Piran Nanekaran Negin, Felefly Tony H, Schieda Nicola, Morgan Scott C, Mittal Richa, Ukwatta Eran
University of Guelph, 50 Stone Rd E, Guelph, Ontario, N1G 2W1, CANADA.
University of Ottawa Department of Radiology Radiation Oncology and Medical Physics, 451 Smyth Road, Ottawa, Ontario, K1H 8L6, CANADA.
Biomed Phys Eng Express. 2024 Oct 1. doi: 10.1088/2057-1976/ad8201.
The risk of biochemical recurrence (BCR) after radiotherapy for localized prostate cancer (PCa) varies widely within standard risk groups. There is a need for low-cost tools to more robustly predict recurrence and personalize therapy. Radiomic features from pretreatment MRI show potential as noninvasive biomarkers for BCR prediction. However, previous research has not fully combined radiomics with clinical and pathological data to predict BCR in PCa patients following radiotherapy. Purpose: This study aims to predict 5-year BCR using radiomics from pretreatment T2W MRI and clinical-pathological data in PCa patients treated with radiation therapy, and to develop a unified model compatible with both 1.5T and 3T MRI scanners. Methods: A total of 150 T2W scans and clinical parameters were preprocessed. Of these, 120 cases were used for training and validation, and 30 for testing. Four distinct machine learning models were developed: Model 1 used radiomics, Model 2 used clinical and pathological data, and Model 3 combined these using late fusion. Model 4 integrated radiomic and clinical-pathological data using early fusion. Results: Model 1 achieved an AUC of 0.73, while Model 2 had an AUC of 0.64 for predicting outcomes in 30 new test cases. Model 3, using late fusion, had an AUC of 0.69. Early fusion models showed strong potential, with Model 4 reaching an AUC of 0.84, highlighting the effectiveness of the early fusion model. Conclusions: This study is the first to use a fusion technique for predicting BCR in PCa patients following radiotherapy, utilizing pre-treatment T2W MRI images and clinical-pathological data. The methodology improves predictive accuracy by fusing radiomics with clinical-pathological information, even with a relatively small dataset, and introduces the first unified model for both 1.5T and 3T MRI images.
局限性前列腺癌（PCa）放疗后生化复发（BCR）的风险在标准风险组内差异很大。需要低成本工具来更可靠地预测复发并实现治疗个体化。治疗前MRI的放射组学特征显示出作为BCR预测的非侵入性生物标志物的潜力。然而，先前的研究尚未充分将放射组学与临床和病理数据相结合来预测放疗后PCa患者的BCR。
本研究旨在利用治疗前T2加权MRI（T2W）的放射组学和临床病理数据预测接受放射治疗的PCa患者的5年BCR，并开发一种与1.5T和3T MRI扫描仪兼容的统一模型。
共对150例T2W扫描和临床参数进行了预处理。其中，120例用于训练和验证，30例用于测试。开发了四种不同的机器学习模型：模型1使用放射组学，模型2使用临床和病理数据，模型3使用后期融合将两者结合，模型4使用早期融合整合放射组学和临床病理数据。
在预测30个新测试病例的结果时，模型1的曲线下面积（AUC）为0.73，而模型2的AUC为0.64。使用后期融合的模型3的AUC为0.69。早期融合模型显示出强大的潜力，模型4的AUC达到0.84，突出了早期融合模型的有效性。
本研究首次使用融合技术，利用治疗前T2W MRI图像和临床病理数据预测放疗后PCa患者的BCR。该方法通过将放射组学与临床病理信息融合提高了预测准确性，即使数据集相对较小，并引入了首个针对1.5T和3T MRI图像的统一模型。
