting and Data System (PI-RADS) ≥4 lesions who received RP without preoperative biopsy were enrolled from two tertiary hospitals. The consistency between clinical and pathological diagnoses was evaluated. Preoperative characteristics were compared among patients with different pathological types, T stages, International Society of Urological Pathology (ISUP) grades, and European Association of Urology (EAU) risk groups. RESULTS: Fifty-five (98%) patients were confirmed with PCa by pathology, including 49 (89%) with clinically significant prostate cancer (csPCa, defined as ISUP grade ≥2 malignancy). One patient was diagnosed with high-grade prostatic intraepithelial neoplasia (HGPIN). CsPCa patients, compared with clinically insignificant prostate cancer (cisPCa) and HGPIN patients, were associated with a higher level of prostate-specific antigen (22.9 ng/mL vs . 10.0 ng/mL, P = 0.032), a lower median prostate volume (32.2 mL vs . 65.0 mL, P = 0.001), and a higher median SUVmax (13.3 vs . 5.6, P <0.001). CONCLUSIONS It might be feasible to avoid biopsy before RP for patients with a high probability of PCa based on PSMA PET/CT and mpMRI. However, the diagnostic efficacy of csPCa with PI-RADS ≥4 and SUVmax of ≥4 is inadequate for performing a procedure such as RP. Further prospective multicenter studies with larger sample sizes are necessary to confirm our perspectives and establish predictive models with PSMA PET/CT and mpMRI.
Humans ; Male ; Prostatectomy/methods* ; Prostatic Neoplasms/diagnosis* ; Middle Aged ; Aged ; Positron Emission Tomography Computed Tomography/methods* ; Biopsy ; Multiparametric Magnetic Resonance Imaging ; Prostate-Specific Antigen/metabolism*

Artificial intelligence (AI), particularly deep learning, has demonstrated remarkable performance in medical imaging across a variety of modalities, including X-ray, computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, positron emission tomography (PET), and pathological imaging. However, most existing state-of-the-art AI techniques are task-specific and focus on a limited range of imaging modalities. Compared to these task-specific models, emerging foundation models represent a significant milestone in AI development. These models can learn generalized representations of medical images and apply them to downstream tasks through zero-shot or few-shot fine-tuning. Foundation models have the potential to address the comprehensive and multifactorial challenges encountered in clinical practice. This article reviews the clinical applications of both task-specific and foundation models, highlighting their differences, complementarities, and clinical relevance. We also examine their future research directions and potential challenges. Unlike the replacement relationship seen between deep learning and traditional machine learning, task-specific and foundation models are complementary, despite inherent differences. While foundation models primarily focus on segmentation and classification, task-specific models are integrated into nearly all medical image analyses. However, with further advancements, foundation models could be applied to other clinical scenarios. In conclusion, all indications suggest that task-specific and foundation models, especially the latter, have the potential to drive breakthroughs in medical imaging, from image processing to clinical workflows.
Humans ; Artificial Intelligence ; Deep Learning ; Diagnostic Imaging/methods* ; Magnetic Resonance Imaging ; Tomography, X-Ray Computed ; Positron-Emission Tomography

