He Yongfu, Batumalay Malathy, Thinakaran Rajermani
Faculty of Information Engineering, Gongqing College of Nanchang University, 332020, Gongqing, Jiangxi, China.
Faculty of Data Science and Information Technology, INTI International University, 71800, Nilai, Negeri Sembilan, Malaysia.
J Imaging Inform Med. 2025 Jul 14. doi: 10.1007/s10278-025-01608-1.
In this study, we proposed a lightweight neural network architecture based on inverted residual network, efficient squeeze excitation (ESE) module, and double transfer learning, called TLese-ResNet, for breast cancer molecular subtype recognition. The inverted ResNet reduces the number of network parameters while enhancing the cross-layer gradient propagation and feature expression capabilities. The introduction of the ESE module reduces the network complexity while maintaining the channel relationship collection. The dataset of this study comes from the mammography images of patients diagnosed with invasive breast cancer in a hospital in Jiangxi. The dataset comprises preoperative mammography images with CC and MLO views. Given that the dataset is somewhat small, in addition to the commonly used data augmentation methods, double transfer learning is also used. Double transfer learning includes the first transfer, in which the source domain is ImageNet and the target domain is the COVID-19 chest X-ray image dataset, and the second transfer, in which the source domain is the target domain of the first transfer, and the target domain is the mammography dataset we collected. By using five-fold cross-validation, the mean accuracy and area under received surgery feature on mammographic images of CC and MLO views were 0.818 and 0.883, respectively, outperforming other state-of-the-art deep learning-based models such as ResNet-50 and DenseNet-121. Therefore, the proposed model can provide clinicians with an effective and non-invasive auxiliary tool for molecular subtype identification of breast cancer.
在本研究中，我们提出了一种基于倒置残差网络、高效挤压激励（ESE）模块和双重迁移学习的轻量级神经网络架构，称为TLese-ResNet，用于乳腺癌分子亚型识别。倒置残差网络在减少网络参数数量的同时，增强了跨层梯度传播和特征表达能力。ESE模块的引入在保持通道关系收集的同时降低了网络复杂度。本研究的数据集来自江西某医院被诊断为浸润性乳腺癌患者的乳腺钼靶图像。该数据集包括CC位和MLO位的术前乳腺钼靶图像。鉴于数据集规模较小，除了常用的数据增强方法外，还采用了双重迁移学习。双重迁移学习包括第一次迁移，其中源域是ImageNet，目标域是COVID-19胸部X光图像数据集，以及第二次迁移，其中源域是第一次迁移的目标域，目标域是我们收集的乳腺钼靶数据集。通过使用五折交叉验证，CC位和MLO位乳腺钼靶图像上的平均准确率和接受手术特征下的面积分别为0.818和0.883，优于其他基于深度学习的先进模型，如ResNet-50和DenseNet-121。因此，所提出的模型可以为临床医生提供一种有效且无创的乳腺癌分子亚型识别辅助工具。
