Molecular Pathology Group, Translational Science, AstraZeneca, Cambridge, United Kingdom.
Centre for Evolution and Cancer, Division of Molecular Pathology, Institute of Cancer Research London, London, United Kingdom.
Sci Rep. 2019 Sep 6;9(1):12845. doi: 10.1038/s41598-019-49139-4.
Uncontrolled proliferation is a hallmark of cancer and can be assessed by labelling breast tissue using immunohistochemistry for Ki67, a protein associated with cell proliferation. Accurate measurement of Ki67-positive tumour nuclei is of critical importance, but requires annotation of the tumour regions by a pathologist. This manual annotation process is highly subjective, time-consuming and subject to inter- and intra-annotator experience. To address this challenge, we have developed Proliferation Tumour Marker Network (PTM-NET), a deep learning model that objectively annotates the tumour regions in Ki67-labelled breast cancer digital pathology images using a convolution neural network. Our custom designed deep learning model was trained on 45 immunohistochemical Ki67-labelled whole slide images to classify tumour and non-tumour regions and was validated on 45 whole slide images from two different sources that were stained using different protocols. Our results show a Dice coefficient of 0.74, positive predictive value of 70% and negative predictive value of 88.3% against the manual ground truth annotation for the combined dataset. There were minimal differences between the images from different sources and the model was further tested in oestrogen receptor and progesterone receptor-labelled images. Finally, using an extension of the model, we could identify possible hotspot regions of high proliferation within the tumour. In the future, this approach could be useful in identifying tumour regions in biopsy samples and tissue microarray images.
不受控制的增殖是癌症的一个标志，可以通过使用免疫组织化学方法对 Ki67 进行标记来评估，Ki67 是一种与细胞增殖相关的蛋白质。准确测量 Ki67 阳性肿瘤细胞核至关重要，但需要病理学家对肿瘤区域进行注释。这个手动注释过程非常主观，耗时且受注释者经验的影响。为了解决这个挑战，我们开发了增殖肿瘤标志物网络（PTM-NET），这是一种深度学习模型，它使用卷积神经网络客观地注释 Ki67 标记的乳腺癌数字病理学图像中的肿瘤区域。我们的定制深度学习模型在 45 张 Ki67 免疫组化标记的全幻灯片图像上进行了训练，以对肿瘤和非肿瘤区域进行分类，并在来自两个不同来源的 45 张全幻灯片图像上进行了验证，这些图像使用不同的方案进行了染色。我们的结果显示，对于合并数据集，与手动真实注释相比，Dice 系数为 0.74，阳性预测值为 70%，阴性预测值为 88.3%。来自不同来源的图像之间几乎没有差异，并且还在雌激素受体和孕激素受体标记的图像中对模型进行了进一步测试。最后，通过扩展模型，我们可以识别肿瘤内可能存在高增殖的热点区域。将来，这种方法可用于识别活检样本和组织微阵列图像中的肿瘤区域。
