Pseudomyogenic hemangioendothelioma (PMH) is an extremely rare intermediate-grade vascular neoplasm. It often arises in the distal extremities and characteristically involves multiple tissue planes. It has a male predominance, and usually affects individuals in the second to fourth decades of life. Here we report a 54-year-old man who presented with an occipital mass lasting for three months. On imaging studies, the occipital bone tumors were expansile, well circumscribed and lytic, accompanied by adjacent scalp and subcutaneous nodules, with marked enhancement of the lesion upon contrast administration. FDG PET/CT demonstrated high FDG affinity in the lesion. Surgical pathology diagnosed as PMH.

BACKGROUND Post-radiation angiosarcoma (PRA) is a rare, invasive mesenchymal tumor associated with prior cancer radiotherapy. The diagnostic criteria for PRA include a history of radiation exposure, the development of a new malignant tumor with a long latency period within the irradiated field, and a histological type different from that of the primary malignancy if radiation was administered for the original cancer. Although PRA can arise in any part of the body, it most commonly occurs in the skin. Only a few cases of vascular sarcoma secondary to radiotherapy for cervical cancer have been reported, and reports of peritoneal angiosarcoma following pelvic irradiation for cervical cancer are exceedingly rare. CASE REPORT A 69-year-old woman presented with abdominal discomfort 22 years after receiving radiation therapy for cervical cancer. Imaging and laboratory evaluations failed to reveal a definitive cause, leading to suspicion of recurrence or metastasis of cervical cancer. The patient underwent surgical exploration; postoperative histopathology with immunohistochemistry confirmed the diagnosis of angiosarcoma. She subsequently received 4 cycles of chemotherapy with paclitaxel, carboplatin, and bevacizumab. However, 4 months after surgery, computed tomography revealed new lesions in the abdominal cavity and intestinal wall. The patient ultimately died of disease progression. CONCLUSIONS This case illustrates a rare instance of peritoneal angiosarcoma occurring after radiotherapy for cervical cancer. Clinicians should maintain a high index of suspicion for secondary malignancies in long-term cancer survivors presenting with new-onset peritoneal symptoms. Secondary peritoneal angiosarcoma should be considered in patients with prior radiation exposure and peritoneal involvement.

Pseudomyogenic hemangioendothelioma (PMH) is an extremely rare intermediate-grade vascular neoplasm. It often arises in the distal extremities and characteristically involves multiple tissue planes. It has a male predominance, and usually affects individuals in the second to fourth decades of life. Here we report a 54-year-old man who presented with an occipital mass lasting for three months. On imaging studies, the occipital bone tumors were expansile, well circumscribed and lytic, accompanied by adjacent scalp and subcutaneous nodules, with marked enhancement of the lesion upon contrast administration. FDG PET/CT demonstrated high FDG affinity in the lesion. Surgical pathology diagnosed as PMH.

We present a case of 46-year-old man who underwent surgery for a right thigh myxoma 20 years ago. Due to a discovery of cervical metastatic squamous cell carcinoma of unknown primary(CMSCCUP), a 18F-FDG-PET/CT examination was taken and it revealed the recurrence of the right thigh intramuscular myxomas and multiple fibrous dysplasia in the right lower extremity bones, ultimately leading to the diagnosis of Mazabraud’s syndrome. Due to its whole-body imaging capability, PET/CT can simultaneously detect the characteristic combination of fibrous dysplasia and intramuscular myxoma in Mazabraud’s syndrome and effectively rule out malignant possibilities. It serves as an important imaging modality for the diagnosis of this syndrome.

