MoPET: Parameter-Efficient Mixture-of-Experts for Unified Medical Image Classification

AI 中文解读

医学影像AI迎来新突破！研究人员开发出名为MoPET的智能系统，让一个AI模型同时胜任多种医疗影像诊断任务，准确率还比以往更高。传统方法中，每种疾病需要单独训练一个AI助手，不仅成本高昂，而且不同任务之间还会互相干扰。MoPET借鉴了“专家会诊”的思路：系统内置多个专业“小助手”，每张医学影像进来时，智能调度员会精准指定最合适的几位专家协同诊断，既共享了知识，又避免了互相添乱。在权威医学影像数据集MedMNIST上的测试表明，MoPET用单一模型处理四种不同诊断任务，平均准确率达到93.46%，优于传统独立模型组合的92.83%。更令人振奋的是，将不同来源的影像数据一起训练能显著提升数据匮乏场景的诊断性能，平均准确率从81.58%跃升至83.58%。这项技术意味着未来医院可能只需一个通用AI系统就能辅助多种疾病筛查，大大降低部署成本；对患者而言，意味着更精准高效的影像诊断服务，尤其造福医疗资源稀缺地区。研究团队已公开全部代码，加速了这一技术走向临床应用的进程。

Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with full end-to-end network updates. Although PEFT successfully navigates limited data scenarios, it inherently forces the training of a separate, isolated adapter for every specific diagnostic task. Consolidating these isolated adapters into a single generalist network risks negative transfer, as optimization gradients from conflicting visual domains interfere. To address this, we propose MoPET, a mixture-of-experts (MoE) method that uses a learned sparse router to direct each input through a small subset of low-rank PEFT experts injected into a frozen foundation model, sharing capacity across datasets while limiting cross-domain gradient conflict. Through selected evaluations on the MedMNIST benchmark, we first establish that PEFT outperforms full network updates, improving average accuracy from 86.50% to 88.97%. We then show that a single MoPET model consolidates four heterogeneous datasets into one network, improving average accuracy over the best isolated PEFT adapters (93.46% versus 92.83%). Finally, we show that co-training with auxiliary datasets improves accuracy on data-constrained clinical targets, raising average target accuracy over the strongest isolated adapter from 81.58% to 83.58%. Our source code is publicly available at https://github.com/sdoerrich97/mopet .