Sliding Window FastEdit: A Framework for Lesion Annotation in Whole-body PET Images
This work addresses the problem of time-consuming lesion annotation for medical imaging researchers and practitioners, offering an incremental improvement over prior interactive methods by using full volumes instead of cropped/resized ones.
The paper tackles the challenge of manual voxel annotation for lesion segmentation in whole-body PET images by introducing SW-FastEdit, an interactive framework that uses user clicks instead of voxelwise annotations. It outperforms existing models on the AutoPET dataset, generalizes to the HECKTOR dataset, and a user study shows high-quality predictions with only 10 click iterations and low workload.
Deep learning has revolutionized the accurate segmentation of diseases in medical imaging. However, achieving such results requires training with numerous manual voxel annotations. This requirement presents a challenge for whole-body Positron Emission Tomography (PET) imaging, where lesions are scattered throughout the body. To tackle this problem, we introduce SW-FastEdit - an interactive segmentation framework that accelerates the labeling by utilizing only a few user clicks instead of voxelwise annotations. While prior interactive models crop or resize PET volumes due to memory constraints, we use the complete volume with our sliding window-based interactive scheme. Our model outperforms existing non-sliding window interactive models on the AutoPET dataset and generalizes to the previously unseen HECKTOR dataset. A user study revealed that annotators achieve high-quality predictions with only 10 click iterations and a low perceived NASA-TLX workload. Our framework is implemented using MONAI Label and is available: https://github.com/matt3o/AutoPET2-Submission/