Bin Zheng, Ph.D.

Professor, School of Electrical and Computer Engineering & Stephenson Cancer Center, University of Oklahoma

郑斌

美国俄克拉何马大学电子和计算机工程系教授，史蒂文森癌症中心特邀研究员，美国科学院医学与生物工程院会士。从事开发和优化交互式CAD方案的工作，旨在为临床医生提供癌症诊断的“可视化辅助”工具，开发和验证从生物医学图像和电信号中提取的计算机化的生物标志物，以帮助提高癌症预后和治疗效果的准确性和可靠性。

Developing New Quantitative Imaging Markers to Assist Cancer Risk and Prognosis Assessment

Developing and establishing the precision or personalized medicine requires accurate clinical markers and/or multi-feature fusion-based prediction models to identify the personalized disease (e.g., cancer) risk and prognosis or patients’ response to the different treatment. Radiographic medical imaging is widely used in current clinical practice and carries much useful information to phenotype the disease risk and prognosis. However, how to reliably and quantitatively extract and compute the useful image features, which can be used to develop new and highly performed clinical prediction models, particularly, using the machine learning methods, remains a very challenged and hot research topic in the biomedical imaging and informatics field. In this presentation, I will discuss the general concept of applying the computer-aided quantitative image feature analysis methods in this research field and report several research work recently conducted in our laboratory to identify new quantitative imaging markers and apply machine learning technology to develop new prediction models, which include (1) using a new imaging marker based on the bilateral mammographic density asymmetry computed from the negative mammograms to predict risk of cancer detection in the next subsequent mammography screening; (2) extracting image features from breast MR images to predict complete response (CR) of breast tumors to the neoadjuvant chemotherapy; (3) using tumor density heterogeneity features computed from lung CT images to build a prediction model to assess lung cancer recurrence risk after surgery; and (4) using image features computed from abdominal CT images to predict response of ovarian cancer patients to chemotherapy at the early stage of the clinical trials. In summary, these examples demonstrate that developing computer-aided quantitative image feature analysis schemes has broad application values in biomedical imaging informatics field.

参考译文

开发应用于辅助癌症风险预测和预后评估的新型医学影像标志物

发展和实现精准或者个性化医疗需要应用准确的医学临床标志物或者基于多特征相融合的预测模型来预测个性化的疾病（比如，癌症）的发病风险和预后（或者对于不同治疗的反应）。医学影像广泛的应用在当前的医学临床实践中，并且包含了分析疾病风险和用户的影像表型特征。但是，在生物医学影像信息学领域中，如何有效的和定量的提取和计算能够应用于同开发新型的和准确的临床预测模型相关联的高性能医学影像特依然是一个很大的挑战，也是当前的一个研究热点。在本演讲报告中，结合讨论如何有效的发掘新型医学图像特征标志物和应用机器学习的方法训练开发癌症风险预测和预后评估的基本原理，我将简单的介绍我们实验室近年在该研究研究领域的几个工作案例。这包括（1）从乳腺钼靶图像中提取基于左右乳腺密度不对称性的新型影像标志物应用于预测近期乳腺癌发病风险，（2）从乳腺核磁共振图像中提取相关动态特征应用于预测乳腺癌病人对于新辅助化疗的反应，（3）从肺部CT图像中提取同肿瘤密度的不同质性特征应用于预测早期肺癌病人在手术后癌症复发的风险，（4）从腹部CT图像中提取相关影像特征应用于卵巢癌化疗效果的早期预测。从这些案例中，我们可以证明通过计算机辅助提取和计算的定量医学影像特征在生物医学影像信息学领域中有着非常广泛的应用前景。