Objectives: This article aims to predict the presence of vascular endothelial growth factor (VEGF) expression and to predict the expression level of VEGF by machine learning based on preoperative magnetic resonance imaging (MRI) of glioblastoma (GBM). Methods: We analyzed the axial T2-weighted images (T2WI) and T1-weighted contrast-enhancement images of preoperative MRI in 217 patients with pathologically diagnosed GBM. Patients were divided into negative and positive VEGF groups, with the latter group further subdivided into low and high expression. The machine learning models were established with the maximum relevance and minimum redundancy algorithm and the extreme gradient boosting classifier. The area under the receiver operating curve (AUC) and accuracy were calculated for the training and validation sets. Results: Positive VEGF in GBM was 63.1% (137/217), with a high expression ratio of 53.3% (73/137). To predict the positive and negative VEGF expression, 7 radiomic features were selected, with 3 features from T1CE and 4 from T2WI. The accuracy and AUC were 0.83 and 0.81, respectively, in the training set and were 0.73 and 0.74, respectively, in the validation set. To predict high and low levels, 7 radiomic features were selected, with 2 from T1CE, 1 from T2WI, and 4 from the data combinations of T1CE and T2WI. The accuracy and AUC were 0.88 and 0.88, respectively, in the training set and were 0.72 and 0.72, respectively, in the validation set. Conclusion: The VEGF expression status in GBM can be predicted using a machine learning model. Radiomic features resulting from data combinations of different MRI sequences could be helpful.

Prostate cancer (PCa) is one of the most common malignancies and the second leading cause of cancer-related death in men worldwide. The six-transmembrane epithelial antigen of the prostate 1 (STEAP1) is exceptionally overexpressed in PCa, maintaining high expression even in the castration-resistant prostate cancer (CRPC) stage, making it a promising target for diagnosis and treatment. STEAP1-positive extracellular vesicles and STEAP1-PET imaging are optimistic approaches for the non-invasive detection of different stages of PCa. STEAP1-targeted therapy includes an antibody–drug conjugate (ADC), chimeric antigen receptor T cell (CAR-T), T-cell engager (TCE), and vaccines, which demonstrate valuable therapeutic prospects. This review presents the structure and pathophysiological function of STEAP1, synthesizes cutting-edge advances in STEAP1-targeted molecular imaging and clinical applications, and critically analyzes their translational potential to overcome the limitations of current PCa diagnosis and treatment.

Prostate cancer (PCa) is the most common malignant tumor of the male genitourinary system, and its incidence and mortality have shown a marked global increase in recent years. Prostate-specific membrane antigen (PSMA), a type II transmembrane glycoprotein highly expressed in PCa cells, has emerged as a vital molecular target in the field of PCa precision diagnosis and therapy. In recent years, significant advances have been achieved in PSMA-based molecular imaging, radioligand therapy, and the development of novel targeted drugs. This review aims to summarize and critically discuss recent advances in PSMA-targeted molecular imaging, radioligand therapy, and emerging therapeutic strategies, highlighting their roles in precision diagnosis and personalized treatment of PCa. PSMA positron emission tomography/computed tomography (PET/CT) imaging using radionuclides such as ⁶⁸Ga and ¹⁸F has markedly improved the accuracy of primary tumor staging, localization of recurrent lesions, and therapeutic response assessment. Radioligand therapies, such as ¹⁷⁷Lu-PSMA-617 and ²²⁵Ac-PSMA-617, have prolonged survival and demonstrated symptomatic benefits in multiple clinical trials, and are now applied in early disease stages, including chemotherapy-naïve and hormone-sensitive settings. Meanwhile, PSMA-targeted antibodies and antibody–drug conjugates (PSMA-ADCs), as well as bispecific T-cell engagers (BiTEs) and chimeric antigen receptor T-cell (CAR-T) therapies, are constantly being optimized and show promising clinical potential. Furthermore, PSMA-targeted nanoplatforms enable precise delivery of chemotherapeutic agents, photosensitizers, or imaging probes, achieving integrated diagnosis and therapy with multimodal imaging guidance, and offering new strategies for individualized treatment. Taken together, the evidence summarized in this review highlights PSMA as a pivotal molecular target supporting precision diagnosis and personalized treatment across the continuum of prostate cancer management.

Purpose: To differentiate cerebral glioblastoma (GBM) and solitary metastases (MET), as well as MET from lung (MET-lung) and other cancers (MET-other) through clinic, routine MRI, and radiomics analysis. Materials and methods: This study included 152 patients with GBM and 319 patients with MET. Among patients with MET, brain MET-free interval (month) was available in 273 patients