目前基于卷积神经网络的前列腺癌自动分类模型常常依赖于大量的手动标注。虽然自监督学习(Self-supervised Learning, SSL)在解决这个问题上显示出了潜力，但来自医学场景的数据存在着类内相似性冲突，因此直接使用包括正负样本对的损失计算可能会误导训练。SSL方法往往侧重于图像级别的全局一致性，而不考虑特征图中的内部信息关系。为了提高前列腺癌诊断的效率，我们提出了一种自监督双头注意力引导引导学习网络(Self-supervised dual-head attentional bootstrap learning network, SDABL)，包括在线网络(Online-Net)和目标网络(Target-Net)。自定位注意力模块(Self-Position Attention Module, SPAM)和自适应最大通道注意力模块(Channel Attention Module, CAAM)同时插入两个路径。它们使用少量参数捕捉原始特征图的位置和通道注意力，并解决了SSL中特征图信息优化的问题。在损失计算中，我们舍弃了负样本对的构建，而是通过不断接近正样本嵌入表示来引导网络学习位置空间和通道空间的一致性。我们在前列腺经直肠超声(TRUS)数据集上进行了大量实验证明，我们的SDABL预训练方法在主流对比学习方法和其他基于注意力的方法上具有明显优势。具体而言，在经过微调后，SDABL预训练骨干模型在我们的TRUS数据集上达到了80.46%的准确率。版权所有：2023 Elsevier Ltd. 保留所有权利。

Current convolutional neural network-based ultrasound automatic classification models for prostate cancer often rely on extensive manual labeling. Although Self-supervised Learning (SSL) have shown promise in addressing this problem, those data that from medical scenarios contains intra-class similarity conflicts, so using loss calculations directly that include positive and negative sample pairs can mislead training. SSL method tends to focus on global consistency at the image level and does not consider the internal informative relationships of the feature map. To improve the efficiency of prostate cancer diagnosis, using SSL method to learn key diagnostic information in ultrasound images, we proposed a self-supervised dual-head attentional bootstrap learning network (SDABL), including Online-Net and Target-Net. Self-Position Attention Module (SPAM) and adaptive maximum channel attention module (CAAM) are inserted in both paths simultaneously. They captures position and inter-channel attention and of the original feature map with a small number of parameters, solve the information optimization problem of feature maps in SSL. In loss calculations, we discard the construction of negative sample pairs, and instead guide the network to learn the consistency of the location space and channel space by drawing closer to the embedding representation of positive samples continuously. We conducted numerous experiments on the prostate Transrectal ultrasound (TRUS) dataset, experiments show that our SDABL pre-training method has significant advantages over both mainstream contrast learning methods and other attention-based methods. Specifically, the SDABL pre-trained backbone achieves 80.46% accuracy on our TRUS dataset after fine-tuning.Copyright © 2023 Elsevier Ltd. All rights reserved.