Graduate Collaborative Training base of Hunan Cancer Hospital, Hengyang Medical School, University of South China, Hengyang, Hunan, China.
Department of Diagnostic Radiology, The Affiliated Cancer Hospital of Xiangya School of Medicine & Hunan Cancer Hospital, Central South University, Changsha, Hunan, China.
Med Phys. 2024 Jun;51(6):4219-4230. doi: 10.1002/mp.17037. Epub 2024 Mar 20.
Pulmonary sclerosing pneumocytoma (PSP) and pulmonary carcinoid (PC) are difficult to distinguish based on conventional imaging examinations. In recent years, radiomics has been used to discriminate benign from malignant pulmonary lesions. However, the value of radiomics based on computed tomography (CT) images to differentiate PSP from PC has not been well explored.
We aimed to investigate the feasibility of radiomics in the differentiation between PSP and PC.
Fifty-three PSP and fifty-five PC were retrospectively enrolled and then were randomly divided into the training and test sets. Univariate and multivariable logistic analyses were carried to select clinical predictor related to differential diagnosis of PSP and PC. A total of 1316 radiomics features were extracted from the unenhanced CT (UECT) and contrast-enhanced CT (CECT) images, respectively. The minimum redundancy maximum relevance and the least absolute shrinkage and selection operator were used to select the most significant radiomics features to construct radiomics models. The clinical predictor and radiomics features were integrated to develop combined models. Two senior radiologists independently categorized each patient into PSP or PC group based on traditional CT method. The performances of clinical, radiomics, and combined models in differentiating PSP from PC were investigated by the receiver operating characteristic (ROC) curve. The diagnostic performance was also compared between the combined models and radiologists.
In regard to differentiating PSP from PC, the area under the curves (AUCs) of the clinical, radiomics, and combined models were 0.87, 0.96, and 0.99 in the training set UECT, and were 0.87, 0.97, and 0.98 in the training set CECT, respectively. The AUCs of the clinical, radiomics, and combined models were 0.84, 0.92, and 0.97 in the test set UECT, and were 0.84, 0.93, and 0.98 in the test set CECT, respectively. In regard to the differentiation between PSP and PC, the combined model was comparable to the radiomics model, but outperformed the clinical model and the two radiologists, whether in the test set UECT or CECT.
Radiomics approaches show promise in distinguishing between PSP and PC. Moreover, the integration of clinical predictor (gender) has the potential to enhance the diagnostic performance even further.
在常规影像学检查中，肺硬化性血管平滑肌脂肪瘤（PSP）和肺类癌（PC）难以区分。近年来，放射组学已被用于鉴别良恶性肺部病变。然而，基于 CT 图像的放射组学鉴别 PSP 与 PC 的价值尚未得到充分探索。
旨在研究放射组学在 PSP 与 PC 鉴别中的可行性。
回顾性纳入 53 例 PSP 和 55 例 PC，并随机分为训练集和测试集。进行单变量和多变量逻辑分析，以选择与 PSP 和 PC 鉴别诊断相关的临床预测因素。分别从平扫 CT（UECT）和增强 CT（CECT）图像中提取 1316 个放射组学特征。采用最小冗余最大相关性和最小绝对收缩和选择算子选择对鉴别 PSP 和 PC 最有意义的放射组学特征，构建放射组学模型。将临床预测因素和放射组学特征相结合，构建联合模型。两名资深放射科医生根据传统 CT 方法将每位患者独立分类为 PSP 或 PC 组。采用受试者工作特征（ROC）曲线评价临床、放射组学和联合模型在鉴别 PSP 与 PC 中的性能。并比较联合模型与放射科医生的诊断性能。
在鉴别 PSP 与 PC 方面，训练集 UECT 中临床、放射组学和联合模型的曲线下面积（AUC）分别为 0.87、0.96 和 0.99，训练集 CECT 中分别为 0.87、0.97 和 0.98。测试集 UECT 中临床、放射组学和联合模型的 AUC 分别为 0.84、0.92 和 0.97，测试集 CECT 中分别为 0.84、0.93 和 0.98。在鉴别 PSP 与 PC 方面，联合模型与放射组学模型相当，但优于临床模型和两名放射科医生，无论是在测试集 UECT 还是 CECT 中。
放射组学方法在鉴别 PSP 和 PC 方面具有潜力。此外，将临床预测因素（性别）纳入其中可能进一步提高诊断性能。
