New York University, New York, NY, 10012, USA; Applied Mathematics and Computational Science Program, University of Pennsylvania, Philadelphia, PA, 19104, USA.
Carroll College, Helena, MT, 59625, USA; Computer, Information Science and Engineering Department, University of Florida, Gainesville, FL, 32611, USA.
Comput Biol Med. 2021 Feb;129:104127. doi: 10.1016/j.compbiomed.2020.104127. Epub 2020 Nov 28.
Thanks to advancements in diagnosis and treatment, prostate cancer patients have high long-term survival rates. Currently, an important goal is to preserve quality of life during and after treatment. The relationship between the radiation a patient receives and the subsequent side effects he experiences is complex and difficult to model or predict. Here, we use machine learning algorithms and statistical models to explore the connection between radiation treatment and post-treatment gastro-urinary function. Since only a limited number of patient datasets are currently available, we used image flipping and curvature-based interpolation methods to generate more data to leverage transfer learning. Using interpolated and augmented data, we trained a convolutional autoencoder network to obtain near-optimal starting points for the weights. A convolutional neural network then analyzed the relationship between patient-reported quality-of-life and radiation doses to the bladder and rectum. We also used analysis of variance and logistic regression to explore organ sensitivity to radiation and to develop dosage thresholds for each organ region. Our findings show no statistically significant association between the bladder and quality-of-life scores. However, we found a statistically significant association between the radiation applied to posterior and anterior rectal regions and changes in quality of life. Finally, we estimated radiation therapy dose thresholds for each organ. Our analysis connects machine learning methods with organ sensitivity, thus providing a framework for informing cancer patient care using patient reported quality-of-life metrics.
得益于诊断和治疗方面的进步，前列腺癌患者的长期生存率很高。目前，一个重要的目标是在治疗期间和治疗后保持生活质量。患者接受的辐射与其随后经历的副作用之间的关系非常复杂，难以建模或预测。在这里，我们使用机器学习算法和统计模型来探索放射治疗与治疗后胃肠功能之间的关系。由于目前只有有限数量的患者数据集，我们使用图像翻转和基于曲率的插值方法来生成更多数据以利用迁移学习。使用插值和扩充的数据，我们训练了一个卷积自动编码器网络，以获得权重的近似最优起点。然后，一个卷积神经网络分析了患者报告的生活质量与膀胱和直肠的辐射剂量之间的关系。我们还使用方差分析和逻辑回归来探索器官对辐射的敏感性，并为每个器官区域开发剂量阈值。我们的研究结果表明，膀胱与生活质量评分之间没有统计学上的显著关联。然而，我们发现后直肠和前直肠区域接受的辐射与生活质量变化之间存在统计学上的显著关联。最后，我们估计了每个器官的放射治疗剂量阈值。我们的分析将机器学习方法与器官敏感性联系起来，从而为使用患者报告的生活质量指标为癌症患者护理提供了一个框架。
