Artificial Intelligence-based decision support for chemotherapy-response assessment in Brain Tumors

基于人工智能的脑肿瘤化疗反应评估决策支持

• 批准号: 10589512
• 负责人: Pallavi Tiwari
• 金额: --
• 依托单位: WM S. MIDDLETON MEMORIAL VETERANS HOSP
• 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 2027-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10589512
• 关键词: Adjuvant; Adjuvant Chemotherapy; Adoption; Aftercare; Anatomy; Anxiety; Appearance; Artificial Intelligence; Award; Benign; Biological; Biophysics; Biopsy; Brain; Brain Neoplasms; Cells; Characteristics; Clinical; Clinical Trials; Clinical assessments; Combination Drug Therapy; Combined Modality Therapy; Coupled; Data; Diagnosis; Diagnostic; Discrimination; Disease; Disease Progression; Entropy; Excision; Exposure to; Gadolinium; Genomics; Glioblastoma; Glioma; Gulf War veteran; Healthcare Systems; Heterogeneity; Histologic; Histology; Human; Image; Institution; Intervention; Ionizing radiation; Iraq; Lesion; Link; MGMT gene; MRI Scans; Magnetic Resonance Imaging; Malignant Neoplasms; Malignant neoplasm of brain; Maps; Measurement; Medical center; Methylation; Molecular; Morbidity - disease rate; Morphology; Neurologic; Ohio; Oncologist; Operative Surgical Procedures; Pathway interactions; Patient Selection; Patients; Pattern; Perfusion; Persons; Pharmaceutical Preparations; Pharmacotherapy; Phenotype; Play; Population; Quality of life; Radiation; Radiation therapy; Reader; Reading; Recurrent tumor; Refractory; Resistance; Resort; Risk; Role; Scanning; Shapes; Site; Surface; Survival Rate; Tennessee; Texture; Time Management; Tissues; Treatment-related toxicity; Tumor Biology; Unnecessary Surgery; Validation; Vasodilation; Veterans; Visual; War; Work; brain magnetic resonance imaging; brain parenchyma; chemoradiation; chemotherapy; clinically actionable; cohort; comorbidity; companion diagnostics; conventional therapy; cost; deep learning; diagnostic tool; financial toxicity; follow-up; high risk; imaging biomarker; improved; innovation; mortality; nerve agent; nervous system disorder; neuroimaging; predictive marker; prognostic; promoter; radiation effect; radiologist; radiomics; responders and non-responders; response biomarker; segregation; side effect; standard of care; success; treatment effect; treatment response; tumor; tumor microenvironment

ABSTRACT: In 2020, over 23,000 patients in the US will be diagnosed with Glioblastoma (GBM), a highly aggressive brain tumor, with a dismal median survival of 15-18 months. Studies focusing on Gulf War Veterans especially those exposed to nerve agents in Iraq in 1991 have shown a higher risk of brain tumors among neurological diseases and a distinct neurological brain pattern as compared with the other Veterans. The standard-of-care for GBM consists of surgical resection followed by radiotherapy combined with concomitant and adjuvant chemotherapy. However, ~50% of GBM patients do not respond favorably to chemoradiation following surgery. A priori identification of non-responders could allow for selection of these patients as potential candidates for genomically-driven drug therapies (over 64 ongoing clinical trials in the US) over conventional treatment. Further, chemotherapy costs >$100K/year. There is hence an unmet need to develop and validate predictive biomarkers to identify up front which Veteran patients will not benefit from chemotherapy. Another significant challenge in GBM management is the differentiation of suspicious lesions on post-treatment MRI, as tumor recurrence or treatment-induced radiation effects. In the absence of reliable diagnosis, patients with a benign treatment effect have to undergo an unnecessary surgical confirmation biopsy. The co-morbidities due to unnecessary biopsies disproportionately impact Veteran GBM patients who tend to be older and have increased comorbidity burden. Consequently, developing a companion diagnostic solution using clinical MRI could represent a compelling solution in substantially improve quality-of-life years for Veteran GBM patients by sparing them of the side-effects of surgery, while providing timely management in patients with tumor recurrence. Recently, we have developed a new “Neuro-Image Risk Classifier” (NeuRisC), that uses artificial-intelligence (AI)-driven computational features corresponding to the micro-architectural measurements of disorder in the local intensity gradients (i.e. gradient entropy) on Gadolinium (Gd)-T1w MRI; the initial version of NeuRisC has been shown to (a) be prognostic of GBM survival on n=203 studies (p<0.001), and (2) have an accuracy of 85% (a 37% improvement over expert readers) on n=58 studies in distinguishing radiation effects from tumor recurrence. In this VA project, we propose to further improve, and validate the accuracy of NeuRisC by expanding our initial feature set (using Gd-T1w MRI alone) by including (1) additional features from anatomical (T2w, FLAIR) and functional MR sequences (perfusion), (2) a new class of biophysical deformation attributes from “normal” brain parenchyma, and (3) peritumoral features from outside the lesion. In Aim 1, we will develop (NeuRisC)predict as a predictive image-based marker of benefit to chemotherapy by combining intra- and peri-tumor gradient entropy and biophysical deformation attributes from “normal” brain parenchyma. Similarly, (NeuRisC)diagnose will be developed in Aim 2 by including lesion and peri-lesional features from pre- and multiple post-treatment MRIs, to improve discrimination of radiation effects and tumor recurrence. Overcoming limitations in previous work pertaining to small cohorts & lack of spatially mapped ex-vivo histology, NeuRisC modules will be validated on a large multi-institutional cohort of >1000 studies with co-localized tissue and MRI scans obtained across multiple biopsies/lesion. This cohort will also allow for establishing associations of NeuRisC features with underlying histological/molecular tumor characteristics - a prerequisite for clinical adoption. Lastly, NeuRisC modules will be deployed at Northeast Ohio & Tennessee VA Healthcare Systems to validate their utility as decision support. On an independent cohort of N=200 MRIs from Veteran patients, interpretation results from oncologists and radiologists at these two VA sites will be compared, with and without NeuRisC, to evaluate added benefit of NeuRisC as decision support. Criteria for success will be to demonstrate that NeuRisC is able to (a) predict GBM patients that respond favorably to chemoradiation with >90% accuracy, and (b) is non-inferior to accuracy for invasive biopsies (85-90% accuracy), thereby avoiding biopsies in patients with a benign radiation effect.