Gastric-type endocervical adenocarcinoma (GAS) is an aggressive, non-HPV-associated cervical adenocarcinoma that is often difficult to recognize preoperatively. This study aimed to characterize the integrated PET/CT phenotype of GAS and evaluate whether morphological, metabolic, serological, and explainable machine-learning features could support its differentiation from squamous cell carcinoma (SCC) and usual-type endocervical adenocarcinoma (UEA). This retrospective study included 144 patients with histologically confirmed cervical cancer who underwent pretreatment 18 F-FDG PET/CT, including 22 with GAS, 82 with SCC, and 40 with UEA. Clinical characteristics, serum tumor markers, PET/CT-derived morphological features, metabolic parameters, and dissemination-related variables were collected. Intergroup differences were assessed using appropriate statistical tests. Five machine-learning models were developed for histological differentiation, and model performance was evaluated using ROC analysis, classification metrics, calibration assessment, and decision curve analysis. SHAP analysis was used to interpret feature contributions. GAS demonstrated a distinctive PET/CT phenotype characterized by diffuse infiltrative growth, cystic morphology, intrauterine fluid accumulation, relatively lower FDG uptake, CA19-9 positivity, and more frequent distant and peritoneal metastasis. The median cervical lesion SUVmax was lower in GAS than in SCC and UEA, and similar trends were observed for liver-normalized and blood pool-normalized SUV ratios. Despite its relatively low metabolic activity, GAS showed more aggressive dissemination-related features. Among the machine-learning models, tree-based ensemble models showed better exploratory discriminative performance than Logistic Regression and multilayer perceptron. SHAP analysis indicated that growth pattern, cystic morphology, intrauterine fluid, cervical lesion SUVmax, liver SUV ratio, blood pool ratio, CA19-9, and SCC antigen were the main contributors to model prediction. GAS exhibits a recognizable PET/CT phenotype characterized by a descriptive metabolic–morphological mismatch, namely relatively low primary-tumor FDG uptake despite aggressive infiltrative morphology and metastatic dissemination. Integrated assessment of PET/CT morphology, metabolic parameters, tumor markers, and dissemination patterns may help raise preoperative suspicion of GAS and guide further pathological work-up. Explainable machine learning may serve as a complementary tool for feature integration, but external validation is required before clinical implementation.

ObjectivesNasopharyngeal carcinoma shows considerable biological heterogeneity that leads to wide variations in clinical outcomes. Anatomy-based staging and single-modality imaging cannot fully represent the complexity of tumor phenotype. This study aimed to develop and validate a prognostic model for progression-free survival by integrating multimodal positron emission tomography, computed tomography, magnetic resonance imaging, quantitative radiomics, deep learning representations, and clinical variables.MethodsA total of 261 patients with locoregionally advanced disease were retrospectively included. Radiomics and deep learning features were extracted from pretreatment positron emission tomography/computed tomography and T1-weighted magnetic resonance imaging. Fourteen survival models were constructed using Cox proportional hazards regression. Model performance was assessed through concordance index, time-dependent receiver operating characteristic analysis, Brier score, and calibration. The Friedman-Nemenyi procedure compared overall performance across models, and SHapley Additive Explanation identified key prognostic contributors.ResultsMultimodal fusion models outperformed clinical-only and single-modality models. The fully integrated model achieved the highest discrimination and stable performance across multiple follow-up intervals, with consistently strong calibration. Ranking analysis showed that deep-feature-dominant models performed worst, radiomics-based models achieved intermediate performance, and multimodal models formed the top-performing group. Feature attribution analysis highlighted several texture descriptors and deep representations as major predictors associated with adverse outcomes.ConclusionThe integrated multimodal model demonstrated superior accuracy, robustness, and interpretability for predicting progression-free survival. This approach provides a reliable imaging-based tool for individualized risk stratification and may contribute to more precise treatment planning in clinical practice.

This study aimed to develop and validate a non-invasive, multimodal radiomics model based on preoperative 1⁸F-FDG PET/CT to predict CLDN18.2 expression in gastric adenocarcinoma (GAC), addressing the limitations of intratumoral heterogeneity and invasiveness associated with endoscopic biopsies. This retrospective study enrolled 291 patients with pathologically confirmed GAC who underwent preoperative 1⁸F-FDG PET/CT. The cohort was randomly divided into a training set (n = 204) and an independent validation set (n = 87). High-dimensional radiomic features were extracted from PET and CT images. Feature selection was performed using the minimum redundancy maximum relevance (mRMR) algorithm and LASSO regression. A radiomics signature (Rad-score) was constructed using XGBoost and integrated with clinical variables. Among five machine learning algorithms evaluated, AdaBoost was identified as the optimal model. Performance was assessed via receiver operating characteristic (ROC) analysis, and interpretability was visualized using SHapley Additive exPlanations (SHAP). CLDN18.2-positive tumors exhibited a distinct hypometabolic phenotype, characterized by significantly lower SUVmax (P = 0.012) and SUVmean (P < 0.001) compared to negative tumors. The combined multimodal model demonstrated superior discrimination, achieving an AUC of 0.926 (95

