Department of Anatomical Pathology, Singapore General Hospital, Singapore, Singapore.
AI Singapore, Singapore, Singapore.
Lab Invest. 2022 Mar;102(3):245-252. doi: 10.1038/s41374-021-00689-0. Epub 2021 Nov 24.
Breast fibroepithelial lesions (FEL) are biphasic tumors which consist of benign fibroadenomas (FAs) and the rarer phyllodes tumors (PTs). FAs and PTs have overlapping features, but have different clinical management, which makes correct core biopsy diagnosis important. This study used whole-slide images (WSIs) of 187 FA and 100 PT core biopsies, to investigate the potential role of artificial intelligence (AI) in FEL diagnosis. A total of 9228 FA patches and 6443 PT patches was generated from WSIs of the training subset, with each patch being 224 × 224 pixel in size. Our model employed a two-stage architecture comprising a convolutional neural network (CNN) component for feature extraction from the patches, and a recurrent neural network (RNN) component for whole-slide classification using activation values from the global average pooling layer in the CNN model. It achieved an overall slide-level accuracy of 87.5%, with accuracies of 80% and 95% for FA and PT slides respectively. This affirms the potential role of AI in diagnostic discrimination between FA and PT on core biopsies which may be further refined for use in routine practice.
乳腺纤维上皮性病变（FEL）是一种由良性纤维腺瘤（FA）和更罕见的叶状肿瘤（PT）组成的双相肿瘤。FA 和 PT 具有重叠的特征，但临床管理方式不同，因此正确的核心活检诊断很重要。本研究使用了 187 例 FA 和 100 例 PT 核心活检的全切片图像（WSI），以探讨人工智能（AI）在 FEL 诊断中的潜在作用。从训练子集的 WSI 中总共生成了 9228 个 FA 补丁和 6443 个 PT 补丁，每个补丁的大小为 224×224 像素。我们的模型采用了两阶段架构，包括一个卷积神经网络（CNN）组件，用于从补丁中提取特征，以及一个递归神经网络（RNN）组件，用于使用 CNN 模型中全局平均池化层的激活值进行整个切片的分类。它在幻灯片级别上的总体准确率为 87.5%，FA 和 PT 幻灯片的准确率分别为 80%和 95%。这证实了 AI 在核心活检中对 FA 和 PT 进行诊断鉴别中的潜在作用，它可以进一步改进并用于常规实践。
