用于分类上颌窦鼻旁异常的自监督学习
Self-supervised learning for classifying paranasal anomalies in the maxillary sinus
AI总结：
针对上颌窦鼻旁异常分类缺乏专用自监督方法的问题，提出基于3D卷积自编码器生成残差图像并重建的SSL任务，在仅用10%标注数据时AUPRC达0.79，优于现有通用方法。
摘要：
目的：鼻旁异常在常规放射学筛查中经常被发现，表现出多样的形态学特征。由于异常的多样性，监督学习方法需要包含多样异常形态的大型标注数据集。自监督学习（SSL）可用于从无标签数据中学习表示。然而，目前没有专门为上颌窦（MS）鼻旁异常分类这一下游任务设计的 SSL 方法。方法：我们的方法使用在无监督异常检测（UAD）框架中训练的 3D 卷积自编码器（CAE）。首先，我们训练 3D CAE 以减少重建正常上颌窦（MS）图像时的重建误差。然后，将此 CAE 应用于无标签数据集，通过创建残差 MS 图像来生成粗略的异常位置。随后，3D 卷积神经网络（CNN）重建这些残差图像，这构成了我们的 SSL 任务。最后，我们在包含正常和异常 MS 图像的标注数据集上微调 3D CNN 的编码器部分。结果：与现有的通用自监督方法相比，所提出的 SSL 技术表现出卓越的性能，尤其是在标注数据有限的情况下。当仅在 10% 的标注数据集上进行训练时，我们的方法在下游分类任务中实现了 0.79 的精确率-召回率曲线下面积（AUPRC）。这一性能超越了其他方法，其中 BYOL 达到 0.75 的 AUPRC，SimSiam 为 0.74，SimCLR 为 0.73，以及使用 SparK 的掩码自编码为 0.75。结论：一种本质上专注于定位鼻旁异常的自监督学习方法被证明是有利的，特别是当后续任务涉及区分正常和异常上颌窦时。访问我们的代码请前往 https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly
英文摘要：
Purpose: Paranasal anomalies, frequently identified in routine radiological screenings, exhibit diverse morphological characteristics. Due to the diversity of anomalies, supervised learning methods require large labelled dataset exhibiting diverse anomaly morphology. Self-supervised learning (SSL) can be used to learn representations from unlabelled data. However, there are no SSL methods designed for the downstream task of classifying paranasal anomalies in the maxillary sinus (MS). Methods: Our approach uses a 3D Convolutional Autoencoder (CAE) trained in an unsupervised anomaly detection (UAD) framework. Initially, we train the 3D CAE to reduce reconstruction errors when reconstructing normal maxillary sinus (MS) image. Then, this CAE is applied to an unlabelled dataset to generate coarse anomaly locations by creating residual MS images. Following this, a 3D Convolutional Neural Network (CNN) reconstructs these residual images, which forms our SSL task. Lastly, we fine-tune the encoder part of the 3D CNN on a labelled dataset of normal and anomalous MS images. Results: The proposed SSL technique exhibits superior performance compared to existing generic self-supervised methods, especially in scenarios with limited annotated data. When trained on just 10% of the annotated dataset, our method achieves an Area Under the Precision-Recall Curve (AUPRC) of 0.79 for the downstream classification task. This performance surpasses other methods, with BYOL attaining an AUPRC of 0.75, SimSiam at 0.74, SimCLR at 0.73 and Masked Autoencoding using SparK at 0.75. Conclusion: A self-supervised learning approach that inherently focuses on localizing paranasal anomalies proves to be advantageous, particularly when the subsequent task involves differentiating normal from anomalous maxillary sinuses. Access our code at https://github.com/mtec-tuhh/self-supervised-paranasal-anomaly
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
