目的:建立并验证99msestamibi(99mTc-MIBI)单光子发射计算机断层扫描/计算机断层扫描(SPECT/CT)列线图,用于预测非小细胞肺癌(NSCLC)。比较早期和延迟SPECT/CT列线图的诊断性能,并比较SPECT/CT影像组学模型与单个SPECT和CT影像组学模型的诊断性能。
方法:这项前瞻性研究纳入了103例患者(平均年龄:59.68±8.94岁)的119个病变(NSCLC:n=92,良性肺部病变:n=27)。患者接受双相99mTc-MIBISPECT/CT成像。他们被分为训练组(n=83)和验证组(n=36)。Logistic回归,支持向量机,随机森林,应用光梯度增强机训练并确定最优的机器学习模型。然后,结合影像组学评分和临床因素,建立诊断NSCLC的列线图。
结果:选择CYFRA21-1构建临床模型。在早期成像中,临床模型的曲线下面积(AUC),影像组学模型,和列线图分别为0.571、0.830和0.875。列线图表现优于临床模型,与影像组学模型相似(P=0.020,P=0.216),影像组学模型和临床模型的预测性能无统计学差异(P=0.103)。在延迟成像中,AUC分别为0.643,0.888和0.893.列线图的预测性能优于临床模型,与影像组学模型相当(P=0.042,P=0.480),与临床模型相比,影像组学模型也显示出更高的诊断性能(P=0.049).与早期SPECT/CT结果相比,延迟阶段的列线图和影像组学模型的AUC值较高,差异无统计学意义(P=0.831,P=0.568)。在延迟成像中,CT和SPECT的影像组学模型的AUC分别为0.696和0.768,SPECT/CT影像组学与单用CT和SPECT相比,差异有统计学意义(P=0.042,P=0.038)。
结论:双相99mTc-MIBISPECT/CT列线图和影像组学模型可以有效预测NSCLC,提供一种经济且无创的诊断非小细胞肺癌的成像方法,此外,这些发现为NSCLC患者的早期诊断和治疗策略提供了依据.延迟期SPECT/CT成像在诊断NSCLC方面可能比早期成像提供更大的实用价值。然而,这种新颖的方法需要在更大的范围内进一步验证,多中心队列。
结论:基于SPECT/CT的影像组学列线图用于区分NSCLC和肺部良性病变有助于早期诊断和指导治疗。
结论:列线图,基于双相SPECT/CT,用于区分非小细胞肺癌和良性病变。SPECT/CT影像组学模型比SPECT和CT影像组学模型具有更好的预测性能。
OBJECTIVE: To establish and validate a technetium 99m sestamibi (99mTc-MIBI) single-photon emission computed tomography/computed tomography (SPECT/CT) nomogram for predicting non-small cell lung cancer (NSCLC). Comparing the diagnostic performance of early and delayed SPECT/CT nomogram, and compare the diagnostic performance of SPECT/CT radiomics models with single SPECT and CT radiomics models.
METHODS: This prospective study included 119 lesions (NSCLC: n = 92, benign pulmonary lesions: n = 27) from 103 patients (mean age: 59.68 ± 8.94 years). Patients underwent dual-phase 99mTc-MIBI SPECT/CT imaging. They were divided into the training (n = 83) and validation (n = 36) cohorts. Logistic regression, support vector machine, random forest, and light-gradient boosting machine were applied to train and determine the optimal machine learning model. Then, combining radiomics score and clinical factors, establish nomograms for diagnosing NSCLC.
RESULTS: CYFRA21-1 was selected for constructing the clinical model. In early imaging, the areas under the curve (AUCs) of the clinical model, radiomics model, and nomogram were 0.571, 0.830, and 0.875, respectively. The nomogram performed better than the clinical model and similarly to the radiomics model (P=0.020, P=0.216), and there are no statistically significant differences in the predictive performance between the radiomics model and the clinical model (P=0.103). In delayed imaging, the AUC was 0.643, 0.888, and 0.893, respectively. The predictive performance of the nomogram was superior compared to the clinical model and comparable to the radiomics model (P=0.042, P=0.480), and the radiomics model also demonstrated superior diagnostic performance compared to the clinical model (P=0.049). Compared to early SPECT/CT results, the AUC values of the nomogram and radiomics models in the delayed phase were higher, although no statistical differences were found (P=0.831, P=0.568). In delayed imaging, the AUC of the radiomics models for CT and SPECT was 0.696 and 0.768, respectively, SPECT/CT radiomics exhibited significant differences compared with CT and SPECT alone (P=0.042, P=0.038).
CONCLUSIONS: Dual-phase 99mTc-MIBI SPECT/CT nomograms and radiomics models can effectively predict NSCLC, providing an economically and non-invasive imaging method for diagnosing NSCLC, moreover, these findings provide a basis for early diagnosis and treatment strategies in NSCLC patients. Delayed-phase SPECT/CT imaging may offer greater practical value than early-phase imaging for diagnosing NSCLC. However, this novel approach necessitates further validation in larger, multi-center cohorts.
CONCLUSIONS: Radiomics nomogram based on SPECT/CT for discriminating NSCLC from benign lung lesions helps to aid early diagnosis and guide treatment.
CONCLUSIONS: Nomograms, based on dual-phase SPECT/CT, was constructed to discriminate between non-small cell lung cancer and benign lesions. SPECT/CT radiomics model has better predictive performance than SPECT and CT radiomics model.