Matteo Ferro, Octavian Sabin Tataru, Giuseppe Carrieri, Gian Maria Busetto, Ugo Giovanni Falagario, Martina Maggi, Felice Crocetto, Biagio Barone, Francesco Del Giudice, Michele Marchioni, Daniela Terracciano, Giuseppe Lucarelli, Pasquale Ditonno, Raul Gherasim, Ciprian Todea-Moga, Giuseppe Fallara, Marco Tozzi, Antonio Cioffi, Roberto Bianchi, Alessio Digiacomo, Alessandro Veccia, Alessandro Antonelli, Maria Chiara Sighinolfi, Luigi Schips, Bernardo Rocco
{"title":"Artificial intelligence and radiomics applications in adrenal lesions: a systematic review.","authors":"Matteo Ferro, Octavian Sabin Tataru, Giuseppe Carrieri, Gian Maria Busetto, Ugo Giovanni Falagario, Martina Maggi, Felice Crocetto, Biagio Barone, Francesco Del Giudice, Michele Marchioni, Daniela Terracciano, Giuseppe Lucarelli, Pasquale Ditonno, Raul Gherasim, Ciprian Todea-Moga, Giuseppe Fallara, Marco Tozzi, Antonio Cioffi, Roberto Bianchi, Alessio Digiacomo, Alessandro Veccia, Alessandro Antonelli, Maria Chiara Sighinolfi, Luigi Schips, Bernardo Rocco","doi":"10.1177/17562872251352553","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Adrenal lesions, often incidentally detected, present diagnostic challenges in distinguishing benign from malignant or hormonally active lesions. Conventional imaging (computed tomography/magnetic resonance imaging (CT/MRI)) has limitations, driving interest in artificial intelligence (AI) and radiomics for enhanced accuracy.</p><p><strong>Objectives: </strong>To systematically evaluate AI and radiomics applications in adrenal lesion characterization, focusing on diagnostic performance, methodologies, and clinical utility.</p><p><strong>Design: </strong>PRISMA-guided systematic review of studies published up to June 2024.</p><p><strong>Data sources and methods: </strong>PubMed, Scopus, Web of Science, and Google Scholar were searched using the keywords: <i>adrenal lesions, AI, radiomics</i>, and <i>machine learning</i>. Inclusion followed PICO criteria: patients with indeterminate lesions, AI/radiomics interventions, comparisons to standard diagnostics, and diagnostic accuracy. Two reviewers screened studies, resolving discrepancies via consensus. Eleven retrospective studies (996 patients) met eligibility.</p><p><strong>Results: </strong>CT-based radiomics (eight studies) achieved a mean AUC of 0.88 (range: 0.84-0.94) in differentiating benign/malignant or functional/non-functional lesions. Top-performing models identified aldosterone-producing adenomas (AUC: 0.99). MRI-based radiomics (three studies) yielded mean AUC: 0.82 (0.72-0.92), with test-set performance declines (e.g., AUC: 0.72) suggesting overfitting. Nuclear medicine (four studies) demonstrated that hybrid 18F-FDG PET/CT models (SUVmax + texture features) achieved an AUC of 0.97 for metastatic versus benign lesions. AI applications extended to intraoperative navigation (AUC: 0.93) and prognostic prediction.</p><p><strong>Conclusion: </strong>CT-based radiomics outperformed MRI, aligning with guidelines favoring CT for adrenal assessment. AI-enhanced models show promise in refining diagnostics and reducing invasive procedures. However, retrospective designs, small cohorts, and protocol variability limit generalizability. Future work requires multicenter collaboration, standardized protocols, and prospective validation to translate AI/radiomics into clinical practice.</p>","PeriodicalId":23010,"journal":{"name":"Therapeutic Advances in Urology","volume":"17 ","pages":"17562872251352553"},"PeriodicalIF":3.5000,"publicationDate":"2025-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12319203/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Therapeutic Advances in Urology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/17562872251352553","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Adrenal lesions, often incidentally detected, present diagnostic challenges in distinguishing benign from malignant or hormonally active lesions. Conventional imaging (computed tomography/magnetic resonance imaging (CT/MRI)) has limitations, driving interest in artificial intelligence (AI) and radiomics for enhanced accuracy.
