发表机构
University of British Columbia; Vector Institute; Ordensklinikum Linz; University of Alberta; Exact Imaging（不列颠哥伦比亚大学; 向量研究所; 林茨 Ordenklinikum 医院; 阿尔伯塔大学; Exact Imaging 公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对微超声前列腺癌检测的域偏移问题，提出ANT分段引导的测试时自适应框架，在多中心临床试验数据上提升了活检芯和患者水平的AUC，优于TTA基线。
AI 中文摘要
使用不同成像硬件或采集协议的临床中心之间的域偏移，仍然是部署深度学习模型用于前列腺癌（PCa）检测的根本障碍。现有的测试时自适应（TTA）方法通过熵最小化或基于增强的自监督来解决分布偏移，校正图像外观的统计差异，但忽略了目标域的解剖结构。我们提出ANT，这是一个分段引导的TTA框架，通过在测试时解决辅助前列腺分段任务，将预训练的癌症检测编码器适配到目标域，该任务由来自冻结的预训练分段网络的伪掩码监督。通过将编码器表示与目标域的前列腺解剖结构对齐，ANT可校正特定域的特征漂移，同时保留癌症判别结构。该模型在一项多中心临床试验中，使用早期一代微超声扫描仪对693名患者成像进行训练，并在另一项临床试验中，使用新一代系统对两个中心的118名患者进行评估。在所有方法评估条件相同的留一中心协议下，与无自适应方法相比，ANT在活检芯和患者水平上分别将平均AUC提高了2.9%和3.6%，优于TTA基线。代码可在以下网址获取：this https URL。
英文摘要
Domain shift across clinical centers using different imaging hardware or acquisition protocols remains a fundamental barrier to deploying deep learning models for prostate cancer (PCa) detection. Existing test-time adaptation (TTA) methods address distribution shift through entropy minimization or augmentation-based self-supervision, correcting for statistical differences in image appearance but ignoring the anatomical structure of the target domain. We propose ANT, a segmentation-guided TTA framework that adapts a pretrained cancer detection encoder to the target domain by solving an auxiliary prostate segmentation task at test time, supervised by pseudo-masks from a frozen pretrained segmentation network. By aligning encoder representations to prostate anatomy in the target domain, ANT corrects domain-specific feature drift while preserving cancer-discriminative structure. The model was trained on 693 patients imaged with an earlier-generation micro-ultrasound scanner in a multi-center clinical trial, and evaluated on 118 patients acquired with a newer-generation system across two centers in another clinical trial. Under a leave-one-center-out protocol with identical evaluation conditions across all methods, ANT improves mean AUC by 2.9% and 3.6% at the biopsy-core and patient levels, respectively, over no adaptation, outperforming TTA baselines. Code is available at: https://github.com/ObedDzik/ant.git.
