DataSheet1_Perfect prosthetic heart valve: generative design with machine learning, modeling, and optimization.docx

Majority of modern techniques for creating and optimizing the geometry of medical devices are based on a combination of computer-aided designs and the utility of the finite element method This approach, however, is limited by the number of geometries that can be investigated and by the time required for design optimization. To address this issue, we propose a generative design approach that combines machine learning (ML) methods and optimization algorithms. We evaluate eight different machine learning methods, including decision tree-based and boosting algorithms, neural networks, and ensembles. For optimal design, we investigate six state-of-the-art optimization algorithms, including Random Search, Tree-structured Parzen Estimator, CMA-ES-based algorithm, Nondominated Sorting Genetic Algorithm, Multiobjective Tree-structured Parzen Estimator, and Quasi-Monte Carlo Algorithm. In our study, we apply the proposed approach to study the generative design of a prosthetic heart valve (PHV). The design constraints of the prosthetic heart valve, including spatial requirements, materials, and manufacturing methods, are used as inputs, and the proposed approach produces a final design and a corresponding score to determine if the design is effective. Extensive testing leads to the conclusion that utilizing a combination of ensemble methods in conjunction with a Tree-structured Parzen Estimator or a Nondominated Sorting Genetic Algorithm is the most effective method in generating new designs with a relatively low error rate. Specifically, the Mean Absolute Percentage Error was found to be 11.8% and 10.2% for lumen and peak stress prediction respectively. Furthermore, it was observed that both optimization techniques result in design scores of approximately 95%. From both a scientific and applied perspective, this approach aims to select the most efficient geometry with given input parameters, which can then be prototyped and used for subsequent in vitro experiments. By proposing this approach, we believe it will replace or complement CAD-FEM-based modeling, thereby accelerating the design process and finding better designs within given constraints. The repository, which contains the essential components of the study, including curated source code, dataset, and trained models, is publicly available at https://github.com/ViacheslavDanilov/generative_design.

当前绝大多数用于医疗器件几何造型与优化的主流技术，均基于计算机辅助设计（computer-aided design, CAD）与有限元法（finite element method, FEM）的结合应用。然而该类方法受限于可研究的几何模型数量，以及设计优化所需的耗时成本。为解决上述局限，本文提出一种融合机器学习（machine learning, ML）方法与优化算法的生成式设计方案。本次研究共评估了八种不同的机器学习方法，涵盖基于决策树的算法、提升算法、神经网络以及集成学习方法。针对优化设计任务，本文研究了六种当前前沿的优化算法，分别为随机搜索（Random Search）、树状结构帕森估计器（Tree-structured Parzen Estimator）、基于CMA-ES的算法、非支配排序遗传算法（Nondominated Sorting Genetic Algorithm）、多目标树状结构帕森估计器以及拟蒙特卡洛算法。本研究将所提方案应用于人工心脏瓣膜（prosthetic heart valve, PHV）的生成式设计任务，以人工心脏瓣膜的设计约束（包括空间要求、材料属性与制造工艺）作为输入，本方案可输出最终设计方案与对应的有效性评分，用于判断该设计是否合格。通过大量实验验证，本文得出结论：将集成学习方法与树状结构帕森估计器或非支配排序遗传算法相结合，是生成低误差率新型设计的最优方案。具体而言，在管腔与峰值应力预测任务中，模型的平均绝对百分比误差（Mean Absolute Percentage Error, MAPE）分别为11.8%与10.2%。此外，实验结果显示，上述两种优化算法均可使设计评分达到约95%。从科学研究与实际应用双重视角来看，本方案旨在基于给定输入参数筛选出最优几何构型，后续可通过原型制作并开展体外实验验证。本文认为，该方案可替代或补充基于CAD-FEM的建模流程，从而加速设计进程，并在给定约束条件下获得更优的设计方案。本研究的核心组件（包括整理后的源代码、数据集与预训练模型）已开源至 https://github.com/ViacheslavDanilov/generative_design。