OBJECTIVE: To investigate the prognostic value of ¹⁸ F-deoxyglucose (FDG) PET/CT metabolic parameters combined with clinicopathological features for newly diagnosed diffuse large B-cell lymphoma (DLBCL) before treatment, and analyze the relationship between tumor metabolic volume (MTV), total lesion glycolysis (TLG) and clinicopathological features. METHODS: The clinical data of 120 patients with pathologically confirmed DLBCL were retrospectively analyzed and ¹⁸F-FDG PET/CT was performed 1 week before treatment. The metabolic parameters including SUVmax, SUVmean, tumor-to-blood standardized uptake value ratio (TBR), tumor-to-liver standardized uptake value ratio (TLR) were obtained. MTV and TLG of the lesions were obtained with 41% of SUVmax as the threshold, and the correlation of MTV and TLG with clinicopathological features were analyzed. Progression-free survival (PFS) was calculated by follow-up for 6-153 months. Receiver operating characteristic (ROC) curve, chi-square test, Kaplan-Meier test, log-rank test and Cox proportional hazards model were used to analyze the date. RESULTS: The optimum cut-off values of the SUVmax, MTV, TLG, TBR and TLR for predicting tumor progression were 22.25, 256.05, 5 232.67, 12.97 and 10.60, respectively. The patients were divided into two groups according to the above cut-off values, respectively. Kaplan-Meier survival analysis showed that there were statistically significant differences in PFS between the two group (all P <0.05). The MTV and TLG values were correlated with NCCN-IPI score, Ann Arbor stage, serum lactate dehydrogenase level, and C-MYC, BCL-2, BCL-6 gene rearrangement (all P <0.05). Univariate analysis showed that NCCN-IPI score >3, C-MYC, BCL-2, BCL-6 gene rearrangement positive, SUVmax≥22.25, MTV≥256.05 cm³, TLG≥5 232.67 g and TBR≥12.97 were adverse factors for prognosis (HR: 1.949-5.759, all P <0.05). Multivariate Cox regression analysis showed that C-MYC, BCL-2 gene rearrangement positive and TLG≥5 232.67 g were all independent risk factors affecting PFS (HR: 4.660, 3.350, 4.031, all P <0.05). CONCLUSION The ¹⁸F-FDG PET/CT metabolic parameters SUVmax, MTV, TLG, TBR and TLR can be used as important indicators to predict PFS of DLBCL patients, and combining clinicopathological features can better predict the prognosis of patients.
Humans ; Lymphoma, Large B-Cell, Diffuse/diagnosis* ; Fluorodeoxyglucose F18 ; Positron Emission Tomography Computed Tomography ; Prognosis ; Retrospective Studies ; Male ; Female ; Middle Aged ; Adult

OBJECTIVE: To analyze the correlation between baseline ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) and circulating tumor DNA (ctDNA) parameters in diffuse large B-cell lymphoma (DLBCL) and compare the value of the two methods in the prognosis assessment of DLBCL. METHODS: A total of 50 DLBCL patients confirmed by pathology, including 26 males and 24 females, with a median age of 55.5(43.5, 64.0) years from August 2018 to April 2021 were retrospectively analyzed. PET/CT parameters, including maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), total lesion glycolysis (TLG), ctDNA parameters, including mutation number, mutation gene number, mean variant allele frequency (meanVAF), and clinical data of patients were collected. The relationship between PET/CT, ctDNA parameters and patient clinical features was analyzed, as well as the correlation between PET/CT and ctDNA parameters. The diagnostic efficacy of PET/CT and ctDNA parameters was compared. Patients were followed up for 36-69 months. Progression-free survival (PFS) was calculated, and survival analysis was performed. RESULTS: PET/CT parameters all had good correlation with ctDNA parameters, among which MTV was moderately correlated with mutation number, mutation gene number, and meanVAF (r_s=0.72, 0.64, 0.71), TLG was strongly correlated with mutation number (r_s=0.83) and moderately correlated with mutation gene number and mean VAF (r_s=0.72, 0.79), while SUVmax was weakly correlated with mutation number, mutation gene number and meanVAF (r_s=0.47, 0.46, 0.47). PET/CT parameters and ctDNA parameters showed no statistically significant differences in predicting the prognosis of DLBCL and area under the curve (AUC) of receiver operating characteristic (ROC) (P >0.05). However, the specificity of MTV and TLG in predicting prognosis of 1-, 2- and 3-year PFS was better than that of meanVAF (all P < 0.05), while the sensitivity of meanVAF in predicting prognosis of 1-, 2- and 3-year PFS was better than that of MTV (all P < 0.05). The optimal cut-off values of SUVmax, MTV, TLG, mutation number, mutation gene number and meanVAF in predicting tumor progression were obtained using ROC curve analysis. Patients were divided into high and low expression groups according to the cut-off values and survival analysis was performed. The results of survival analysis showed that there were statistically significant differences in PFS between the high and low expression groups (all P < 0.05). CONCLUSION Baseline ¹⁸F-FDG PET/CT and ctDNA parameters can both predict the prognosis of DLBCL, and are equally valuable in the evaluation of DLBCL prognosis.
Humans ; Lymphoma, Large B-Cell, Diffuse/diagnosis* ; Positron Emission Tomography Computed Tomography ; Fluorodeoxyglucose F18 ; Middle Aged ; Prognosis ; Female ; Male ; Circulating Tumor DNA ; Retrospective Studies ; Adult ; Mutation

