Chen Xiahan, Wang Weishen, Jiang Yu, Qian Xiaohua
School of Biomedical Engineering, Shanghai JiaoTong University, Shanghai 200240, China.
Department of General Surgery, Pancreatic Disease Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China.
Med Image Anal. 2023 Apr;85:102753. doi: 10.1016/j.media.2023.102753. Epub 2023 Jan 19.
Pancreatic cancer is a malignant tumor, and its high recurrence rate after surgery is related to the lymph node metastasis status. In clinical practice, a preoperative imaging prediction method is necessary for prognosis assessment and treatment decision; however, there are two major challenges: insufficient data and difficulty in discriminative feature extraction. This paper proposed a deep learning model to predict lymph node metastasis in pancreatic cancer using multiphase CT, where a dual-transformation with contrastive learning framework is developed to overcome the challenges in fine-grained prediction with small sample sizes. Specifically, we designed a novel dynamic surface projection method to transform 3D data into 2D images for effectively using the 3D information, preserving the spatial correlation of the original texture information and reducing computational resources. Then, this dynamic surface projection was combined with the spiral transformation to establish a dual-transformation method for enhancing the diversity and complementarity of the dataset. A dual-transformation-based data augmentation method was also developed to produce numerous 2D-transformed images to alleviate the effect of insufficient samples. Finally, the dual-transformation-guided contrastive learning scheme based on intra-space-transformation consistency and inter-class specificity was designed to mine additional supervised information, thereby extracting more discriminative features. Extensive experiments have shown the promising performance of the proposed model for predicting lymph node metastasis in pancreatic cancer. Our dual-transformation with contrastive learning scheme was further confirmed on an external public dataset, representing a potential paradigm for the fine-grained classification of oncological images with small sample sizes. The code will be released at https://github.com/SJTUBME-QianLab/Dual-transformation.
胰腺癌是一种恶性肿瘤，其术后高复发率与淋巴结转移状态有关。在临床实践中，术前影像预测方法对于预后评估和治疗决策是必要的；然而，存在两个主要挑战：数据不足和鉴别特征提取困难。本文提出了一种深度学习模型，利用多期CT预测胰腺癌的淋巴结转移，其中开发了一种具有对比学习框架的双重变换，以克服小样本量细粒度预测中的挑战。具体而言，我们设计了一种新颖的动态表面投影方法，将三维数据转换为二维图像，以有效利用三维信息，保留原始纹理信息的空间相关性并减少计算资源。然后，将这种动态表面投影与螺旋变换相结合，建立一种双重变换方法，以增强数据集的多样性和互补性。还开发了一种基于双重变换的数据增强方法，以生成大量二维变换图像，减轻样本不足的影响。最后，设计了一种基于空间内变换一致性和类间特异性的双重变换引导对比学习方案，以挖掘额外的监督信息，从而提取更多鉴别特征。大量实验表明，所提出的模型在预测胰腺癌淋巴结转移方面具有良好的性能。我们的具有对比学习方案的双重变换在外部公共数据集上得到了进一步验证，代表了小样本量肿瘤图像细粒度分类的潜在范式。代码将在https://github.com/SJTUBME-QianLab/Dual-transformation上发布。
