nnU-Net

Image datasets are enormously diverse: image dimensionality (2D, 3D), modalities/input channels (RGB image, CT, MRI, microscopy, ...), image sizes, voxel sizes, class ratio, target structure properties and more change substantially between datasets. Traditionally, given a new problem, a tailored solution needs to be manually designed and optimized - a process that is prone to errors, not scalable and where success is overwhelmingly determined by the skill of the experimenter. Even for experts, this process is anything but simple: there are not only many design choices and data properties that need to be considered, but they are also tightly interconnected, rendering reliable manual pipeline optimization all but impossible!图像数据集的多样性极为显著：不同数据集间的图像维度（2D、3D）、模态与输入通道（RGB图像（RGB image）、计算机断层扫描（CT）、磁共振成像（MRI）、显微成像（microscopy）等）、图像尺寸、体素尺寸（voxel sizes）、类别比例、目标结构属性等均存在大幅差异。 传统范式下，针对全新任务需手动设计并优化定制化解决方案——这一过程不仅易出错、可扩展性不足，且任务成功与否在极大程度上取决于实验人员的专业技能。 即便对于领域专家而言，该流程也绝非易事：不仅需要考量诸多设计选型与数据属性，且这些要素彼此紧密关联，使得可靠的手动处理流程优化几乎不可能实现！

搜集汇总

背景与挑战

背景概述

nnU-Net是一个针对多样化图像数据集（如2D/3D图像、CT、MRI等）设计的工具，旨在克服传统手动定制解决方案易出错且不可扩展的问题。该数据集包含心脏图像数据和nnU-Net主程序文件。