DOMINO: Domain-aware loss for deep learning calibration
DOMINO: Domain-aware loss for deep learning calibration
复制标题
DOI：
10.1016/j.simpa.2023.100478
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Skylar E. Stolte;Kyle Volle;A. Indahlastari;Alejandro Albizu;A. Woods;K. Brink;Matthew Hale;R. Fang
中科院分区：
文献类型：
--
作者：
Skylar E. Stolte;Kyle Volle;A. Indahlastari;Alejandro Albizu;A. Woods;K. Brink;Matthew Hale;R. Fang
深度学习已在医学成像任务中实现了最先进的性能;然而，通常不考虑模型校准。未校准的模型在高风险应用中具有潜在的危险，因为用户不知道它们何时会失败。因此，本文提出了一种新的领域感知损失函数来校准深度学习模型。建议的损失函数应用类的基础上的相似性在一个给定的目标域类之间的惩罚。因此，该方法改进了校准，同时还确保模型即使在不正确的情况下也会产生风险较小的错误。该软件的代码可在https://github.com/lab-smile/DOMINO上获得。
Deep learning has achieved the state-of-the-art performance across medical imaging tasks; however, model calibration is often not considered. Uncalibrated models are potentially dangerous in high-risk applications since the user does not know when they will fail. Therefore, this paper proposes a novel domain-aware loss function to calibrate deep learning models. The proposed loss function applies a class-wise penalty based on the similarity between classes within a given target domain. Thus, the approach improves the calibration while also ensuring that the model makes less risky errors even when incorrect. The code for this software is available at https://github.com/lab-smile/DOMINO.