Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal image

TL;DR

This paper introduces SMILE, a semi-supervised generative model that produces high-quality pseudo-normal medical images from abnormal ones, reducing the need for extensive lesion segmentation data.

Contribution

The paper presents a novel semi-supervised learning approach for medical image synthesis that effectively leverages limited segmentation data and large unlabeled datasets.

Findings

Outperforms state-of-the-art models by up to 6% in data augmentation

Achieves comparable quality with fully supervised models using only 50% segmentation data

Generates realistic pseudo-normal images with less lesion segmentation annotation

Abstract

Pseudo-normality synthesis, which computationally generates a pseudo-normal image from an abnormal one (e.g., with lesions), is critical in many perspectives, from lesion detection, data augmentation to clinical surgery suggestion. However, it is challenging to generate high-quality pseudo-normal images in the absence of the lesion information. Thus, expensive lesion segmentation data have been introduced to provide lesion information for the generative models and improve the quality of the synthetic images. In this paper, we aim to alleviate the need of a large amount of lesion segmentation data when generating pseudo-normal images. We propose a Semi-supervised Medical Image generative LEarning network (SMILE) which not only utilizes limited medical images with segmentation masks, but also leverages massive medical images without segmentation masks to generate realistic pseudo-normal images. Extensive experiments show that our model outperforms the best state-of-the-art model by up to 6% for data augmentation task and 3% in generating high-quality images. Moreover, the proposed semi-supervised learning achieves comparable medical image synthesis quality with supervised learning model, using only 50 of segmentation data.