Dilek Okan, Demırel Emin, Tas Zeynel Abidin, Bılgın Emre
Department of Radiology, Adana City Training and Research Hospital, University of Health Sciences, 01370 Adana, Turkey.
Department of Radiology, Faculty of Medicine, Afyonkarahisar University of Health Sciences, 03030 Afyonkarahisar, Turkey.
Diagnostics (Basel). 2025 May 20;15(10):1283. doi: 10.3390/diagnostics15101283.
: This study aimed to investigate whether small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC) can be distinguished based on radiomics data derived from T2-FLAIR digital subtraction images of the peritumoral edema region in patients with brain metastases. A total of 136 patients who underwent surgery for brain tumors, including 100 patients in the Pretreat-Metstobrain-MASKS dataset and 36 patients from our institution, were included in our study. Radiomic features were extracted from digitally subtracted T2-FLAIR images in the peritumoral edema area. Patients were divided into NSCLC and SCLC groups. The maximum relevance-minimum redundancy (mRMR) method was then used for dimensionality reduction. The Naive Bayes algorithm was used for model development, and the interpretability of the model was explored using SHapley Additive exPlanations (SHAP). The performance metrics included the area under the curve (AUC), sensitivity (SENS), and specificity (SPEC). The mean age of NSCLC patients was 64.6 ± 10.3 years, and that of SCLC patients was 63.4 ± 11.7 years. In the external validation cohort, the model achieved an AUC of 0.82 (0.68-0.97), a SENS of 0.87 (0.74-0.91), and a SPEC of 0.72 (0.72-0.89). In the train cohort, the model achieved an AUC of 1.000, a SENS of 1.000, and a SPEC of 1.000. The feature providing the best effect was wavelet-HHHglcmJointEnergy, with a SHAP value of approximately 2.5. An artificial intelligence model developed using radiomics data from T2-FLAIR digital subtraction images of the peritumoral edema area can identify the histologic type of lung cancer in patients with associated brain metastases.
本研究旨在探讨能否基于脑转移瘤患者瘤周水肿区域的T2-FLAIR数字减影图像衍生的放射组学数据来区分小细胞肺癌（SCLC）和非小细胞肺癌（NSCLC）。本研究纳入了136例接受脑肿瘤手术的患者，其中包括Pretreat-Metstobrain-MASKS数据集中的100例患者以及来自我们机构的36例患者。从瘤周水肿区域的数字减影T2-FLAIR图像中提取放射组学特征。患者被分为NSCLC组和SCLC组。然后使用最大相关最小冗余（mRMR）方法进行降维。使用朴素贝叶斯算法进行模型开发，并使用SHapley加性解释（SHAP）探索模型的可解释性。性能指标包括曲线下面积（AUC）、敏感性（SENS）和特异性（SPEC）。NSCLC患者的平均年龄为64.6±10.3岁，SCLC患者的平均年龄为63.4±11.7岁。在外部验证队列中，该模型的AUC为0.82（0.68-0.97），SENS为0.87（0.74-0.91），SPEC为0.72（0.72-0.89）。在训练队列中，该模型的AUC为1.000，SENS为1.000，SPEC为1.000。效果最佳的特征是小波-HHHglcm联合能量，SHAP值约为2.5。使用瘤周水肿区域的T2-FLAIR数字减影图像的放射组学数据开发的人工智能模型可以识别伴有脑转移的肺癌患者的组织学类型。
