i3Deep: Efficient 3D interactive segmentation with the nnU-NetDownload PDF

Published: 28 Feb 2022, Last Modified: 16 May 2023MIDL 2022Readers: Everyone
Keywords: interactive segmentation, nnU-Net, uncertainty, out-of-distribution
TL;DR: Interactive segmentation based on pre-selected uncertain slices for which the presegmentation is subsequently corrected by an expert and globally refined by the nnU-Net.
Abstract: 3D interactive segmentation is highly relevant in reducing the annotation time for experts. However, current methods often achieve only small segmentation improvements per interaction as lightweight models are a requirement to ensure near-realtime usage. Models with better predictive performance such as the nnU-Net cannot be employed for interactive segmentation due to their high computational demands, which result in long inference times. To solve this issue, we propose the 3D interactive segmentation framework i3Deep. Slices are selected through uncertainty estimation in an offline setting and afterwards corrected by an expert. The slices are then fed to a refinement nnU-Net, which significantly improves the global 3D segmentation from the local corrections. This approach bypasses the issue of long inference times by moving expensive computations into an offline setting that does not include the expert. For three different anatomies, our approach reduces the workload of the expert by 80.3%, while significantly improving the Dice by up to 39.5%, outperforming other state-of-the-art methods by a clear margin. Even on out-of-distribution data i3Deep is able to improve the segmentation by 19.3%.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: methodological development
Primary Subject Area: Active Learning
Secondary Subject Area: Segmentation
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
Code And Data: https://github.com/Karol-G/i3Deep
6 Replies