Published on Fri May 25 2018

Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations

Michael Gadermayr, Laxmi Gupta, Barbara M. Klinkhammer, Peter Boor, Dorit Merhof

Generative adversarial networks exhibited excellent performances in semi-supervised image analysis scenarios. In this paper, we go even further by proposing a fully unsupervised approach for segmentation applications with prior knowledge of objects' shapes.

0
0
0
Abstract

Recently, generative adversarial networks exhibited excellent performances in semi-supervised image analysis scenarios. In this paper, we go even further by proposing a fully unsupervised approach for segmentation applications with prior knowledge of the objects' shapes. We propose and investigate different strategies to generate simulated label data and perform image-to-image translation between the image and the label domain using an adversarial model. Specifically, we assess the impact of the annotation model's accuracy as well as the effect of simulating additional low-level image features. For experimental evaluation, we consider the segmentation of the glomeruli, an application scenario from renal pathology. Experiments provide proof of concept and also confirm that the strategy for creating the simulated label data is of particular relevance considering the stability of GAN trainings.

Tue Nov 12 2019
Artificial Intelligence
Unsupervised Medical Image Segmentation with Adversarial Networks: From Edge Diagrams to Segmentation Maps
We develop and approach to unsupervised semantic medical image segmentation that extends previous work with generative adversarial networks. We use existing edge detection methods to construct simple edge diagrams, train aGenerative model to convert them into synthetic medical images, and construct a synthetic images with known segmentations.
0
0
0
Tue Dec 29 2020
Computer Vision
Annotation-Efficient Learning for Medical Image Segmentation based on Noisy Pseudo Labels and Adversarial Learning
0
0
0
Thu Oct 25 2018
Computer Vision
An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection
The identification of lesion within medical image data is necessary for diagnosis, treatment and prognosis. Segmentation and classification approaches are mainly based on supervised learning. We propose a medical image synthesis model named abnormal-to-normal translation generative adversarial network (ANT-GAN)
0
0
0
Fri May 01 2020
Computer Vision
ACCL: Adversarial constrained-CNN loss for weakly supervised medical image segmentation
We propose adversarial constrained-CNN loss, a new paradigm for weakly supervised medical image segmentation. In the new paradigm, prior knowledge is encoded and depicted by reference masks. We report an average Dice score of 75.4% with an average annotations ratio of 0.65%.
0
0
0
Fri May 08 2020
Computer Vision
Progressive Adversarial Semantic Segmentation
Progressive Adversarial Semantic Segmentation (PASS) can make improved segmentation predictions without requiring any domain-specific data during training time. PASS was tested on 8 public diabetic retinopathy and chest X-ray datasets.
0
0
0
Sun Feb 26 2017
Computer Vision
Adversarial Networks for the Detection of Aggressive Prostate Cancer
Semantic segmentation constitutes an integral part of medical image analyses. We propose utilizing an adversarial network which discriminates between expert and generated annotations. We show that the proposed scheme is superior over the de facto standard in terms of the detection sensitivity and the dice-score for aggressive prostate cancer.
0
0
0