Weakly supervised segmentation from extreme points

Abstract

Annotation of medical images has been a major bottleneck for the development of accurate and robust machine learning models. Annotation is costly and time-consuming and typically requires expert knowledge, especially in the medical domain. Here, we propose to use minimal user interaction in the form of extreme point clicks in order to train a segmentation model that can, in turn, be used to speed up the annotation of medical images. We use extreme points in each dimension of a 3D medical image to constrain an initial segmentation based on the random walker algorithm. This segmentation is then used as a weak supervisory signal to train a fully convolutional network that can segment the organ of interest based on the provided user clicks. We show that the network's predictions can be refined through several iterations of training and prediction using the same weakly annotated data. Ultimately, our method has the potential to speed up the generation process of new training datasets for the development of new machine learning and deep learning-based models for, but not exclusively, medical image analysis.

Accepted at the MICCAI Workshop for Large-scale Annotation of Biomedical data and Expert Label Synthesis, Shenzen, China, 2019

References in corpus (5)

• Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
• DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
• Constrained-CNN losses for weakly supervised segmentation
• Interactive segmentation of medical images through fully convolutional neural networks
• Accurate Weakly Supervised Deep Lesion Segmentation on CT Scans: Self-Paced 3D Mask Generation from RECIST

Cited by in corpus (4)

• MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning
• GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
• Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans
• Dense Regression Activation Maps For Lesion Segmentation in CT scans of COVID-19 patients