Cyst-X: Interpretable Deep Learning Based Risk Stratification of Pancreatic Cystic Tumors

Cyst-X：基于可解释深度学习的胰腺囊性肿瘤风险分层

• 批准号: 10391173
• 负责人: Ulas Bagci
• 金额: $ 43.88万
• 依托单位: NORTHWESTERN UNIVERSITY AT CHICAGO
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10391173
• 关键词: Academic Medical Centers; Algorithms; Artificial Intelligence; Biopsy; Cancer Etiology; Cessation of life; Characteristics; Clinic; Clinical; Colon Carcinoma; Colonic Polyps; Cyst; Cystic Neoplasm; Data; Data Set; Detection; Development; Diagnosis; Diagnostic; Disease; Early Diagnosis; Epithelial cyst; Evaluation; Excision; Goals; Guidelines; High Prevalence; Histopathology; Image; In Situ Lesion; Individual; International; Lead; Lesion; MRI Scans; Magnetic Resonance Imaging; Malignant - descriptor; Malignant Neoplasms; Malignant neoplasm of pancreas; Medical center; Methods; Modeling; Morbidity - disease rate; Mucinous Cystadenoma; Mucinous Neoplasm; Multicenter Studies; Names; Noninfiltrating Intraductal Carcinoma; Operative Surgical Procedures; Organ; Outcome; Outcomes Research; Pancreas; Pancreatectomy; Pancreatic Cyst; Pancreatic cystic neoplasia; Papillary; Patient Triage; Patient-Focused Outcomes; Patients; Performance; Prognosis; Property; Radiology Specialty; Recommendation; Reference Standards; Research; Risk; Scanning; Sensitivity and Specificity; Series; Serous Cystadenoma; Side; Structure; Surveillance Program; Survival Rate; System; Technology; Testing; Time; Trust; Universities; Unnecessary Surgery; Visual; automated algorithm; base; cancer invasiveness; cancer type; capsule; clinical center; clinical decision-making; cost; deep learning; deep learning algorithm; design; detection method; detection platform; diagnostic accuracy; efficacy validation; experimental study; follow-up; high risk; improved; learning strategy; malignant breast neoplasm; mortality; novel diagnostics; pancreatic neoplasm; premalignant; prognostic significance; radiological imaging; radiologist; radiomics; risk stratification; screening; stem; tool

Project Summary The overall goal of this project is to develop a new diagnostic tool, called Cyst-X, for accurate detection and characterization of pre-cancerous pancreatic cysts and improve patient outcome through precise decisions (surgical resection or surveillance). Pancreatic cancer is the most fatal cancer among all cancers due to its poor prognosis and lack of early detection methods. Unlike other common cancers where precursor lesions are well known (colon polyps-colon cancer, ductal carcinoma in situ (DCIS)-breast cancer), pancreas cancer precursors (cysts) are poorly understood. Diagnosing pancreatic cancer at earlier stages may decrease mortality and morbidity rates of this lethal disease. One major approach for diagnosing pancreatic cancer at earlier stages is to target pancreatic precancerous pancreatic neoplasms (cysts) before they turn into invasive cancer. Once cysts are detected with radiology imaging such as magnetic resonance imaging (MRI), they should be characterized with respect to their malignant potential. Low-risk cysts remain harmless; hence, patients should remain under surveillance program. On the other hand, high-risk cysts can progress into an aggressive cancer, therefore, patients should undergo surgical resection if possible. Despite this, international guidelines for risk stratification of pancreatic cysts are woefully deficient (55-76% accuracy for determining characteristics of low-risk vs high risk cystic tumors, while only 40-50% accuracy detecting cysts with MRI). Combined, these critical barriers indicate that there is an urgent need for improving characterization of pancreatic cystic tumors. Based on our preliminary results, which support the development of an image-based diagnostic decision tool, we hypothesize that our proposed Cyst-X will produce higher diagnostic accuracy for characterizing pancreatic cysts and provide better patient management compared to the current guidelines. Towards this overarching hypothesis, we will first use powerful deep learning methods (specifically deep capsule networks) for automatically detecting and segmenting the pancreas and pancreatic cysts from multi-sequence MRI scans (Aim 1). Next, we will create an interpretable image-based diagnosis model for characterizing pancreatic cysts (Aim 2). Accurate characterization is necessary for such a diagnostic model; however, emphasis will also be placed on interpretability of the machine generated diagnostic model. Visual explanation of the discriminative features will help radiologists obtain higher decision rates in patient management. In Aim 3, we will validate the proposed Cyst-X framework in a multi-center study. A total of 1200 multi-sequence MRI scans will be collected from three participating clinical centers (Mayo Clinic, Columbia University Medical Center, Erasmus Medical Center). Comprehensive evaluations will be made to test the validity and generalizability of Cyst-X. All evaluations will be made with respect to the international guidelines and biopsy proven ground truths. Our proposed study has wide implications: specifically, in the long term, it will influence early diagnosis of pancreatic cancer and clinical decision making to improve survival rates of pancreatic cancer.

项目摘要 该项目的总体目标是开发一种新的诊断工具，称为Cyst-X，以进行准确检测和 癌前胰腺囊肿的表征并通过精确决策改善患者结果 （手术切除或监视）。胰腺癌是所有癌症中最致命的癌症，因为其较差 预后和缺乏早期检测方法。与其他前体病变良好的常见癌症不同 已知的（结肠息肉癌，癌症癌（DCIS） - 胸癌），胰腺癌前体 （囊肿）知之甚少。在早期诊断胰腺癌可能会降低死亡率和 这种致命疾病的发病率。在早期诊断胰腺癌的一种主要方法是 靶向胰腺癌胰腺肿瘤（囊肿），然后才能变成侵入性癌症。一旦囊肿 用放射学成像（例如磁共振成像（MRI））检测到它们，应表征它们 关于它们的恶性潜力。低风险囊肿保持无害；因此，患者应保持在 监视计划。另一方面，高风险囊肿可以发展为侵略性癌症 如果可能的话，患者应进行手术切除。尽管如此，国际风险分层指南 胰腺囊肿的严重缺陷（55-76％的精度，用于确定低风险的特征与高的特征 风险囊性肿瘤，而使用MRI的囊肿只有40-50％的精度）。结合了这些关键障碍 表明迫切需要改善胰腺囊性肿瘤的表征。基于我们 初步结果，支持基于图像的诊断决策工具的开发，我们假设 我们提出的cyst-X将产生更高的诊断精度，以表征胰腺囊肿并提供 与当前指南相比，患者管理更好。走向这个总体假设，我们将 首先使用强大的深度学习方法（特别是深胶囊网络）来自动检测和 从多序列MRI扫描中分割胰腺和胰腺囊肿（AIM 1）。接下来，我们将创建一个 可解释的基于图像的诊断模型，用于表征胰腺囊肿（AIM 2）。准确的 对于这种诊断模型，表征是必要的。但是，重点也将放在 机器生成的诊断模型的解释性。视觉解释歧视特征将 帮助放射科医生在患者管理方面获得更高的决策率。在AIM 3中，我们将验证提议的 多中心研究中的Cyst-X框架。总共将收集1200次多序列MRI扫描 参与临床中心（伊拉斯mus医学中心哥伦比亚大学医学中心梅奥诊所）。 将进行全面的评估以测试Cyst-X的有效性和概括性。所有评估将是 就国际准则和活检证明了基础真理而制定。我们提出的研究很广 含义：特别是，从长远来看，它将影响胰腺癌和临床的早期诊断 提高胰腺癌存活率的决策。