Objectives: To systematically evaluate AI and radiomics applications in adrenal lesion characterization, focusing on diagnostic performance, methodologies, and clinical utility.
Design: PRISMA-guided systematic review of studies published up to June 2024.
Data sources and methods: PubMed, Scopus, Web of Science, and Google Scholar were searched using the keywords: adrenal lesions, AI, radiomics, and machine learning. Inclusion followed PICO criteria: patients with indeterminate lesions, AI/radiomics interventions, comparisons to standard diagnostics, and diagnostic accuracy. Two reviewers screened studies, resolving discrepancies via consensus. Eleven retrospective studies (996 patients) met eligibility.
Results: CT-based radiomics (eight studies) achieved a mean AUC of 0.88 (range: 0.84-0.94) in differentiating benign/malignant or functional/non-functional lesions. Top-performing models identified aldosterone-producing adenomas (AUC: 0.99). MRI-based radiomics (three studies) yielded mean AUC: 0.82 (0.72-0.92), with test-set performance declines (e.g., AUC: 0.72) suggesting overfitting. Nuclear medicine (four studies) demonstrated that hybrid 18F-FDG PET/CT models (SUVmax + texture features) achieved an AUC of 0.97 for metastatic versus benign lesions. AI applications extended to intraoperative navigation (AUC: 0.93) and prognostic prediction.
Conclusion: CT-based radiomics outperformed MRI, aligning with guidelines favoring CT for adrenal assessment. AI-enhanced models show promise in refining diagnostics and reducing invasive procedures. However, retrospective designs, small cohorts, and protocol variability limit generalizability. Future work requires multicenter collaboration, standardized protocols, and prospective validation to translate AI/radiomics into clinical practice.
背景：肾上腺病变通常是偶然发现的，在区分良性和恶性或激素活性病变方面存在诊断挑战。传统成像（计算机断层扫描/磁共振成像（CT/MRI））具有局限性，这推动了人们对人工智能（AI）和放射组学的兴趣，以提高准确性。目的：系统评估人工智能和放射组学在肾上腺病变表征中的应用，重点是诊断性能、方法和临床应用。设计：对截至2024年6月发表的prisma指导的研究进行系统评价。数据来源和方法：检索关键词：肾上腺病变，人工智能，放射组学，机器学习，PubMed, Scopus, Web of Science，谷歌Scholar。纳入遵循PICO标准：病变不确定的患者，人工智能/放射组学干预，与标准诊断的比较，诊断准确性。两位审稿人筛选研究，通过共识解决差异。11项回顾性研究（996例患者）符合资格。结果：基于ct的放射组学（8项研究）在鉴别良/恶性或功能性/非功能性病变方面的平均AUC为0.88（范围：0.84-0.94）。表现最好的模型鉴定出醛固酮分泌腺瘤（AUC: 0.99）。基于mri的放射组学（三项研究）得出的平均AUC为0.82(0.72-0.92)，测试集性能下降（例如AUC: 0.72）表明过拟合。核医学（四项研究）表明，混合18F-FDG PET/CT模型（SUVmax +纹理特征）对转移性病变与良性病变的AUC为0.97。人工智能应用扩展到术中导航（AUC: 0.93）和预后预测。结论：基于CT的放射组学优于MRI，与偏向CT的肾上腺评估指南一致。人工智能增强模型有望改善诊断和减少侵入性手术。然而，回顾性设计、小队列和方案可变性限制了通用性。未来的工作需要多中心合作、标准化协议和前瞻性验证，以将人工智能/放射组学转化为临床实践。
期刊介绍：
Therapeutic Advances in Urology delivers the highest quality peer-reviewed articles, reviews, and scholarly comment on pioneering efforts and innovative studies across all areas of urology.
The journal has a strong clinical and pharmacological focus and is aimed at clinicians and researchers in urology, providing a forum in print and online for publishing the highest quality articles in this area. The editors welcome articles of current interest across all areas of urology, including treatment of urological disorders, with a focus on emerging pharmacological therapies.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
