Cui Lijuan, Li Dengao, Yang Xiaofeng, Liu Chao
College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China.
Department of Urology, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China.
PeerJ Comput Sci. 2024 Jul 10;10:e2064. doi: 10.7717/peerj-cs.2064. eCollection 2024.
Medical imaging datasets frequently encounter a data imbalance issue, where the majority of pixels correspond to healthy regions, and the minority belong to affected regions. This uneven distribution of pixels exacerbates the challenges associated with computer-aided diagnosis. The networks trained with imbalanced data tends to exhibit bias toward majority classes, often demonstrate high precision but low sensitivity.
We have designed a new network based on adversarial learning namely conditional contrastive generative adversarial network (CCGAN) to tackle the problem of class imbalancing in a highly imbalancing MRI dataset. The proposed model has three new components: (1) class-specific attention, (2) region rebalancing module (RRM) and supervised contrastive-based learning network (SCoLN). The class-specific attention focuses on more discriminative areas of the input representation, capturing more relevant features. The RRM promotes a more balanced distribution of features across various regions of the input representation, ensuring a more equitable segmentation process. The generator of the CCGAN learns pixel-level segmentation by receiving feedback from the SCoLN based on the true negative and true positive maps. This process ensures that final semantic segmentation not only addresses imbalanced data issues but also enhances classification accuracy.
The proposed model has shown state-of-art-performance on five highly imbalance medical image segmentation datasets. Therefore, the suggested model holds significant potential for application in medical diagnosis, in cases characterized by highly imbalanced data distributions. The CCGAN achieved the highest scores in terms of dice similarity coefficient (DSC) on various datasets: 0.965 ± 0.012 for BUS2017, 0.896 ± 0.091 for DDTI, 0.786 ± 0.046 for LiTS MICCAI 2017, 0.712 ± 1.5 for the ATLAS dataset, and 0.877 ± 1.2 for the BRATS 2015 dataset. DeepLab-V3 follows closely, securing the second-best position with DSC scores of 0.948 ± 0.010 for BUS2017, 0.895 ± 0.014 for DDTI, 0.763 ± 0.044 for LiTS MICCAI 2017, 0.696 ± 1.1 for the ATLAS dataset, and 0.846 ± 1.4 for the BRATS 2015 dataset.
医学成像数据集经常遇到数据不平衡问题，其中大多数像素对应健康区域，少数像素属于受影响区域。这种像素的不均匀分布加剧了与计算机辅助诊断相关的挑战。用不平衡数据训练的网络往往对多数类表现出偏差，通常显示出高精度但低灵敏度。
我们设计了一种基于对抗学习的新网络，即条件对比生成对抗网络（CCGAN），以解决高度不平衡的MRI数据集中的类不平衡问题。所提出的模型有三个新组件：（1）类特定注意力，（2）区域重新平衡模块（RRM）和基于监督对比的学习网络（SCoLN）。类特定注意力聚焦于输入表示中更具判别力的区域，捕获更多相关特征。RRM促进特征在输入表示的各个区域更平衡地分布，确保更公平的分割过程。CCGAN的生成器通过基于真阴性和真阳性映射从SCoLN接收反馈来学习像素级分割。这个过程确保最终的语义分割不仅解决了不平衡数据问题，还提高了分类准确性。
所提出的模型在五个高度不平衡的医学图像分割数据集上表现出了领先的性能。因此，在数据分布高度不平衡的情况下，该模型在医学诊断中具有巨大的应用潜力。CCGAN在各个数据集上的骰子相似系数（DSC）方面取得了最高分：BUS2017为0.965±0.012，DDTI为0.896±0.091，LiTS MICCAI 2017为0.786±0.046，ATLAS数据集为0.712±1.5，BRATS 2015数据集为0.877±1.2。DeepLab-V3紧随其后，在BUS2017的DSC分数为0.948±0.010，DDTI为0.895±0.014，LiTS MICCAI 2017为0.763±0.044，ATLAS数据集为0.696±1.1，BRATS 2015数据集为0.846±1.4的情况下获得第二好的位置。
