Mayer Robin S, Gretser Steffen, Heckmann Lara E, Ziegler Paul K, Walter Britta, Reis Henning, Bankov Katrin, Becker Sven, Triesch Jochen, Wild Peter J, Flinner Nadine
Dr. Senckenberg Institute of Pathology, University Hospital Frankfurt, Frankfurt am Main, Germany.
Department of Gynecology and Obstetrics, University Hospital Frankfurt, Frankfurt am Main, Germany.
Front Med (Lausanne). 2022 Aug 29;9:959068. doi: 10.3389/fmed.2022.959068. eCollection 2022.
There is a lot of recent interest in the field of computational pathology, as many algorithms are introduced to detect, for example, cancer lesions or molecular features. However, there is a large gap between artificial intelligence (AI) technology and practice, since only a small fraction of the applications is used in routine diagnostics. The main problems are the transferability of convolutional neural network (CNN) models to data from other sources and the identification of uncertain predictions. The role of tissue quality itself is also largely unknown. Here, we demonstrated that samples of the TCGA ovarian cancer (TCGA-OV) dataset from different tissue sources have different quality characteristics and that CNN performance is linked to this property. CNNs performed best on high-quality data. Quality control tools were partially able to identify low-quality tiles, but their use did not increase the performance of the trained CNNs. Furthermore, we trained NoisyEnsembles by introducing label noise during training. These NoisyEnsembles could improve CNN performance for low-quality, unknown datasets. Moreover, the performance increases as the ensemble become more consistent, suggesting that incorrect predictions could be discarded efficiently to avoid wrong diagnostic decisions.
近年来，计算病理学领域备受关注，因为许多算法被引入用于检测癌症病变或分子特征等。然而，人工智能（AI）技术与实践之间存在很大差距，因为只有一小部分应用程序用于常规诊断。主要问题在于卷积神经网络（CNN）模型对来自其他来源数据的可转移性以及不确定预测的识别。组织质量本身的作用在很大程度上也尚不清楚。在此，我们证明了来自不同组织来源的TCGA卵巢癌（TCGA-OV）数据集样本具有不同的质量特征，并且CNN的性能与这一特性相关。CNN在高质量数据上表现最佳。质量控制工具能够部分识别低质量切片，但其使用并未提高训练后CNN的性能。此外，我们通过在训练期间引入标签噪声来训练噪声集成模型。这些噪声集成模型可以提高CNN对低质量、未知数据集的性能。而且，随着集成模型变得更加一致，性能会提高，这表明可以有效地丢弃错误预测以避免错误的诊断决策。
