Supervised deep learning techniques show promise in medical image analysis. However, they require comprehensive annotated data sets, which poses challenges, particularly for rare diseases. Consequently, unsupervised anomaly detection (UAD) emerges as a viable alternative for pathology segmentation, as only healthy data is required for training. However, recent UAD anomaly scoring functions often focus on intensity only and neglect structural differences, which impedes the segmentation performance. This work investigates the potential of Structural Similarity (SSIM) to bridge this gap. SSIM captures both intensity and structural disparities and can be advantageous over the classical $l1$ error. However, we show that there is more than one optimal kernel size for the SSIM calculation for different pathologies. Therefore, we investigate an adaptive ensembling strategy for various kernel sizes to offer a more pathology-agnostic scoring mechanism. We demonstrate that this ensembling strategy can enhance the performance of DMs and mitigate the sensitivity to different kernel sizes across varying pathologies, highlighting its promise for brain MRI anomaly detection.

翻译：监督式深度学习方法在医学图像分析中展现出广阔前景，但需要大量标注数据集，这给罕见病等场景带来挑战。因此，无监督异常检测（UAD）成为病理分割的可行替代方案，因其仅需健康数据训练。然而，现有UAD异常评分函数常仅关注强度而忽视结构差异，制约了分割性能。本研究探索结构相似性（SSIM）弥补这一不足的潜力。SSIM能同时捕获强度与结构差异，相较传统$l1$误差更具优势。但我们发现，不同病理所需SSIM计算的最优核尺寸并非单一值。为此，我们提出一种针对多种核尺寸的自适应集成策略，构建与病理无关的评分机制。实验表明，该集成策略既能提升扩散模型性能，又可缓解不同病理对核尺寸选择的敏感性，突显其在脑MRI异常检测中的应用前景。