Machine Learning-Based Identification of Cardiomyopathy Risk in Childhood Cancer Survivors

基于机器学习的儿童癌症幸存者心肌病风险识别

• 批准号: 10730177
• 负责人: Patrick M Boyle
• 金额: $ 22.75万
• 依托单位: FRED HUTCHINSON CANCER CENTER
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2025-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10730177
• 关键词: 3-Dimensional; Address; Adult; Age; Anthracycline; Architecture; Artificial Intelligence; Biomedical Engineering; Calibration; Cancer Patient; Cancer Survivor; Cardiac; Cardiology; Cardiomyopathies; Cardiotoxicity; Chemotherapy and/or radiation; Chest; Child; Clinical; Community Clinical Oncology Program; Computers; Consensus; Data; Data Set; Dependence; Detection; Development; Diagnosis; Disease Outcome; Early Diagnosis; Early Intervention; Echocardiography; Equilibrium; Exposure to; Functional disorder; General Population; Geometry; Guidelines; Heart; Heart Diseases; Heart failure; Image; Individual; Interdisciplinary Study; International; Interobserver Variability; Ionizing radiation; Left; Left Ventricular Dysfunction; Left Ventricular Ejection Fraction; Long-Term Survivors; Machine Learning; Malignant Childhood Neoplasm; Measurement; Measures; Medical Imaging; Medicine; Methods; Monitor; Morbidity - disease rate; National Clinical Trials Network; Network-based; Oncology; Onset of illness; Patients; Pattern; Pediatric Oncology Group; Process; Radiation therapy; Recommendation; Research; Risk; Sedation procedure; Shortening Fraction; Standardization; Survivors; Testing; Therapeutic; Time; Training; Treatment-Related Cancer; Ventricular; cancer imaging; cardiac magnetic resonance imaging; childhood cancer survivor; cohort; convolutional neural network; cost; deep learning; disease diagnosis; efficacy evaluation; heart function; high risk; high risk population; image archival system; imaging biomarker; imaging modality; improved; improved outcome; insight; interest; outcome prediction; premature; programs; screening; standard of care; two-dimensional; ultrasound; unstructured data

PROJECT SUMMARY / ABSTRACT Treatment-related cardiomyopathy/heart failure (CHF) is a leading cause of premature morbidity in childhood cancer survivors. Given the widespread use of anthracycline and related cardiotoxic chemotherapeutics, and in combination with radiotherapy exposure to the chest, over half of long-term survivors of childhood cancer are at significantly increased risk of early CHF compared with an age-matched general population. Currently, national and international consensus guidelines recommend the routine use of 2-dimensional (2D) echocardiography to screen this high-risk population for early signs of CHF, in particular, left ventricular (LV) systolic dysfunction and changes in LV geometry. At present, 2D echocardiography represents the standard of care across the US given its widespread availability, relatively lower cost, and avoidance of ionizing radiation or sedation. Nevertheless, limitations of 2D echocardiography include greater intra-patient and inter-observer variability. As a result, current echocardiography-based surveillance continues to have limited sensitivity and often requires serial studies before a patient is identified as having a potential abnormality. Although there is insufficient evidence to guide CHF management specific to pediatric cancer survivors, the evidence for non-cancer-related cardiomyopathy in both children and adults suggests that earlier intervention can mitigate or delay CHF progression. Therefore, methods that improve the detection of early CHF in childhood cancer survivors may have important clinical implications. Deep learning (DL), a subfield of machine learning, can automatically extract patterns from large unstructured datasets, such as medical images, and is increasingly being utilized in medicine for disease diagnosis as well as disease onset and outcome prediction. We propose to leverage a unique imaging dataset we have assembled from the Children’s Oncology Group (COG), a part of the NCI-sponsored National Clinical Trials Network and Community Oncology Research Program, to explore the potential of DL for enhanced detection of CHF. We have longitudinal echocardiographic data on over 100 survivors of childhood cancer who developed CHF and over 350 who did not, all defined using standardized criteria, representing an imaging repository of >3000 individual echocardiograms (and growing). Using this extant and clinically annotated dataset, we propose to: 1) Using a deep convolutional neural network (DCNN), identify the optimal process for a DL- based assessment of CHF in pediatric cancer survivors; and 2) Assess the feasibility and preliminary efficacy of DCNN-based prediction of cardiomyopathy onset from pre-CHF diagnosis echocardiograms. Expected results include the development of a DCNN that will differentiate between abnormal and normal echocardiograms from pediatric cancer survivors with and without CHF, respectively. After optimization, we will conduct a preliminary efficacy analysis to determine how many years in advance a survivor's transition to CHF can be predicted using an optimized DCNN.

项目摘要/摘要 治疗相关性心肌病/心力衰竭（CHF）是儿童期过早发病的主要原因 癌症幸存者鉴于蒽环类药物和相关心脏毒性化疗药物的广泛使用， 结合胸部放射治疗，超过一半的儿童癌症长期幸存者在 与年龄匹配的一般人群相比，早期CHF的风险显著增加。目前，国家 和国际共识指南建议常规使用二维（2D）超声心动图， 筛查该高危人群的CHF早期体征，特别是左心室（LV）收缩功能障碍， LV几何结构的变化。目前，2D超声心动图代表了美国的护理标准， 其广泛的可用性、相对较低的成本以及避免电离辐射或镇静。然而，尽管如此， 2D超声心动图的局限性包括更大的患者内和观察者间变异性。因此，目前 基于超声心动图的监测仍然具有有限的灵敏度，并且通常需要系列研究 在患者被识别为具有潜在异常之前。虽然没有足够的证据来指导 儿童癌症幸存者的CHF管理，非癌症相关心肌病的证据 儿童和成人均提示早期干预可减轻或延缓CHF进展。因此，我们认为， 改善儿童癌症幸存者早期CHF检测的方法可能具有重要的临床意义。 影响深度学习（DL）是机器学习的一个子领域，它可以自动从大规模数据中提取模式。 非结构化数据集，如医学图像，并越来越多地用于疾病医学 诊断以及疾病发作和结果预测。我们建议利用独特的成像数据集 我们聚集了来自儿童肿瘤学小组（COG），一个由NCI赞助的国家临床研究计划的一部分， 试验网络和社区肿瘤学研究计划，以探索DL的潜力， 检测CHF。我们有100多名儿童癌症幸存者的纵向超声心动图数据， 超过350名患者没有发生CHF，所有患者都使用标准化标准定义，代表成像检查结果。 储存了超过3000个单独的超声心动图（并且还在增长）。使用这个现存的临床注释数据集， 我们建议：1）使用深度卷积神经网络（DCNN），识别DL的最佳过程， 评估儿童癌症幸存者的CHF; 2）评估以下治疗的可行性和初步疗效： 根据CHF诊断前超声心动图，基于DCNN的心肌病发病预测。预期结果 包括DCNN的发展，将区分异常和正常的超声心动图， 儿童癌症幸存者分别与CHF和无CHF。优化后，我们将进行初步的 疗效分析，以确定提前多少年可以预测幸存者的过渡到CHF，使用 优化的DCNN。