发表机构
Emory University; Yale University（埃默里大学; 耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RadHarmony是一款开源Python库，用于统一处理异构放射数据集，引入AI智能体技能简化数据集整合，可预训练视觉Transformer基线并提供相关代码与模型权重。
AI 中文摘要
在放射图像上训练深度学习模型，需要整合来自不同来源、文件格式、目录布局、标签架构及注释类型的异构数据集。我们提出RadHarmony，一款开源Python库，提供统一API用于加载、协调与扩充放射数据集，主要聚焦胸部X线片，早期支持计算机断层扫描（CT）与磁共振成像（MRI）。RadHarmony将24个公开数据集的元数据标准化为单一表格格式，封装MONAI的映射式数据集以实现深度学习就绪的样本交付，支持可选的磁盘缓存，通过单一接口支持分类标签、分割掩码、边界框及放射报告文本，还配备交互式可视化工具用于数据集探索与验证。为降低新数据集整合门槛，RadHarmony引入AI智能体技能，指导从原始数据检查到代码生成与测试的完整整合工作流。我们通过预训练RadHarmony-ViT（一款参考视觉Transformer基线）展示该库的实用性，该模型无需数据集专属代码即可整合三个异构胸部X线片数据集，代码与预训练模型权重可在指定URL获取。
英文摘要
Training deep learning models on radiological images requires integrating heterogeneous datasets across different sources, file formats, directory layouts, label schemas, and annotation types. We present RadHarmony, an open-source Python library that provides a unified API for loading, harmonizing, and augmenting radiological datasets, with a primary focus on chest radiographs and early support for computed tomography (CT) and magnetic resonance imaging (MRI). RadHarmony standardizes metadata from 24 public datasets into a single tabular format, wraps MONAI's map-style datasets for deep-learning-ready sample delivery with optional on-disk caching, and supports classification labels, segmentation masks, bounding boxes, and radiology report text through a single interface, with an interactive visualization tool for dataset exploration and verification. To lower the barrier for integrating new datasets, RadHarmony introduces an AI-agent skill that guides the full integration workflow from raw data inspection through code generation and testing. We demonstrate the library's utility by pretraining RadHarmony-ViT, a reference vision transformer baseline that combines three heterogeneous chest radiograph datasets with no dataset-specific code. The code and pretrained model weights are available at https://github.com/f10409/RadHarmony.
