针对医学影像异常检测，提出测试时选择性自适应方法，提升新场景下检测准确率。
Selective Test-Time Adaptation for Unsupervised Anomaly Detection using Neural Implicit Representations
- 利用预训练特征的固有特性，零样本选择性适配未知域图像
- 在脑部异常检测中，对脑室扩大和水肿的检出率分别提升78%和24%
- 无需修改源模型，可兼容任意基于重构的异常检测方法
医学影像深度学习模型在面对训练时未见的新临床场景时面临挑战。测试时自适应为优化模型提供了有前景的解决方案，但其在异常检测（AD）中的应用仍基本空白。AD旨在高效识别偏离正常分布的情况；然而，完全自适应（包括病理性变化）可能意外学习到本应检测的异常。本文提出一种新颖的“选择性测试时自适应”概念，利用深度预训练特征的内在特性，以零样本方式选择性地适配任何来自未知域的测试图像。该方法采用模型无关、轻量级多层感知机实现神经隐式表示，可在不改变源训练模型的前提下，适配任意基于重构的异常检测方法输出。在脑部异常检测上的严格验证表明，该策略显著提升了多种病症及不同目标分布下的检测准确率。具体而言，对脑室扩大和水肿的检出率分别提高达78%和24%。
原文摘要 · Abstract (English)
Deep learning models in medical imaging often encounter challenges when adapting to new clinical settings unseen during training. Test-time adaptation offers a promising approach to optimize models for these unseen domains, yet its application in anomaly detection (AD) remains largely unexplored. AD aims to efficiently identify deviations from normative distributions; however, full adaptation, including pathological shifts, may inadvertently learn the anomalies it intends to detect. We introduce a novel concept of selective test-time adaptation that utilizes the inherent characteristics of deep pre-trained features to adapt selectively in a zero-shot manner to any test image from an unseen domain. This approach employs a model-agnostic, lightweight multi-layer perceptron for neural implicit representations, enabling the adaptation of outputs from any reconstruction-based AD method without altering the source-trained model. Rigorous validation in brain AD demonstrated that our strategy substantially enhances detection accuracy for multiple conditions and different target distributions. Specifically, our method improves the detection rates by up to 78% for enlarged ventricles and 24% for edemas.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。