Sweet syndrome (acute febrile neutrophilic dermatosis) is a relatively rare inflammatory di-sease, which is characterized by the sudden appearance of tender erythematous skin lesions, often accompanied by pyrexia and elevated neutrophil count. The pathogenesis is not clear yet. Recently, multiple studies have found the association between Sweet syndrome and infections, autoimmune diseases, malignant tumors and the application of multiple drugs. According to different causes, Sweet syndrome can be divided into three types: classical (or idiopathic) Sweet syndrome, malignancy-associated Sweet syndrome and drug-induced Sweet syndrome. Classical Sweet syndrome usually presents in women between the age of 30 to 50 years and may be related to infection, inflammatory bowel disease, or pregnancy. The clinical symptoms typically respond promptly after corticosteroid therapy. The major diagnostic criteria of classical Sweet syndrome include sudden painful erythematous skin lesions, histopathologic evidence of a dense neutrophilic infiltrate without evidence of leukocytoclastic vasculitis; minor criteria include pyrexia over 38 ℃, association with hematologic or visceral malignancies, inflammatory diseases, pregnancy or preceded by infection, prompt response to systemic glucocorticoid or potassium iodide treatment, abnormal laboratory values (three of four: erythrocyte sedimentation rate >20 mm/h, positive C-reactive protein, >8.0×10⁹/L leukocytes, >70% neutrophils). The presence of both major criteria and two of the four minor criteria are required to diagnose classical Sweet syndrome. As for the malignancy-associated Sweet syndrome, skin lesions can be found precede, follow, or at the same time with the diagnosis of hematologic malignancy or a solid tumor. At present, ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) is commonly used as a positron emission tomography computed tomography (PET/CT) imaging agent for diagnosing and screening malignant tumors. Therefore, most of the case reports on the ¹⁸F-FDG PET/CT manifestations of Sweet syndrome are malignancy-associated. Even classical Sweet syndrome is often accompanied by inflammatory bowel disease, autoimmune diseases, etc. Therefore, for patients with suspected or confirmed Sweet syndrome, it is necessary to take ¹⁸F-FDG PET/CT examination to clarify the general condition, whether it is for patients with malignant signs such as elevated tumor markers values and weight loss, or for patients with classical Sweet syndrome to exclude underlying inflammatory diseases. ¹⁸F-FDG PET/CT is often able to detect the solid tumor early, and assess the degree of hematologic malignancy and inflammatory disease. This study reported a classical Sweet syndrome case associated with inflammatory bowel disease, which was confirmed with skin and intestinal histological examination. The clinical manifestations, laboratory values, ¹⁸F-FDG PET/CT manifestations of the patient related diseases were reported, which was to improve nuclear medicine physicians' understanding of Sweet syndrome. Early diagnosis and treatment can often achieve excellent clinical effect.
Humans ; Sweet Syndrome/diagnostic imaging* ; Fluorodeoxyglucose F18 ; Positron Emission Tomography Computed Tomography ; Female

OBJECTIVES: Non-small cell lung cancer (NSCLC) is associated with poor prognosis, with 30% of patients diagnosed at an advanced stage. Mutations in the EGFR and KRAS genes are important prognostic factors for NSCLC, and targeted therapies can significantly improve survival in these patients. Although tissue biopsy remains the gold standard for detecting gene mutations, it has limitations, including invasiveness, sampling errors due to tumor heterogeneity, and poor reproducibility. This study aims to develop machine learning models based on radiomic features to predict EGFR and KRAS gene mutation status in NSCLC patients, thereby providing a reference for precision oncology. METHODS: Imaging and mutation data from eligible NSCLC patients were obtained from the publicly available Lung-PET-CT-Dx dataset in The Cancer Imaging Archive (TCIA). A three-dimensional-convolutional neural network (3D-CNN) was used to extract imaging features from the regions of interest (ROI). The LightGBM algorithm was employed to build classification models for predicting EGFR and KRAS gene mutation status. Model performance was evaluated using 5-fold cross-validation, with receiver operator characteristic (ROC) curves, area under the curve (AUC), accuracy, sensitivity, and specificity used for validation. RESULTS: The models effectively predicted EGFR and KRAS mutations in NSCLC patients, achieving an AUC of 0.95 for EGFR mutations and 0.90 for KRAS. The models also demonstrated high accuracy (EGFR 89.66%; KRAS 87.10%), sensitivity (EGFR 93.33%; KRAS 87.50%), and specificity (EGFR 85.71%; KRAS 86.67%). CONCLUSIONS A radiogenomics-machine learning predictive model can serve as a non-invasive tool for anticipating EGFR and KRAS gene mutation status in NSCLC patients.
Humans ; Carcinoma, Non-Small-Cell Lung/diagnostic imaging* ; Lung Neoplasms/diagnostic imaging* ; Mutation ; Proto-Oncogene Proteins p21(ras)/genetics* ; ErbB Receptors/genetics* ; Machine Learning ; Positron Emission Tomography Computed Tomography ; Female ; Male ; Neural Networks, Computer ; Middle Aged ; Aged

