nnDetection: A Self-configuring Method for Medical Object Detection
This addresses the research bottleneck of manual configuration in medical object detection, which is crucial for clinical diagnostics, though it is incremental as it extends the nnU-Net approach from segmentation to detection.
The authors tackled the cumbersome configuration process in medical object detection by developing nnDetection, a self-configuring method that adapts automatically to various tasks, achieving results on par with or superior to state-of-the-art on benchmarks like ADAM and LUNA16.
Simultaneous localisation and categorization of objects in medical images, also referred to as medical object detection, is of high clinical relevance because diagnostic decisions often depend on rating of objects rather than e.g. pixels. For this task, the cumbersome and iterative process of method configuration constitutes a major research bottleneck. Recently, nnU-Net has tackled this challenge for the task of image segmentation with great success. Following nnU-Net's agenda, in this work we systematize and automate the configuration process for medical object detection. The resulting self-configuring method, nnDetection, adapts itself without any manual intervention to arbitrary medical detection problems while achieving results en par with or superior to the state-of-the-art. We demonstrate the effectiveness of nnDetection on two public benchmarks, ADAM and LUNA16, and propose 11 further medical object detection tasks on public data sets for comprehensive method evaluation. Code is at https://github.com/MIC-DKFZ/nnDetection .