School of Electrical Engineering, Korea University, Seoul, 02841, Republic of Korea.
Department of Pathology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, 03181, Republic of Korea.
Comput Methods Programs Biomed. 2024 May;248:108112. doi: 10.1016/j.cmpb.2024.108112. Epub 2024 Mar 7.
Multi-class cancer classification has been extensively studied in digital and computational pathology due to its importance in clinical decision-making. Numerous computational tools have been proposed for various types of cancer classification. Many of them are built based on convolutional neural networks. Recently, Transformer-style networks have shown to be effective for cancer classification. Herein, we present a hybrid design that leverages both convolutional neural networks and transformer architecture to obtain superior performance in cancer classification.
We propose a dual-branch dual-task adaptive cross-weight feature fusion network, called DAX-Net, which exploits heterogeneous feature representations from the convolutional neural network and Transformer network, adaptively combines them to boost their representation power, and conducts cancer classification as categorical classification and ordinal classification. For an efficient and effective optimization of the proposed model, we introduce two loss functions that are tailored to the two classification tasks.
To evaluate the proposed method, we employed colorectal and prostate cancer datasets, of which each contains both in-domain and out-of-domain test sets. For colorectal cancer, the proposed method obtained an accuracy of 88.4%, a quadratic kappa score of 0.945, and an F1 score of 0.831 for the in-domain test set, and 84.4%, 0.910, and 0.768 for the out-of-domain test set. For prostate cancer, it achieved an accuracy of 71.6%, a kappa score of 0.635, and an F1 score of 0.655 for the in-domain test set, 79.2% accuracy, 0.721 kappa score, and 0.686 F1 score for the first out-of-domain test set, and 58.1% accuracy, 0.564 kappa score, and 0.493 F1 score for the second out-of-domain test set. It is worth noting that the performance of the proposed method outperformed other competitors by significant margins, in particular, with respect to the out-of-domain test sets.
The experimental results demonstrate that the proposed method is not only accurate but also robust to varying conditions of the test sets in comparison to several, related methods. These results suggest that the proposed method can facilitate automated cancer classification in various clinical settings.
多类癌症分类在数字和计算病理学中得到了广泛研究，因为它对临床决策至关重要。已经提出了许多用于各种类型癌症分类的计算工具。其中许多是基于卷积神经网络构建的。最近，Transformer 风格的网络已被证明在癌症分类中非常有效。在此，我们提出了一种混合设计，利用卷积神经网络和 Transformer 架构来获得癌症分类的优异性能。
我们提出了一种称为 DAX-Net 的双分支双任务自适应交叉权重特征融合网络，该网络利用来自卷积神经网络和 Transformer 网络的异构特征表示，自适应地将它们组合在一起以提高它们的表示能力，并进行癌症分类作为类别分类和有序分类。为了有效地优化所提出的模型，我们引入了两个针对这两个分类任务量身定制的损失函数。
为了评估所提出的方法，我们使用了结直肠癌和前列腺癌数据集，每个数据集都包含域内和域外测试集。对于结直肠癌，所提出的方法在域内测试集上的准确率为 88.4%，二次 kappa 评分为 0.945，F1 得分为 0.831，在域外测试集上的准确率为 84.4%，kappa 评分为 0.910，F1 得分为 0.768。对于前列腺癌，它在域内测试集上的准确率为 71.6%，kappa 评分为 0.635，F1 得分为 0.655，在第一个域外测试集上的准确率为 79.2%，kappa 评分为 0.721，F1 得分为 0.686，在第二个域外测试集上的准确率为 58.1%，kappa 评分为 0.564，F1 得分为 0.493。值得注意的是，与其他几个相关方法相比，所提出的方法在域内和域外测试集上的表现都具有显著优势。
实验结果表明，与其他几个相关方法相比，所提出的方法不仅准确，而且对测试集的各种条件具有鲁棒性。这些结果表明，所提出的方法可以促进各种临床环境中的自动癌症分类。
