Suppr超能文献
Abstract

A lung nodule is a small (< 30 millimetres), well defined lesion completely surrounded by pulmonary parenchyma (i.e., functional tissue of the lung). Lung nodules are classified as solid or subsolid, and subsolid nodules are subdivided into pure ground-glass nodules (no solid component) and part-solid nodules (both ground glass and solid components). A lesion that measures over 30 millimetres is considered a lung mass. An important distinction for the patient and treatment plan is whether the presenting lung nodule(s) are benign or malignant. For lung nodules, this appropriate classification is crucial to prevent any unnecessary procedures as well as for appropriate treatment planning (e.g., biopsy, surgical resection). It has been found that the majority of lung nodules identified on computed tomography (CT) scans are benign with a prevalence of malignancy as low as one percent for Canadians with lung nodules. To discern whether a lung nodule is benign or malignant, the initial evaluation usually involves a radiologist using clinical and radiographic features (often from a CT scan) to determine the likelihood of malignancy; this likelihood assists in determining further management (e.g., CT surveillance, biopsy). However, discerning malignancy from clinical and radiographic features can be challenging and novel methods are being considered, including artificial intelligence (AI). AI is a branch of computer science concerned with the development of systems that can perform tasks that would usually require human intelligence, such as problem-solving, reasoning, and recognition. AI is an umbrella term that includes a number of subfields and approaches. AI algorithms for reading CT scans often include a machine learning system (e.g., support vector machine [SVM], artificial neural networks [deep learning, including convolutional neural network or CNN]). Machine learning involves training an algorithm to perform tasks by learning from patterns in data rather than performing a task that it is explicitly programmed to do. In order to train the machine learning program, data are divided into learning sets (i.e., human indicates if an outcome of interest is present or absent) and validation sets (i.e., system used what it learns to indicate if the outcome of interest is present or absent). CADTH has previously reviewed the evidence for the use of AI for nodule classification in screening, incidental identification, or known or suspected malignancies for lung cancer via a Rapid Response Summary of Abstracts. The aim of the current report is to summarize and critically appraise the evidence initially identified in the Summary of Abstracts, based on additional screening and review of the full text of these publications.

摘要

相似文献

1
2
Evaluating the Patient With a Pulmonary Nodule: A Review.评估肺部结节患者:综述。
JAMA. 2022 Jan 18;327(3):264-273. doi: 10.1001/jama.2021.24287.
7
Evaluation of pure ground glass pulmonary nodule: a case report.纯磨玻璃样肺结节的评估:一例报告
J Community Hosp Intern Med Perspect. 2014 Sep 29;4(4). doi: 10.3402/jchimp.v4.24562. eCollection 2014.

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验