PathFlowAI: A High-Throughput Workflow for Preprocessing, Deep Learning and Interpretation in Digital Pathology
PathFlowAI: A High-Throughput Workflow for Preprocessing, Deep Learning and Interpretation in Digital Pathology
复制标题
DOI：
10.1142/9789811215636_0036
复制
发表时间：
2019-11
影响因子：
--
通讯作者：
Joshua J. Levy;L. Salas;B. Christensen;Aravindhan Sriharan;L. Vaickus
中科院分区：
文献类型：
--
作者：
Joshua J. Levy;L. Salas;B. Christensen;Aravindhan Sriharan;L. Vaickus
疾病的诊断通常需要对活组织检查进行分析。许多诊断不仅取决于某些特征的存在，还取决于它们在组织中的位置。最近，已经开发了许多深度学习诊断辅助工具来对数字化活检切片进行分类。临床工作流程通常涉及每天处理500多个载玻片。但是，深度学习诊断辅助工具的临床使用需要一个具有成本效益、灵活、可扩展、快速、可解释和透明的预处理工作流程。在这里，我们提出了这样一个工作流程，使用Dask和通过APEX进行的混合精度训练进行了优化，能够处理任何补丁级或幻灯片级分类和预测问题。该工作流使用灵活、快速的预处理和深度学习分析管道，结合了模型解释，并具有高度存储效率的审计跟踪。我们证明了该软件包的实用性分析的一个典型的解剖病理学标本，肝活检评价肝炎的前瞻性队列。初步数据表明，PathFlowAI可能成为人工智能（AI）算法临床使用的一种具有成本效益和时间效率的工具。
The diagnosis of disease often requires analysis of a biopsy. Many diagnoses depend not only on the presence of certain features but on their location within the tissue. Recently, a number of deep learning diagnostic aids have been developed to classify digitized biopsy slides. Clinical workflows often involve processing of more than 500 slides per day. But, clinical use of deep learning diagnostic aids would require a preprocessing workflow that is cost-effective, flexible, scalable, rapid, interpretable, and transparent. Here, we present such a workflow, optimized using Dask and mixed precision training via APEX, capable of handling any patch-level or slide level classification and prediction problem. The workflow uses a flexible and fast preprocessing and deep learning analytics pipeline, incorporates model interpretation and has a highly storage-efficient audit trail. We demonstrate the utility of this package on the analysis of a prototypical anatomic pathology specimen, liver biopsies for evaluation of hepatitis from a prospective cohort. The preliminary data indicate that PathFlowAI may become a cost-effective and time-efficient tool for clinical use of Artificial Intelligence (AI) algorithms.