Erdem Fatih, Gitto Salvatore, Fusco Stefano, Bausano Maria Vittoria, Serpi Francesca, Albano Domenico, Messina Carmelo, Sconfienza Luca Maria
Pediatric Radiology Department, Ankara University Hospital, Ankara, Turkey.
Dipartimento di Scienze Biomediche per la Salute, Università degli Studi di Milano, Milan, Italy.
Radiol Med. 2024 Dec;129(12):1898-1905. doi: 10.1007/s11547-024-01913-9. Epub 2024 Nov 6.
The aim of this study was to systematically review the use of automated detection systems for identifying bone lesions based on CT and MRI, focusing on advancements in artificial intelligence (AI) applications.
A literature search was conducted on PubMed and MEDLINE. Data were extracted and grouped into three main categories, namely baseline study characteristics, model validation strategies, and the type of AI algorithms.
A total of 10 studies were selected and analyzed, including 2,768 patients overall with a median of 187 per study. These studies utilized various AI algorithms, predominantly deep learning models (6 studies) such as Convolutional Neural Networks. Among machine learning validation strategies, K-fold cross-validation was the mostly used (5 studies). Clinical validation was performed using data from the same institution (internal testing) in 8 studies and from both the same and different (external testing) institutions in 1 study, respectively.
AI, particularly deep learning, holds significant promise in enhancing diagnostic accuracy and efficiency. However, the review highlights several limitations, such as the lack of standardized validation methods and the limited use of external datasets for testing. Future research should address these gaps to ensure the reliability and applicability of AI-based detection systems in clinical settings.
本研究旨在系统评价基于CT和MRI的骨病变自动检测系统的应用，重点关注人工智能（AI）应用的进展。
在PubMed和MEDLINE上进行文献检索。提取数据并分为三大类，即基线研究特征、模型验证策略和AI算法类型。
共选取并分析了10项研究，总计2768例患者，每项研究的中位数为187例。这些研究采用了各种AI算法，主要是深度学习模型（6项研究），如卷积神经网络。在机器学习验证策略中，K折交叉验证是最常用的（5项研究）。8项研究使用来自同一机构的数据（内部测试）进行临床验证，1项研究同时使用了来自同一机构和不同机构的数据（外部测试）进行临床验证。
AI，尤其是深度学习，在提高诊断准确性和效率方面具有巨大潜力。然而，该综述突出了几个局限性，如缺乏标准化的验证方法以及用于测试的外部数据集使用有限。未来的研究应弥补这些差距，以确保基于AI的检测系统在临床环境中的可靠性和适用性。
