Lawal Ismaheel O, Ndlovu Honest, Kgatle Mankgopo, Mokoala Kgomotso M G, Sathekge Mike M
Division of Nuclear Medicine and Molecular Imaging, Department of Radiology and Imaging Sciences, Emory University, Atlanta, GA; Department of Nuclear Medicine, University of Pretoria, Pretoria, South Africa.
Department of Nuclear Medicine, University of Pretoria, Pretoria, South Africa; Nuclear Medicine Research Infrastructure (NuMeRI), Steve Biko Academic Hospital, Pretoria, South Africa.
Semin Nucl Med. 2024 Jan;54(1):46-59. doi: 10.1053/j.semnuclmed.2023.07.003. Epub 2023 Jul 22.
Prostate-specific membrane antigen (PSMA) is a transmembrane glycoprotein expressed in the majority of prostate cancer (PCa). PSMA has an enzymatic function that makes metabolic substrates such as folate available for utilization by PCa cells. Intracellular folate availability drives aggressive tumor phenotype. PSMA expression is, therefore, a marker of aggressive tumor biology. The large extracellular domain of PSMA is available for targeting by diagnostic and therapeutic radionuclides, making it a suitable cellular epitope for theranostics. PET imaging of radiolabeled PSMA ligands has several prognostic utilities. In the prebiopsy setting, intense PSMA avidity in a prostate lesion correlate well with clinically significant PCa (csPCa) on histology. When used for staging, PSMA PET imaging outperforms conventional imaging for the accurate staging of primary PCa, and findings on imaging predict post-treatment outcomes. The biggest contribution of PSMA PET imaging to PCa management is in the biochemical recurrence setting, where it has emerged as the most sensitive imaging modality for the localization of PCa recurrence by helping to guide salvage therapy. PSMA PET obtained for localizing the site of recurrence is prognostic, such that a higher lesion number predicts a less favorable outcome to salvage radiotherapy or surgical intervention. Systemic therapy is given to patients with advanced PCa with distant metastasis. PSMA PET is useful for predicting response to treatments with chemotherapy, first- and second-line androgen deprivation therapies, and PSMA-targeted radioligand therapy. Artificial intelligence using machine learning algorithms allows for the mining of information from clinical images not visible to the human eyes. Artificial intelligence applied to PSMA PET images, therefore, holds great promise for prognostication in PCa management.
前列腺特异性膜抗原（PSMA）是一种跨膜糖蛋白，在大多数前列腺癌（PCa）中表达。PSMA具有酶促功能，可使叶酸等代谢底物可供PCa细胞利用。细胞内叶酸的可利用性驱动侵袭性肿瘤表型。因此，PSMA表达是侵袭性肿瘤生物学的标志物。PSMA的大细胞外结构域可被诊断和治疗性放射性核素靶向，使其成为适用于治疗诊断的细胞表位。放射性标记的PSMA配体的PET成像具有多种预后用途。在活检前的情况下，前列腺病变中强烈的PSMA亲和力与组织学上具有临床意义的PCa（csPCa）密切相关。当用于分期时，PSMA PET成像在原发性PCa的准确分期方面优于传统成像，并且成像结果可预测治疗后的结果。PSMA PET成像对PCa管理的最大贡献在于生化复发情况，它已成为通过帮助指导挽救治疗来定位PCa复发的最敏感成像方式。用于定位复发部位的PSMA PET具有预后价值，即更高的病变数量预示着挽救性放疗或手术干预的结果较差。晚期PCa伴远处转移的患者接受全身治疗。PSMA PET可用于预测对化疗、一线和二线雄激素剥夺治疗以及PSMA靶向放射性配体治疗的反应。使用机器学习算法的人工智能可以从人眼不可见的临床图像中挖掘信息。因此，应用于PSMA PET图像的人工智能在PCa管理的预后方面具有很大的前景。
