Dynamic Prompt Generation for Interactive 3D Medical Image Segmentation Training
This work addresses the challenge of efficient and interactive segmentation for 3D biomedical images, which is incremental as it builds on existing foundation models with specific training enhancements.
The paper tackles the problem of interactive 3D medical image segmentation by proposing a training strategy that combines dynamic volumetric prompt generation and adaptive cropping to optimize model efficiency and simulate realistic user interactions, achieving an average Dice score of 0.6385 and NSD of 0.6614 on a competition benchmark.
Interactive 3D biomedical image segmentation requires efficient models that can iteratively refine predictions based on user prompts. Current foundation models either lack volumetric awareness or suffer from limited interactive capabilities. We propose a training strategy that combines dynamic volumetric prompt generation with content-aware adaptive cropping to optimize the use of the image encoder. Our method simulates realistic user interaction patterns during training while addressing the computational challenges of learning from sequential refinement feedback on a single GPU. For efficient training, we initialize our network using the publicly available weights from the nnInteractive segmentation model. Evaluation on the \textbf{Foundation Models for Interactive 3D Biomedical Image Segmentation} competition demonstrates strong performance with an average final Dice score of 0.6385, normalized surface distance of 0.6614, and area-under-the-curve metrics of 2.4799 (Dice) and 2.5671 (NSD).