Machine Learning and Radiomics Techniques for Analysis of Daily MRI in Glioblastoma Patients

用于分析胶质母细胞瘤患者日常 MRI 的机器学习和放射组学技术

• 批准号: 10751672
• 负责人: Kaylie Cullison
• 金额: $ 5.27万
• 依托单位: UNIVERSITY OF MIAMI SCHOOL OF MEDICINE
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-01 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10751672
• 关键词: 3-Dimensional; Address; Aftercare; Age; Anatomy; Biopsy; Blood specimen; Brain imaging; Cessation of life; Chemotherapy and/or radiation; Clinical; Clinical Medicine; Data; Data Set; Detection; Diffusion; Disease; Disease Progression; Early treatment; Edema; Evolution; Excision; Frustration; Future; Glioblastoma; Goals; Habitats; Image; Immune system; Inflammation; Intervention; Laboratories; Machine Learning; Magnetic Resonance Imaging; Malignant neoplasm of brain; Manuals; Maps; Medial; Methods; Modification; Molecular; Monitor; Necrosis; Neoplasm Circulating Cells; Neuroanatomy; Oncology; Operative Surgical Procedures; Patient Monitoring; Patient-Focused Outcomes; Patients; Performance; Performance Status; Perfusion; Physicians; Physiological; Population; Process; Prognosis; Protocols documentation; Radiation Oncology; Radiation therapy; Research; Resolution; Scanning; Scientist; Statistical Data Interpretation; Surgically-Created Resection Cavity; System; Techniques; Texture; Training; Translating; Treatment outcome; Tumor Volume; aggressive therapy; anatomic imaging; automated segmentation; brain volume; career; chemotherapy; clinical practice; convolutional neural network; deep learning; disability; feature selection; image processing; imaging biomarker; improved; improved outcome; learning network; molecular marker; neovascularization; neuroimaging; novel; novel strategies; predictive modeling; prognostic; quantitative imaging; radiomics; risk stratification; segmentation algorithm; serial imaging; skills; standard care; tool; treatment response; treatment strategy; tumor; tumor growth

PROJECT SUMMARY Glioblastoma is the most common primary brain cancer worldwide. Novel treatment strategies are urgently needed since glioblastoma is nearly universally fatal with a median overall survival of only 1.5- 2 years. A frustrating aspect of glioblastoma is that approximately half of all patients will have what looks to be tumor growth on their post-treatment MRI, termed progression. Although, half of patients with progression will turn out to have pseudoprogression, which is a not-fully understood phenomenon believed to be edema and inflammation caused by the immune system and represents a good response to treatment. In fact, patients with pseudoprogression tend to do better than the general glioblastoma population and have a median overall survival of up to 3 years. On the other hand, patients with true progression of disease (tumor growth and poor/nonresponse to treatment) tend to do worse than the general glioblastoma population and have a medial overall survival of only 10 months. The frustrating part for clinical team, and the patients themselves, is that true progression and pseudoprogression are not discernable from one another during treatment, or even on initial post-treatment imaging (1-month post-treatment). Instead, the current gold-standard to distinguish between true and pseudoprogression is to “watch and wait” – continue monitoring with serial imaging and see if the patient clinically worsens or stabilizes. Thus, there is an unmet need for techniques that reliably and accurately determine if tumor growth/progression is occurring during treatment and predict/determine which sub-type of progression (true progression or pseudoprogression) a patient has. My laboratory focuses on responding to this unmet need through a variety of methods: serial multiparametric MRI (anatomic, perfusion, diffusion, spectroscopic, etc.), quantitative MRI analysis, machine learning, and molecular research including analyzing blood samples of glioblastoma patients to look for circulating tumor cells and other molecular markers. This proposal focuses on auto-detection of tumors on MRI based on machine learning (Aim 1) and analysis of anatomic and physiologic changes (Aim 2) from daily multiparametric MRI to address this issue by creating techniques that can detect enlarging tumors during treatment and predict between true and pseudoprogression months earlier than current methods. The goal of this proposal is to develop tools that identify and monitor patients with significant anatomic and/or physiologic tumor changes much earlier than current methods, so that in the future, prompt, aggressive, and early therapy adaption can be implemented. This project will translate directly to the practice of clinical medicine and advance the field of glioblastoma treatment. Additionally, it will allow me to gain hands-on skills and expertise in machine learning, radiomics, MRI, neuroimaging, neuro-anatomy, radiation therapy, and oncology, and aid in preparing me for a career as an academic physician scientist in the field of radiation oncology.

项目概要 胶质母细胞瘤是全世界最常见的原发性脑癌。 迫切需要，因为胶质母细胞瘤几乎普遍致命，中位总生存期仅为 1.5- 胶质母细胞瘤的一个令人沮丧的方面是，大约一半的患者会出现这种情况。 一半的患者在治疗后 MRI 上发现肿瘤生长，称为进展。 随着进展会出现假进展，这是一个尚未完全理解的现象 据认为是免疫系统引起的水肿和炎症，代表了良好的反应 事实上，假性进展患者往往比一般胶质母细胞瘤患者做得更好。 另一方面，患有这种疾病的患者的中位总生存期高达 3 年。 疾病进展（肿瘤生长和治疗反应不佳/无反应）往往比实际情况更糟 一般胶质母细胞瘤人群的中位总生存期仅为 10 个月。 对于临床团队和患者本身来说，真正的进展和假性进展是不同的 在治疗过程中，甚至在最初的治疗后成像（1个月 相反，目前区分真性进展和假性进展的黄金标准。 就是“观察并等待”——通过连续成像继续监测，看看患者的临床情况是否恶化 因此，对于可靠且准确地确定肿瘤是否存在的技术的需求尚未得到满足。 治疗期间发生生长/进展并预测/确定进展的亚型 （真进展或假进展）我的实验室专注于对此做出反应。 通过多种方法满足未满足的需求：连续多参数 MRI（解剖、灌注、扩散、 光谱等）、MRI 分析、机器定量学习和分子研究，包括 分析胶质母细胞瘤患者的血液样本以寻找循环肿瘤细胞和其他分子 该提案的重点是基于机器学习的 MRI 肿瘤自动检测（Aim）。 1) 分析日常多参数 MRI 的解剖和生理变化（目标 2），以解决 通过创建可以在治疗期间检测扩大的肿瘤并预测之间的技术来解决这个问题 该提案的目标是开发比当前方法早几个月的真进展和假进展。 识别和监测患有显着解剖和/或生理肿瘤变化的患者的工具 比目前的方法更早，因此在未来，迅速、积极和早期的治疗适应可以 该项目的实施将直接转化为临床医学实践并推进 此外，它将使我获得胶质母细胞瘤治疗领域的实践技能和专业知识。 机器学习、放射组学、MRI、神经影像学、神经解剖学、放射治疗和肿瘤学，以及 帮助我为放射肿瘤学领域的学术医师科学家职业生涯做好准备。