Medical image segmentation with imperfect 3D bounding boxes

08/06/2021
by   Ekaterina Redekop, et al.
0

The development of high quality medical image segmentation algorithms depends on the availability of large datasets with pixel-level labels. The challenges of collecting such datasets, especially in case of 3D volumes, motivate to develop approaches that can learn from other types of labels that are cheap to obtain, e.g. bounding boxes. We focus on 3D medical images with their corresponding 3D bounding boxes which are considered as series of per-slice non-tight 2D bounding boxes. While current weakly-supervised approaches that use 2D bounding boxes as weak labels can be applied to medical image segmentation, we show that their success is limited in cases when the assumption about the tightness of the bounding boxes breaks. We propose a new bounding box correction framework which is trained on a small set of pixel-level annotations to improve the tightness of a larger set of non-tight bounding box annotations. The effectiveness of our solution is demonstrated by evaluating a known weakly-supervised segmentation approach with and without the proposed bounding box correction algorithm. When the tightness is improved by our solution, the results of the weakly-supervised segmentation become much closer to those of the fully-supervised one.

READ FULL TEXT

page 3

page 6

research
01/28/2023

Weakly Supervised Image Segmentation Beyond Tight Bounding Box Annotations

Weakly supervised image segmentation approaches in the literature usuall...
research
09/05/2023

Anatomy-Driven Pathology Detection on Chest X-rays

Pathology detection and delineation enables the automatic interpretation...
research
11/17/2018

Weakly Supervised Semantic Image Segmentation with Self-correcting Networks

Building a large image dataset with high-quality object masks for semant...
research
05/29/2021

Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks

Accurate segmentation for medical images is important for clinical diagn...
research
07/27/2020

Point-to-set distance functions for weakly supervised segmentation

When pixel-level masks or partial annotations are not available for trai...
research
04/27/2021

Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation

Pixel-wise segmentation is one of the most data and annotation hungry ta...
research
12/29/2018

Annotation-cost Minimization for Medical Image Segmentation using Suggestive Mixed Supervision Fully Convolutional Networks

For medical image segmentation, most fully convolutional networks (FCNs)...

Please sign up or login with your details

Forgot password? Click here to reset