Targeted radionuclide therapy (TRT) is a promising strategy for precision oncology but is limited by the lack of high-performance targeting ligands. Here, we report a lutetium-177 (177Lu)-labeled PTK7-targeted cyclized bivalent aptamer (CBSgc8) for treating an orthotopic hepatoblastoma. The cyclized multivalent design enhances biostability and binding affinity, while 177Lu labeling preserves its functional properties. The resulting 177Lu-CBSgc8 exhibited high serum stability, strong specificity for PTK7-positive cells, efficient internalization, and dose-dependent cytotoxicity in vitro. In vivo, 177Lu-CBSgc8 inhibited tumor growth in an OVCAR3 ovarian cancer model, although tumor accumulation remained limited. Given its PTK7-targeting capability and preferential hepatic distribution, we further evaluated its therapeutic potential in an orthotopic HepG2 hepatoblastoma model. In this setting, 177Lu-CBSgc8 achieved 76.6% tumor growth inhibition with a favorable safety. These findings demonstrate the potential of exploiting tissue distribution characteristics together with molecular targeting to expand the applicability of aptamer-based TRTs.

The receptor tyrosine kinase-like orphan receptor 1 (ROR1) is aberrantly overexpressed in multiple malignancies and has emerged as a clinically relevant biomarker for tumor staging and therapeutic decision-making. Here, we developed a series of PR7-derived ROR1-targeted radiotracers, including linear and cyclic analogues, and systematically evaluated their specificity in vitro and in vivo. All radiotracers showed high stability in saline and fetal bovine serum for at least 90 min and rapid tumor accumulation within 30 min post-injection in MC38 tumor-bearing mice. Among them, [68Ga]Ga-LP4 achieved favorable tumor targeting and tumor-to-nontumor ratios in PET imaging with predominant renal clearance. Notably, compared with [18F]AlF-NP1 reported in our previous study, [68Ga]Ga-LP4, which incorporates N-methylation and carboxyl amidation, demonstrated improved in vivo metabolic stability. Collectively, these findings identify [68Ga]Ga-LP4 as a promising ROR1-targeted imaging probe and highlight useful peptide optimization strategies.

Locally advanced non-small cell lung cancer (LA-NSCLC) is characterized by substantial heterogeneity, and the traditional TNM staging system has limited capacity for individualized prognostic assessment. This study aimed to develop and evaluate a comprehensive prognostic model integrating clinical characteristics, tumor burden, and PET/CT-based radiomics with exploratory deep learning features, and to assess model interpretability using machine-learning techniques. This single-center retrospective study included patients with LA-NSCLC who underwent pretreatment 18F-FDG PET/CT and were divided into training and internal test cohorts. Radiomic features were extracted separately from PET and CT images, and endpoint-specific radiomics risk scores were constructed using elastic-net Cox regression. A dual-branch 3D CNN-Transformer framework generated deep-learning risk scores. Clinical variables, radiomics, and deep-learning features were integrated to establish multimodal prognostic models for overall survival (OS) and progression-free survival (PFS). All feature selection, model fitting, hyperparameter tuning, and cutoff definition were restricted to the training cohort. Model performance was evaluated in the locked test cohort using the concordance index (C-index), time-dependent receiver operating characteristic curves, calibration, decision curve analysis, and Kaplan-Meier analysis. SHAP analysis was used to describe contributions to model predictions. A total of 221 patients were included (training cohort, n = 176; internal test cohort, n = 45). Radiomics and deep-learning risk scores were associated with survival outcomes. The integrated model yielded OS C-indices of 0.731 and 0.743 in the training and test cohorts, respectively; the gain over the radiomics model was modest. In the test cohort, AUCs for predicting 1-, 2-, and 3-year OS were 0.658, 0.820, and 0.874, respectively. For PFS, the deep-learning model had a higher test C-index than the integrated model. Exploratory subgroup results were limited by small sample sizes. SHAP identified the radiomics risk score as the largest contributor to the primary model predictions. The proposed multimodal PET/CT-based model demonstrated promising prognostic performance for LA-NSCLC.