摘要：到 2020 年，美国将有超过 23,000 名患者被诊断出患有胶质母细胞瘤 (GBM)，这是一种高度 侵袭性脑肿瘤，中位生存期仅为 15-18 个月。研究重点关注海湾战争退伍军人。 尤其是 1991 年在伊拉克接触过神经毒剂的人，其患脑瘤的风险更高。 与其他退伍军人相比，神经系统疾病和独特的神经大脑模式。 GBM 的护理标准包括手术切除、随后放疗并联合其他治疗 然而，约 50% 的 GBM 患者对放化疗没有良好反应。 手术后先验识别无反应者可以选择这些患者作为潜在患者。 与传统药物疗法相比，基因组驱动药物疗法的候选者（美国正在进行超过 64 项临床试验） 此外，化疗费用每年>10万美元，因此开发和验证的需求尚未得到满足。 预测性生物标志物可以预先确定哪些退伍军人患者不会从化疗中受益。 GBM 管理中的重大挑战是在治疗后 MRI 上区分可疑病变，如 肿瘤复发或治疗引起的放射效应在缺乏可靠诊断的情况下，患者可能会出现以下情况： 良性的手术治疗效果必须经过不必要的活检来确认合并症。 不必要的活检对退伍 GBM 患者产生了不成比例的影响，这些患者往往年龄较大且患有 测试了增加的合并症负担，开发了使用临床 MRI 的伴随诊断解决方案。 可以代表一个令人信服的解决方案，通过以下方式大幅提高退伍军人 GBM 患者的生活质量： 使他们免受手术的副作用，同时为肿瘤复发的患者提供及时的治疗。 最近，我们开发了一种新的“神经图像风险分类器”（NeuRisC），它使用人工智能 （AI）驱动的计算特征对应于局部无序的微建筑测量 钆 (Gd)-T1w MRI 的强度梯度（即梯度熵）；NeuRisC 的初始版本是 在 n=203 项研究中显示 (a) 可预测 GBM 存活率 (p<0.001)，并且 (2) 准确度为 85%（a 在 n=58 项研究中，在区分放射效应和肿瘤复发方面，比专家读者提高了 37%。 在这个 VA 项目中，我们建议通过扩展我们的初始模型来进一步改进和验证 NeuRisC 的准确性 特征集（仅使用 Gd-T1w MRI），包括 (1) 解剖学的附加特征（T2w、FLAIR）和 功能性 MR 序列（灌注），(2) 来自“正常”大脑的一类新的生物物理变形属性 (3) 病变外部的肿瘤周围特征 在目标 1 中，我们将开发 (NeuRisC) 预测作为 通过结合肿瘤内和肿瘤周围梯度熵，基于图像的预测化疗获益标记 类似地，（NeuRisC）诊断将是来自“正常”脑实质的生物物理变形属性。 目标 2 中开发的方法包括来自治疗前和多次治疗后 MRI 的病变和病变周围特征， 改善放射效应和肿瘤复发的辨别力，克服先前工作的局限性。 关于小群体和缺乏空间映射的离体组织学，NeuRisC 模块将在 一个由超过 1000 项研究组成的大型多机构队列，其中包括在多个机构获得的共定位组织和 MRI 扫描 该队列还可以建立 NeuRisC 特征与潜在病变的关联。 组织学/分子肿瘤特征 - 临床采用的先决条件最后，NeuRisC 模块将。 部署在俄亥俄州东北部和田纳西州退伍军人管理局医疗系统，以验证其作为决策支持的效用。 在来自退伍军人患者的 N=200 MRI 的独立队列中，肿瘤学家和 这两个 VA 站点的放射科医生将在使用和不使用 NeuRisC 的情况下进行比较，以评估 NeuRisC 作为决策支持的成功标准将是证明 NeuRisC 能够 (a) 预测。 GBM 患者对放化疗反应良好，准确度 >90%，并且 (b) 不低于准确度 用于侵入性活检（准确度为 85-90%），从而避免对具有良性辐射效应的患者进行活检。