Medical Image Computing and Computer Assisted Intervention - MICCAI 2022 - 25th International Conference, Singapore, September 18-22, 2022, Proceedings, Part VIII
Medical Image Computing and Computer Assisted Intervention - MICCAI 2022 - 25th International Conference, Singapore, September 18-22, 2022, Proceedings, Part VIII
复制标题
医学图像计算和计算机辅助干预 - MICCAI 2022 - 第 25 届国际会议，新加坡，2022 年 9 月 18-22 日，会议记录，第八部分
DOI：
10.1007/978-3-031-16452-1_67
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Pinaya W
中科院分区：
文献类型：
--
作者：
Pinaya W
深度生成模型已成为检测数据中任意异常的有前景的工具，无需手动标记。最近，自回归变压器在医学成像异常检测方面取得了最先进的性能。尽管如此，这些模型仍然存在一些内在的弱点，例如需要将图像建模为一维序列、采样过程中误差的累积以及与变压器相关的大量推理时间。去噪扩散概率模型是一类非自回归生成模型，最近被证明可以在计算机视觉中产生出色的样本（超越生成对抗网络），并实现与 Transformer 竞争的对数似然，同时具有相对较快的推理时间。扩散模型可以应用于自动编码器学习的潜在表示，使它们易于扩展，并且非常适合应用于高维数据（例如医学图像）。在这里，我们提出了一种基于扩散模型的方法来检测和分割大脑成像中的异常。通过在健康数据上训练模型，然后探索其在马尔可夫链上的扩散和反向步骤，我们可以识别潜在空间中的异常区域，从而识别像素空间中的异常。与自回归方法相比，我们的扩散模型在涉及合成和真实病理病变的一系列 2D CT 和 MRI 数据实验中实现了具有竞争力的性能，并且推理时间大大缩短，使其在临床上的使用可行。
Deep generative models have emerged as promising tools for detecting arbitrary anomalies in data, dispensing with the necessity for manual labelling. Recently, autoregressive transformers have achieved state-of-the-art performance for anomaly detection in medical imaging. Nonetheless, these models still have some intrinsic weaknesses, such as requiring images to be modelled as 1D sequences, the accumulation of errors during the sampling process, and the significant inference times associated with transformers. Denoising diffusion probabilistic models are a class of non-autoregressive generative models recently shown to produce excellent samples in computer vision (surpassing Generative Adversarial Networks), and to achieve log-likelihoods that are competitive with transformers while having relatively fast inference times. Diffusion models can be applied to the latent representations learnt by autoencoders, making them easily scalable and great candidates for application to high dimensional data, such as medical images. Here, we propose a method based on diffusion models to detect and segment anomalies in brain imaging. By training the models on healthy data and then exploring its diffusion and reverse steps across its Markov chain, we can identify anomalous areas in the latent space and hence identify anomalies in the pixel space. Our diffusion models achieve competitive performance compared with autoregressive approaches across a series of experiments with 2D CT and MRI data involving synthetic and real pathological lesions with much reduced inference times, making their usage clinically viable.