• Corpus ID: 1153755

Learning under Distributed Weak Supervision

@article{Rajchl2016LearningUD,
  title={Learning under Distributed Weak Supervision},
  author={Martin Rajchl and M. J. Lee and Franklin Schrans and Alice Davidson and Jonathan Passerat-Palmbach and Giacomo Tarroni and Amir Alansary and Ozan Oktay and Bernhard Kainz and Daniel Rueckert},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.01100}
}
The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks and collect such annotations from a crowd of non-expert raters. The crowd annotations are… 
View PDF on arXiv
23 Citations
Highly Influential Citations
2
Background Citations
10
Methods Citations
9

Figures and Tables from this paper

23 Citations

Going to Extremes: Weakly Supervised Medical Image Segmentation

This work suggests using minimal user interaction in the form of extreme point clicks to train a segmentation model which, in effect, can be used to speed up medical image annotation.

Employing Weak Annotations for Medical Image Analysis Problems

This study examines the impact of expertise and the amount of available annotations on the accuracy outcome of a liver segmentation problem in an abdominal computed tomography (CT) image database and proposes a method for outlier correction making use of a weakly labelled atlas.

A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis

Constrained‐CNN losses for weakly supervised segmentation☆

Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks

Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis

A Survey on Deep Learning for Skin Lesion Segmentation

This survey cross-examine 177 research papers that deal with deep learning-based segmentation of skin lesions and analyzes these works along several dimensions, including input data, model design, and evaluation aspects.

DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks

This paper proposes a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in this case bounding boxes, and test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset.

Weakly-supervised convolutional neural networks of renal tumor segmentation in abdominal CTA images

A novel weakly-supervised convolutional neural network (CNN) for renal tumor segmentation that achieves a higher dice coefficient (DSC) and is close to the fully supervised deep CNN.

A Survey of Crowdsourcing in Medical Image Analysis

This survey reviews studies applying crowdsourcing to the analysis of medical images, published prior to July 2018, and identifies common approaches, challenges and considerations, providing guidance of utility to researchers adopting this approach.

References

SHOWING 1-10 OF 19 REFERENCES

Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

Expectation-Maximization (EM) methods for semantic image segmentation model training under weakly supervised and semi-supervised settings are developed and extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentsation benchmark, while requiring significantly less annotation effort.

Can Masses of Non-Experts Train Highly Accurate Image Classifiers? - A Crowdsourcing Approach to Instrument Segmentation in Laparoscopic Images

This study suggests that segmentations computed from annotations of multiple anonymous non-experts are comparable to those made by medical experts and that the scientific community might no longer need to rely on experts to generate reference or training data for certain applications.

Predicting Semantic Descriptions from Medical Images with Convolutional Neural Networks

This paper demonstrates how it can learn accurate voxel-level classifiers based on weak volume-level semantic descriptions on a set of 157 optical coherence tomography volumes and shows how semantic information increases classification accuracy for intraretinal cystoid fluid, subretinal fluid and normal retinal tissue.

DeepCut: Object Segmentation From Bounding Box Annotations Using Convolutional Neural Networks

This paper proposes a method to obtain pixelwise object segmentations given an image dataset labelled weak annotations, in this case bounding boxes, and test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset.

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

  • Jifeng DaiKaiming HeJian Sun
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
This paper proposes a method that achieves competitive accuracy but only requires easily obtained bounding box annotations, and yields state-of-the-art results on PASCAL VOC 2012 and PASCal-CONTEXT.

Multi-Atlas Segmentation Using Partially Annotated Data: Methods and Annotation Strategies

This work re-examines the labelling problem common in many existing approaches and formulates its solution in terms of a Markov Random Field energy minimisation problem on a graph connecting atlases and the target image to provide a unifying framework for multi-atlas segmentation.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

Caffe: Convolutional Architecture for Fast Feature Embedding

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.

Automated fetal brain segmentation from 2D MRI slices for motion correction

LabelMe: A Database and Web-Based Tool for Image Annotation

A web-based tool that allows easy image annotation and instant sharing of such annotations is developed and a large dataset that spans many object categories, often containing multiple instances over a wide variety of images is collected.