Embracing the disharmony in medical imaging: A Simple and effective framework for domain adaptation.
Embracing the disharmony in medical imaging: A Simple and effective framework for domain adaptation.
复制标题
DOI：
10.1016/j.media.2021.102309
复制
发表时间：
2022-03
影响因子：
10.9
通讯作者：
Davatzikos C
中科院分区：
文献类型：
--
作者：
Wang R;Chaudhari P;Davatzikos C
域转移（训练和测试数据特征之间的不匹配）会导致多源成像场景中的预测性能显着下降。在医学成像中，不同地点的人群、扫描仪和采集协议的异质性带来了重大的领域转移挑战，并限制了机器学习模型的广泛临床应用。协调方法旨在学习不受这些差异影响的数据表示，是解决域转移的流行工具，但它们通常会导致预测准确性下降。本文从不同的角度来看待这个问题：我们接受数据中的这种不和谐，并设计了一个简单但有效的框架来解决域转移问题。基于我们的理论论点，关键思想是在源数据上构建一个预训练的分类器，并使该模型适应新数据。分类器可以针对研究域内适应进行微调。我们还可以解决我们无法获得目标数据上的地面实况标签的情况;我们展示了如何使用辅助任务进行适应;这些任务使用协变量，如年龄，性别和种族，这些协变量很容易获得，但与主要任务相关。我们证明了在大规模真实世界的3D脑MRI数据集上对阿尔茨海默病和精神分裂症进行分类的研究领域内适应和研究领域间概括的实质性改进。
Domain shift, the mismatch between training and testing data characteristics, causes significant degradation in the predictive performance in multi-source imaging scenarios. In medical imaging, the heterogeneity of population, scanners and acquisition protocols at different sites presents a significant domain shift challenge and has limited the widespread clinical adoption of machine learning models. Harmonization methods, which aim to learn a representation of data invariant to these differences are the prevalent tools to address domain shift, but they typically result in degradation of predictive accuracy. This paper takes a different perspective of the problem: we embrace this disharmony in data and design a simple but effective framework for tackling domain shift. The key idea, based on our theoretical arguments, is to build a pretrained classifier on the source data and adapt this model to new data. The classifier can be fine-tuned for intra-study domain adaptation. We can also tackle situations where we do not have access to ground-truth labels on target data; we show how one can use auxiliary tasks for adaptation; these tasks employ covariates such as age, gender and race which are easy to obtain but nevertheless correlated to the main task. We demonstrate substantial improvements in both intra-study domain adaptation and inter-study domain generalization on large-scale real-world 3D brain MRI datasets for classifying Alzheimer’s disease and schizophrenia.
登录
查看更多内容
影响因子：
14.5
作者：
Chand, Ganesh B.;Dwyer, Dominic B.;Davatzikos, Christos
通讯作者：
Davatzikos, Christos
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
5.7
作者：
Doshi J;Erus G;Ou Y;Resnick SM;Gur RC;Gur RE;Satterthwaite TD;Furth S;Davatzikos C;Alzheimer's Neuroimaging Initiative
通讯作者：
Alzheimer's Neuroimaging Initiative
影响因子：
4.8
作者：
Doshi, Jimit;Erus, Guray;Ou, Yangming;Gaonkar, Bilwaj;Davatzikos, Christos
通讯作者：
Davatzikos, Christos
影响因子：
10.9
作者：
Avants, B. B.;Epstein, C. L.;Gee, J. C.
通讯作者：
Gee, J. C.