Department of Oncology Physics, Edinburgh Cancer Centre, Western General Hospital, Crewe Road South, Edinburgh EH4 2XU, UK; School of Engineering, The University of Edinburgh, The King's Buildings, Mayfield Road, Edinburgh EH9 3JL, UK.
Edinburgh Cancer Research Centre, Institute of Genetics and Cancer, The University of Edinburgh, Edinburgh, UK; Department of Clinical Oncology, Edinburgh Cancer Centre, Western General Hospital, Crewe Road South, Edinburgh EH4 2XU, UK.
Radiother Oncol. 2023 Jun;183:109593. doi: 10.1016/j.radonc.2023.109593. Epub 2023 Mar 3.
This study aims to build machine learning models to predict radiation-induced rectal toxicities for three clinical endpoints and explore whether the inclusion of radiomic features calculated on radiotherapy planning computerised tomography (CT) scans combined with dosimetric features can enhance the prediction performance.
183 patients recruited to the VoxTox study (UK-CRN-ID-13716) were included. Toxicity scores were prospectively collected after 2 years with grade ≥ 1 proctitis, haemorrhage (CTCAEv4.03); and gastrointestinal (GI) toxicity (RTOG) recorded as the endpoints of interest. The rectal wall on each slice was divided into 4 regions according to the centroid, and all slices were divided into 4 sections to calculate region-level radiomic and dosimetric features. The patients were split into a training set (75%, N = 137) and a test set (25%, N = 46). Highly correlated features were removed using four feature selection methods. Individual radiomic or dosimetric or combined (radiomic + dosimetric) features were subsequently classified using three machine learning classifiers to explore their association with these radiation-induced rectal toxicities.
The test set area under the curve (AUC) values were 0.549, 0.741 and 0.669 for proctitis, haemorrhage and GI toxicity prediction using radiomic combined with dosimetric features. The AUC value reached 0.747 for the ensembled radiomic-dosimetric model for haemorrhage.
Our preliminary results show that region-level pre-treatment planning CT radiomic features have the potential to predict radiation-induced rectal toxicities for prostate cancer. Moreover, when combined with region-level dosimetric features and using ensemble learning, the model prediction performance slightly improved.
本研究旨在构建机器学习模型，以预测三个临床终点的放射性直肠毒性，并探讨在放射治疗计划计算机断层扫描（CT）扫描上计算的放射组学特征与剂量学特征相结合是否可以提高预测性能。
纳入了 183 名参与 VoxTox 研究（英国-CRN-ID-13716）的患者。在 2 年后前瞻性地收集毒性评分，采用等级≥1 直肠炎、出血（CTCAEv4.03）和胃肠道（GI）毒性（RTOG）作为感兴趣的终点。根据质心将直肠壁的每一层分为 4 个区域，并将所有切片分为 4 个部分来计算区域级别的放射组学和剂量学特征。将患者分为训练集（75%，N=137）和测试集（25%，N=46）。使用四种特征选择方法去除高度相关的特征。然后使用三种机器学习分类器对单独的放射组学或剂量学或组合（放射组学+剂量学）特征进行分类，以探讨它们与这些放射性直肠毒性的关联。
使用放射组学与剂量学特征，测试集预测直肠炎、出血和 GI 毒性的曲线下面积（AUC）值分别为 0.549、0.741 和 0.669。对于出血的集成放射组学-剂量学模型，AUC 值达到 0.747。
我们的初步结果表明，基于治疗前计划 CT 放射组学特征具有预测前列腺癌放射性直肠毒性的潜力。此外，当与区域剂量学特征结合并使用集成学习时，模型预测性能略有提高。