Accurately distinguishing benign from malignant adrenal lesions remains a clinical challenge, especially in oncology patients with indeterminate imaging findings. This study aimed to develop and interpret machine learning (ML) models for classifying adrenal lesions based on 18 F-FDG PET/CT imaging and clinical parameters. A retrospective cohort of 255 patients undergoing 18 F-FDG PET/CT was analyzed. Imaging features—including adrenal SUVmax, SUVpeak, tumor diameter, CT attenuation, and tumor-to-liver SUVmax ratio (T/L SUVmax)—along with clinical variables were extracted. Two classification tasks were constructed: (1) differentiation of benign and malignant adrenal lesions; and (2) subtyping of malignant lesions into lung cancer metastases or lymphoma. Seven ML models were trained and evaluated using 10-fold cross-validation. SHAP (SHapley Additive exPlanations) analysis was applied to elucidate feature contributions. For the benign/malignant classification, ensemble models (Random Forest, Bagging, XGBoost) achieved outstanding performance (AUC > 0.99), with Bagging yielding 100

BACKGROUND:An integrated model combining clinical variables, radiomic features, and deep learning was developed to predict EGFR mutation status in patients with lung adenocarcinoma based on pretreatment 18F-FDG PET/CT imaging. METHODS:In this retrospective study, data from 218 patients-including PET/CT images, EGFR mutation status, and clinical characteristics-were analyzed. Three predictive models were constructed: a clinical model (C), a clinical-radiomics model (CR), and a clinical-radiomics-deep learning model (CRD). RESULTS:The CRD model integrated screened clinical features, as well as ConvNext-based deep learning scores and radiomic scores selected via LASSO regression. It exhibited significantly superior predictive performance to the C model (AUC = 0.599; DeLong test: Z = -3.522, p < 0.001, corrected p = 0.001) and the CR model (AUC = 0.739; DeLong test: Z = -2.197, p = 0.028, corrected p = 0.028), with an AUC of 0.821 for the CRD model. Calibration curves and decision curve analysis confirmed its robustness and potential clinical benefit. A nomogram based on the CRD model was established, enabling individualized risk prediction of EGFR mutation. CONCLUSIONS:This study highlights the potential of integrating clinical, radiomic, and deep learning features as a noninvasive approach for accurately predicting EGFR mutation status in lung adenocarcinoma.

Background: The Global Leadership Initiative on Malnutrition (GLIM) criteria provide a standardized approach for assessing the nutritional status of patients and demonstrate strong predictive value for the prognosis of patients with gastric cancer. However, these criteria do not incorporate indicators of adipose tissue metabolic activity, which may reflect pro-tumor microenvironmental factors. This study investigated the combined predictive value of malnutrition, defined by the GLIM criteria, and preoperative adipose tissue 18F-fluorodeoxyglucose (18F-FDG) uptake for recurrence-free survival (RFS) in patients with gastric cancer following radical surgery. Methods: A total of 105 patients were retrospectively enrolled and classified into malnourished and non-malnourished groups based on the GLIM criteria. Preoperative 18F-FDG positron emission tomography/computed tomography (18F-FDG PET/CT) was used to measure the mean standardized uptake value (SUVmean) of visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT). The predictive values of these indicators for RFS in patients with gastric cancer were assessed. Results: Multivariate survival analysis was used to identify GLIM-defined malnutrition (p = 0.020) and increased preoperative VAT SUVmean (p = 0.042) as independent risk factors for RFS. The combined analysis revealed that patients with both malnutrition and a high preoperative VAT SUVmean had the poorest RFS (HR = 18.41, p < 0.001). The predictive model integrating GLIM criteria and VAT SUVmean outperformed the GLIM criteria alone. Conclusions: This study demonstrated that combining malnutrition defined by the GLIM criteria with preoperative visceral adipose tissue 18F-FDG uptake optimizes recurrence risk stratification and exhibits superior prognostic predictive efficacy compared to using the GLIM criteria alone. This approach provides new insights into individualized prognostic assessment and intervention strategies.

Objective: To identify distinctive 18F-FDG positron emission tomography (PET)/computer tomography (CT) features of gastric-type endocervical adenocarcinoma (GAS) that differentiate it from squamous cell carcinoma (SCC) and usual-type endocervical adenocarcinoma (UEA), as well as to correlate these findings with pathological characteristics. Methods: Patients treated between December 2018 and December 2024 were retrospectively reviewed. The study included 12 GAS, 48 SCC, and 30 UEA cases. Evaluated parameters included tumor morphology, cystic components, uterine cavity fluid, N/M staging, tumor diameter, the cervical lesion maximum standardized uptake value (SUVmax), and the tumor-to-liver maximum standardized uptake ratio (T/L SUVmax). Results: GAS predominantly exhibited diffuse infiltrative growth (11/12), in contrast to mass-like growth observed in SCC (37/48) and UEA (24/30) (both p < 0.001). Cystic components, uterine cavity fluid, and peritoneal metastasis occurred significantly more frequently in GAS (12/12, 11/12, 5/12, respectively) compared to SCC and UEA (all p < 0.001). Elevated CA19-9 levels were more common in GAS (9/12) compared with SCC (p < 0.001). Tumor diameter did not differ significantly among the groups (p > 0.05). SUVmax and T/L SUVmax values were significantly lower in GAS (7.5 ± 3.8 and 2.5 ± 1.6, respectively) than in UEA (19.1 ± 11.4 and 5.7 ± 3.4) and SCC (17.4 ± 6.7 and 5.5 ± 2.6) (all p < 0.001). Conclusion: The clinical characteristics of GAS include infiltrative tumor growth, fluid accumulation in the uterine cavity, frequent formation of microcystic or macrocystic components, peritoneal metastasis, and elevated CA19-9 levels. In this cohort, SUVmax and T/L SUVmax values in GAS were significantly lower than those observed in SCC and UEA.

