Evolutionary design of explainable algorithms for biomedical image segmentation.
Evolutionary design of explainable algorithms for biomedical image segmentation.
复制标题
生物医学图像分割的可解释算法的进化设计。
DOI：
10.1038/s41467-023-42664-x
复制
发表时间：
2023-11-06
影响因子：
16.6
通讯作者：
Cussat-Blanc, Sylvain
中科院分区：
文献类型：
--
作者：
Cortacero, Kevin;McKenzie, Brienne;Mueller, Sabina;Khazen, Roxana;Lafouresse, Fanny;Corsaut, Gaelle;Van Acker, Nathalie;Frenois, Francois-Xavier;Lamant, Laurence;Meyer, Nicolas;Vergier, Beatrice;Wilson, Dennis G.;Luga, Herve;Staufer, Oskar;Dustin, Michael L.;Valitutti, Salvatore;Cussat-Blanc, Sylvain
当代生物医学中一个尚未解决的问题是需要注释、分析和解释的复杂图像的数量和多样性。深度学习的最新进展彻底改变了计算机视觉领域，创建了在图像分割任务中与人类专家竞争的算法。然而，这些框架需要大量人工标注的数据集进行训练，并且所产生的“黑匣子”模型难以解释。在这项研究中，我们介绍了Kartezio，这是一种基于模块化笛卡尔遗传编程的计算策略，通过迭代组装和参数化计算机视觉功能来生成完全透明且易于解释的图像处理管道。由此生成的管道在实例分割任务上表现出与最先进的深度学习方法相当的精度，同时需要更小的训练数据集。这种少镜头学习方法为这种方法提供了巨大的灵活性，速度和功能。然后，我们部署Kartezio来解决一系列语义和实例分割问题，并在从多路复用组织病理学图像到高分辨率显微镜图像的各种图像中展示其实用性。虽然Kartezio的灵活性，鲁棒性和实用性使这个完全可以解释的进化设计器成为生物医学图像处理领域的潜在游戏规则改变者，但Kartezio仍然是主流深度学习方法的补充和潜在辅助。深度学习框架需要大量人工标注的数据集来进行训练，并且由此产生的“黑匣子”模型很难解释。在这里，作者介绍了Kartezio;一种基于笛卡尔遗传编程的模块化计算策略，可以生成完全透明且易于解释的图像处理管道。
An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation. Recent advances in Deep Learning have revolutionized the field of computer vision, creating algorithms that compete with human experts in image segmentation tasks. However, these frameworks require large human-annotated datasets for training and the resulting “black box” models are difficult to interpret. In this study, we introduce Kartezio, a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines by iteratively assembling and parameterizing computer vision functions. The pipelines thus generated exhibit comparable precision to state-of-the-art Deep Learning approaches on instance segmentation tasks, while requiring drastically smaller training datasets. This Few-Shot Learning method confers tremendous flexibility, speed, and functionality to this approach. We then deploy Kartezio to solve a series of semantic and instance segmentation problems, and demonstrate its utility across diverse images ranging from multiplexed tissue histopathology images to high resolution microscopy images. While the flexibility, robustness and practical utility of Kartezio make this fully explicable evolutionary designer a potential game-changer in the field of biomedical image processing, Kartezio remains complementary and potentially auxiliary to mainstream Deep Learning approaches. Deep learning frameworks require large human-annotated datasets for training and the resulting ‘black box’ models are difficult to interpret. Here, the authors present Kartezio; a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines.
登录
查看更多内容
影响因子：
15.2
作者：
Esteva A;Chou K;Yeung S;Naik N;Madani A;Mottaghi A;Liu Y;Topol E;Dean J;Socher R
通讯作者：
Socher R
影响因子：
64.8
作者：
Harris CR;Millman KJ;van der Walt SJ;Gommers R;Virtanen P;Cournapeau D;Wieser E;Taylor J;Berg S;Smith NJ;Kern R;Picus M;Hoyer S;van Kerkwijk MH;Brett M;Haldane A;Del Río JF;Wiebe M;Peterson P;Gérard-Marchant P;Sheppard K;Reddy T;Weckesser W;Abbasi H;Gohlke C;Oliphant TE
通讯作者：
Oliphant TE
影响因子：
56.9
作者：
Balint, S.;Muller, S.;Dustin, M. L.
通讯作者：
Dustin, M. L.
影响因子：
3.9
作者：
Blank, Julian;Deb, Kalyanmoy
通讯作者：
Deb, Kalyanmoy
DOI：
10.1073/pnas.1218640110
发表时间：
2013-04-09
影响因子：
11.1
作者：
Bertrand, Florie;Mueller, Sabina;Valitutti, Salvatore
通讯作者：
Valitutti, Salvatore