Habitat-Based Radiomics for Predicting Visceral Pleural Invasion in Subpleural Nodules with Solid Component on Low-Dose CT: A Multicenter Study

作者：Yu Long, Xiaoyu Li, Y Li, Yongji Zheng, Wei Lin, Peng Zhou, Jieke Liu · 发表于：Diagnostics · 年份：2026 · DOI：10.3390/diagnostics16081191 · 被引用次数：1 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Lung Cancer Diagnosis and Treatment、Advanced Radiotherapy Techniques

Objectives: Our objectives were to develop and validate the habitat model based on low-dose computed tomography (LDCT) for noninvasive prediction of the visceral pleural invasion (VPI) in subpleural nodules with solid component. Methods: A total of 313 patients with subpleural lung adenocarcinoma nodules from three centers were retrospectively enrolled and divided into training (n = 192), validation (n = 82), and external test (n = 39) sets. All patients underwent preoperative LDCT scan. The habitat model was constructed using unsupervised clustering to partition each tumor into three distinct habitats, from which radiomic features were extracted and selected. Its diagnostic performance was compared with a whole-lesion radiomic model and radiological model. Statistical analysis included receiver operating characteristic (ROC) analysis and DeLong test. Results: The habitat model significantly outperformed both the radiomic and radiological models across the validation and external test sets, with areas under the ROC curve of 0.893 and 0.908, respectively (all p < 0.05). In contrast, the radiomic model achieved 0.833 and 0.772, while the radiological model yielded 0.746 and 0.624. The corresponding software tool has been made publicly available to facilitate broader clinical application. Conclusions: The habitat imaging model based on LDCT effectively predicts the VPI in subpleural lung adenocarcinoma by quantifying intratumoral spatial heterogeneity and demonstrates promisi...