This study aimed to establish and validate prognostic nomogram models for patients who underwent 131I therapy for thyroid cancer with distant metastases. The cohort was divided into training (70%) and validation (30%) sets for nomogram development. Univariate and multivariate Cox regression analyses were used to identify independent predictors for overall survival (OS) and progression-free survival (PFS). Nomograms were developed based on these predictors, and Kaplan-Meier curves were constructed for validation. Among 451 patients who were screened, 412 met the inclusion criteria and were followed-up for a median duration of 65.2 months. The training and validation sets included 288 and 124 patients, respectively. Pathological type, first 131I administrated activity, and lesion 131I uptake in lesions were independent predictors for PFS. For OS, predictors included gender, age, metastasis site, first 131I administrated activity, 131I uptake, pulmonary lesion size, and stimulated thyroglobulin levels. These predictors were used to construct nomograms for predicting PFS and OS. Low-risk patients had significantly longer PFS and OS compared to high-risk patients, with 10-year PFS rates of 81.1% vs. 51.9% and 10-year OS rates of 86.2% vs. 37.4%. These may aid individualized prognostic assessment and clinical decision-making, especially in determining the prescribed activity for the first 131I treatment.

BackgroundPatients with differentiated thyroid cancer (DTC) may have occult lung metastases before 131iodine (131I) treatment. Identifying occult lung metastases before 131I treatment is of great clinical value for the correct staging of patients and the establishment of 131I treatment plans. Our research is of great significance in establishing statistical models for clinical data using machine learning algorithms to study the prediction of lung metastasis before 131I treatment.MethodsPatients were selected from Zhejiang cancer hospital and data was from two groups of DTC patients treated with 131I, where the experimental group consisted of 55 patients who showed no lung metastases on CT but tested positive on 131I-whole body scan (131I-WBS). The control group included 316 patients who tested negative for metastases across CT, ultrasound, and 131I-WBS. Six machine learning algorithms such as Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), and K-Nearest Neighbors (KNN) were employed to predict models and AUC, sensitivity, accuracy, precision, specificity, F1 Score were used to compare the performance between each models. Finally, the SHAP algorithm was used to explain the importance rank of the features.ResultsA total of 371 thyroid cancer patients were included in this study, 55 patients with occult lung metastasis and 316 patients in the control group. The data is divided into a training set and a testing set in a 7:3 ratio. Eleven acceptable variables analyzed including gender, age, T stage, N stage, tumor size, degree of invasion, number of lymph node metastases count, Thyroid Stimulating Hormone (TSH), thyroglobulin (Tg), Thyroglobulin antibodies (Tgab), and administrated activity were screened out by multivariate Cox regression. Evaluation indicators of the best model- LR were as following: accuracy (0.91), recall rate (0.64), precision (0.92), F1-s core (0.70), Area Under Curve (AUC) value (0.93), and the Specificity score (0.96).ConclusionThe logistic model (LR) showed the best performance in predicting occult lung metastases of thyroid cancer patients before 131I-WBS. Lymph nodes metastases and throglobulin have the most significant impact on the prediction.