Prostate cancer is the second most common cancer in men, accounting for 14.1% of new cancer cases in 2020. The aggressiveness of prostate cancer is highly variable, depending on its grade and stage at the time of diagnosis. Despite recent advances in prostate cancer treatment, some patients still experience recurrence or even progression after undergoing radical treatment. Accurate initial staging and monitoring for recurrence determine patient management, which in turn affect patient prognosis and survival. Classical imaging has limitations in the diagnosis and treatment of prostate cancer, but the use of novel molecular probes has improved the detection rate, specificity, and accuracy of prostate cancer detection. Molecular probe-based imaging modalities allow the visualization and quantitative measurement of biological processes at the molecular and cellular levels in living systems. An increased understanding of tumor biology of prostate cancer and the discovery of new tumor biomarkers have allowed the exploration of additional molecular probe targets. The development of novel ligands and advances in nano-based delivery technologies have accelerated the research and development of molecular probes. Here, we summarize the use of molecular probes in positron emission tomography (PET), single-photon emission computed tomography (SPECT), magnetic resonance imaging (MRI), optical imaging, and ultrasound imaging, and provide a brief overview of important target molecules in prostate cancer.
Humans ; Male ; Prostatic Neoplasms/diagnosis* ; Molecular Probes ; Molecular Imaging/methods* ; Magnetic Resonance Imaging ; Positron-Emission Tomography ; Tomography, Emission-Computed, Single-Photon ; Ultrasonography ; Optical Imaging ; Biomarkers, Tumor ; Precision Medicine/methods*

OBJECTIVES: To evaluate the value of ⁶⁸Ga-DOTATATE and ¹⁸F-FDG PET/CT imaging in staging and treatment decision for gastroenteropancreatic neuroendocrine neoplasms (GEP-NEN). METHODS: This retrospective analysis was conducted in 49 patients with GEP-NEN undergoing ¹⁸F-FDG and ⁶⁸Ga-DOTATATE PET/CT imaging at our hospital from August, 2020 to March, 2023, including 34 newly diagnosed patients and 15 patients with recurrence or metastasis after treatment. GEP-NEN were classified into G1, G2, and G3 neuroendocrine tumors (NET) and neuroendocrine carcinomas (NEC) based on pathological typing. The detection efficiency were classified into 4 patterns based on the number of positive tumor lesions detected by the two tracers: ⁶⁸Ga-DOTATATE>¹⁸F-FDG (A); ⁶⁸Ga-DOTATATE=¹⁸F-FDG (B); ⁶⁸Ga-DOTATATE<¹⁸F-FDG (C); and complementation (D). The value of dual-modality imaging in staging and treatment decision were evaluated by visual analysis. RESULTS: In the 49 patients with GEP-NEN, ⁶⁸Ga-DOTATATE PET/CT was superior to ¹⁸F-FDG PET/CT for detecting systemic tumor lesions (P<0.001) and more sensitive for detecting primary/recurrent lesions, lymph node metastasis, liver metastasis, and bone metastasis (P<0.05), while ¹⁸F-FDG PET/CT had higher detection rates for lung metastasis and peritoneal metastasis (P<0.05). In terms of the detection efficiency, Pattern A was found in 46.9% (23/49) patients, Pattern B in 38.8% (19/49), Pattern C in 12.2% (6/49), and Pattern D in 2.0% (1/49). The complementary value of ¹⁸F-FDG PET/CT to ⁶⁸Ga-DOTATATE PET/CT was 0% in G1 NET patients (0/13), 8.3% in G2 NET patients (2/24), 50% in G3 NET patients (3/6), and 33.3% in NEC patients (2/6). 12.2% (6/49) of the patients had their staging confirmed or changed due to additional lesions detected by ¹⁸F-FDG PET/CT imaging, resulting subsequently in establishment or adjustment of their treatment plans. CONCLUSIONS ⁶⁸Ga-DOTATATE PET/CT imaging should be the primary choice for GEP-NEN patients. Additional ¹⁸F-FDG PET/CT imaging can potentially improve precision of staging and treatment decision-making for G2, G3 and NEC patients but provides virtually no clinical benefits for G1 NET patients.
Humans ; Positron Emission Tomography Computed Tomography/methods* ; Neuroendocrine Tumors/therapy* ; Pancreatic Neoplasms/therapy* ; Retrospective Studies ; Organometallic Compounds ; Stomach Neoplasms/therapy* ; Neoplasm Staging ; Fluorodeoxyglucose F18 ; Intestinal Neoplasms/therapy* ; Female ; Male ; Middle Aged ; Aged ; Adult

