From the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
Clin Nucl Med. 2024 Oct 1;49(10):899-908. doi: 10.1097/RLU.0000000000005400.
Non-small cell lung cancer is the most common subtype of lung cancer. Patient survival prediction using machine learning (ML) and radiomics analysis proved to provide promising outcomes. However, most studies reported in the literature focused on information extracted from malignant lesions. This study aims to explore the relevance and additional value of information extracted from healthy organs in addition to tumoral tissue using ML algorithms.
This study included PET/CT images of 154 patients collected from available online databases. The gross tumor volume and 33 volumes of interest defined on healthy organs were segmented using nnU-Net deep learning-based segmentation. Subsequently, 107 radiomic features were extracted from PET and CT images (Organomics). Clinical information was combined with PET and CT radiomics from organs and gross tumor volumes considering 19 different combinations of inputs. Finally, different feature selection (FS; 5 methods) and ML (6 algorithms) algorithms were tested in a 3-fold data split cross-validation scheme. The performance of the models was quantified in terms of the concordance index (C-index) metric.
For an input combination of all radiomics information, most of the selected features belonged to PET Organomics and CT Organomics. The highest C-index (0.68) was achieved using univariate C-index FS method and random survival forest ML model using CT Organomics + PET Organomics as input as well as minimum depth FS method and CoxPH ML model using PET Organomics as input. Considering all 17 combinations with C-index higher than 0.65, Organomics from PET or CT images were used as input in 16 of them.
The selected features and C-indices demonstrated that the additional information extracted from healthy organs of both PET and CT imaging modalities improved the ML performance. Organomics could be a step toward exploiting the whole information available from multimodality medical images, contributing to the emerging field of digital twins in health care.
非小细胞肺癌是最常见的肺癌亚型。使用机器学习（ML）和放射组学分析进行患者生存预测已被证明提供了有前途的结果。然而，文献中大多数报道的研究都集中在从恶性病变中提取的信息上。本研究旨在探索使用 ML 算法从肿瘤组织之外的健康器官中提取的信息的相关性和附加价值。
本研究纳入了来自在线数据库的 154 名患者的 PET/CT 图像。使用基于 nnU-Net 的深度学习分割方法对大体肿瘤体积和定义在健康器官上的 33 个感兴趣区进行分割。随后，从 PET 和 CT 图像（器官组学）中提取了 107 个放射组学特征。将临床信息与器官和大体肿瘤体积的 PET 和 CT 放射组学相结合，考虑了 19 种不同的输入组合。最后，在 3 折数据分割交叉验证方案中测试了不同的特征选择（FS；5 种方法）和 ML（6 种算法）算法。模型的性能通过一致性指数（C-index）指标进行量化。
对于所有放射组学信息的输入组合，大多数选择的特征属于 PET 器官组学和 CT 器官组学。使用单变量 C-index FS 方法和使用 CT 器官组学+PET 器官组学作为输入的随机生存森林 ML 模型以及使用 PET 器官组学作为输入的最小深度 FS 方法和 CoxPH ML 模型，实现了最高的 C-index（0.68）。考虑到所有 17 个 C-index 高于 0.65 的组合，其中 16 个组合使用了来自 PET 或 CT 图像的器官组学作为输入。
所选特征和 C 指数表明，从 PET 和 CT 成像方式的健康器官中提取的附加信息提高了 ML 性能。器官组学可能是利用多模态医学图像中所有可用信息的一个步骤，有助于推动医疗保健领域中数字双胞胎的发展。