RATIONALE AND OBJECTIVES:The purpose of this study is to compare the performance of GPT-4 and DeepSeek large language models in generating structured breast cancer multimodality imaging integrated reports from free-text radiology reports including mammography, ultrasound, MRI, and PET/CT. MATERIALS AND METHODS:A retrospective analysis was conducted on 1358 free-text reports from 501 breast cancer patients across two institutions. The study design involved synthesizing multimodal imaging data into structured reports with three components: primary lesion characteristics, metastatic lesions, and TNM staging. Input prompts were standardized for both models, with GPT-4 using predesigned instructions and DeepSeek requiring manual input. Reports were evaluated based on physician satisfaction using a Likert scale, descriptive accuracy including lesion localization, size, SUV, and metastasis assessment, and TNM staging correctness according to NCCN guidelines. Statistical analysis included McNemar tests for binary outcomes and correlation analysis for multiclass comparisons with a significance threshold of P < .05. RESULTS:Physician satisfaction scores showed strong correlation between models with r-values of 0.665 and 0.558 and P-values below .001. Both models demonstrated high accuracy in data extraction and integration. The mean accuracy for primary lesion features was 91.7% for GPT-4% and 92.1% for DeepSeek, while feature synthesis accuracy was 93.4% for GPT4 and 93.9% for DeepSeek. Metastatic lesion identification showed comparable overall accuracy at 93.5% for GPT4 and 94.4% for DeepSeek. GPT-4 performed better in pleural lesion detection with 94.9% accuracy compared to 79.5% for DeepSeek, whereas DeepSeek achieved higher accuracy in mesenteric metastasis identification at 87.5% vs 43.8% for GPT4. TNM staging accuracy exceeded 92% for T-stage and 94% for M-stage, with N-stage accuracy improving beyond 90% when supplemented with physical exam data. CONCLUSION:Both GPT-4 and DeepSeek effectively generate structured breast cancer imaging reports with high accuracy in data mining, integration, and TNM staging. Integrating these models into clinical practice is expected to enhance report standardization and physician productivity.

Targeted alpha therapy (TAT) has emerged as a promising strategy for cancer treatment by selectively delivering high linear energy transfer (LET) alpha-emitters to tumor cells while minimizing off-target toxicity. However, the clinical translation of alpha-emitters, particularly radium-223 (223Ra), remains challenging due to inefficient targeted delivery and uncontrolled release of recoil daughter products, leading to systemic toxicity. Herein, a dual-locked pretargeted strategy was developed integrating platinumIV (PtIV)-loaded hydrogel nanoparticles (HNPs) (HAQ@HNPs) and 223Ra-loaded HNPs (223Ra@HNPs) into an inverse electron demand Diels–Alder (IEDDA)-activated drug delivery system. In vitro cytotoxicity, ROS, and apoptosis, together with in vivo biodistribution, imaging, and therapeutic studies, were performed to evaluate the therapeutic efficacy and immune activation. This caged dual-locked approach enables precise pretargeted accumulation at the tumor site, followed by rapid dissociation and controlled release of 223Ra and PtIV upon IEDDA-triggered activation, thereby ensuring high tumor specificity while minimizing systemic exposure. The synergistic combination of TAT and chemotherapy effectively disrupts redox homeostasis, induces immunogenic cell death (ICD), and elicits a robust antitumor immune response. Furthermore, when combined with programmed death-ligand 1 (PD-L1) blockade, this strategy significantly enhances systemic antitumor immunity, leading to robust inhibition of tumor growth and metastasis. These findings underscore the potential of dual-locked pretargeted strategies to advance TAT by improving therapeutic efficacy and addressing the critical challenge of radionuclide leakage, paving the way for next-generation precision-targeted radiopharmaceuticals.

Molecular imaging has emerged as a transformative tool in cancer diagnosis, enabling the visualization of biological processes at the cellular and molecular levels. Aptamers, single-stranded oligonucleotides with high affinity and specificity for target molecules, have gained significant attention as versatile probes for molecular imaging due to their unique properties, including small size, ease of modification, low immunogenicity, and rapid tissue penetration. This review explores the integration of aptamers with various imaging agents to enhance cancer diagnosis and therapy. Aptamer-based imaging probes offer high sensitivity and real-time visualization of tumor markers. Aptamer-based fluorescence probes and aptamer-conjugated magnetic resonance imaging (MRI) probes, including gadolinium-based contrast agents, improve tumor targeting and imaging resolution. Additionally, aptamers have been utilized in single-photon emission computed tomography (SPECT) and positron emission tomography (PET) imaging to enhance the specificity of radiotracers for cancer detection. Furthermore, aptamer-targeted ultrasound and computed tomography (CT) imaging demonstrate the potential for noninvasive and precise tumor localization. By leveraging the unique advantages of aptamers, these imaging strategies not only improve diagnostic accuracy but also pave the way for image-guided cancer therapies. This review highlights the significant role of aptamers in advancing molecular imaging and their potential to revolutionize cancer diagnosis and treatment.