OBJECTIVE: To study the clinical, imaging, and pathological features of pulmonary lymphoma. METHODS: Patients with pulmonary lymphoma diagnosed by lung biopsy in Zhongda Hospital Affiliated to Southeast University from November 2013 to December 2020 were collected and divided into secondary pulmonary lymphoma (SPL) group and primary pulmonary lymphoma (PPL) group according to the primary site of lymphoma. The clinical characteristics, stages, imaging features, diagnostic methods and pathological types of the two groups were analyzed. RESULTS: A total of 22 patients were included, 10 cases were PPL and 12 cases were SPL. The main symptoms of the two groups were cough, dyspnea and chest pain. The proportion of stage III/IV patients and international prognostic index (IPI) in SPL group were significantly higher than those in PPL group (P<0.05). Chest high-resolution computed tomography (HRCT) mainly showed masses, nodules and consolidation in both groups. The proportions of single mass and air bronchial sign in PPL group were significantly higher than those in SPL group, while the proportions of multiple nodules, mediastinal/hilar lymphadenopathy and pleural effusion were significantly lower (P<0.05). The max standardized uptake value (SUV_max), peak standardized uptake value (SUV_peak), total lesion glycolysis (TLG) and metabolic tumor volume (MTV) of ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography/computed tomography (PET/CT) in PPL group were lower than those in SPL group, but the differences were not statistically significant (P>0.05). In PPL group, 8 cases were diagnosed by transbronchial lung biopsy (TBLB) and 2 cases by percutaneous lung puncture. In SPL group, 4 cases were diagnosed by TBLB, 7 cases by percutaneous lung puncture, and 1 case by surgery. 95.5% patients were diagnosed by non-surgical methods. The main pathological type of PPL was mucosa-associated lymphoid tissue (MALT) lymphoma, while that of SPL was diffuse large B-cell lymphoma (P<0.05). CONCLUSION The clinical symptoms of pulmonary lymphoma are nonspecific, but the chest HRCT has characteristic manifestations, which can also help to distinguish between SPL and PPL. ¹⁸F-FDG PET/CT is also a potential method to distinguish between SPL and PPL. TBLB and percutaneous lung puncture biopsy are reliable methods for the diagnosis of lung lymphoma. The main pathological type of PPL is MALT lymphoma, while that of SPL is diffuse large B-cell lymphoma.
Humans ; Positron Emission Tomography Computed Tomography ; Fluorodeoxyglucose F18 ; Lung Neoplasms/pathology* ; Lymphoma, Large B-Cell, Diffuse/pathology* ; Lymphoma, B-Cell, Marginal Zone/diagnosis* ; Prognosis ; Retrospective Studies

OBJECTIVE: Current mainstream PET scattering correction methods are introduced and evaluated horizontally, and finally, the existing problems and development direction of scattering correction are discussed. METHODS: Based on NeuWise Pro PET/CT products of Neusoft Medical System Co. Ltd. , the simulation experiment is carried out to evaluate the influence of radionuclide distribution out of FOV (field of view) on the scattering estimation accuracy of each method. RESULTS: The scattering events produced by radionuclide out of FOV have an obvious impact on the spatial distribution of scattering, which should be considered in the model. The scattering estimation accuracy of Monte Carlo method is higher than single scatter simulation (SSS). CONCLUSIONS Clinically, if the activity of the adjacent parts out of the FOV is high, such as brain, liver, kidney and bladder, it is likely to lead to the deviation of scattering estimation. Considering the Monte Carlo scattering estimation of the distribution of radionuclide out of FOV, it's helpful to improve the accuracy of scattering distribution estimation.
Positron Emission Tomography Computed Tomography ; Scattering, Radiation ; Computer Simulation ; Brain ; Monte Carlo Method ; Phantoms, Imaging ; Image Processing, Computer-Assisted