MIPR:Automatic Annotation of Medical Images with Pixel Rearrangement

TL;DR

The paper introduces MIPR, a novel semi-supervised approach that uses pixel rearrangement and GANs to generate labeled medical images, achieving annotation quality comparable to doctors.

Contribution

MIPR is the first method to directly generate labeled medical images from unlabeled data using pixel rearrangement and GANs, reducing annotation effort.

Findings

MIPR achieves segmentation performance comparable to expert annotations.

The method reduces the need for manual labeling in medical imaging.

Experiments on ISIC18 demonstrate improved annotation efficiency.

Abstract

Most of the state-of-the-art semantic segmentation reported in recent years is based on fully supervised deep learning in the medical domain. How?ever, the high-quality annotated datasets require intense labor and domain knowledge, consuming enormous time and cost. Previous works that adopt semi?supervised and unsupervised learning are proposed to address the lack of anno?tated data through assisted training with unlabeled data and achieve good perfor?mance. Still, these methods can not directly get the image annotation as doctors do. In this paper, inspired by self-training of semi-supervised learning, we pro?pose a novel approach to solve the lack of annotated data from another angle, called medical image pixel rearrangement (short in MIPR). The MIPR combines image-editing and pseudo-label technology to obtain labeled data. As the number of iterations increases, the edited image is similar to the original image, and the labeled result is similar to the doctor annotation. Therefore, the MIPR is to get labeled pairs of data directly from amounts of unlabled data with pixel rearrange?ment, which is implemented with a designed conditional Generative Adversarial Networks and a segmentation network. Experiments on the ISIC18 show that the effect of the data annotated by our method for segmentation task is is equal to or even better than that of doctors annotations