An inpainting approach to manipulate asymmetry in pre-operative breast images

TL;DR

This paper introduces an inpainting method to modify breast images, allowing prediction of aesthetic outcomes post-surgery by realistically simulating asymmetries and alterations caused by breast cancer treatments.

Contribution

It presents novel inpainting models, including invertible networks, to manipulate breast shape and nipple position without requiring ground-truth annotations.

Findings

Models can realistically alter breast images.

Able to simulate post-operative asymmetries.

Effective on multiple datasets.

Abstract

One of the most frequent modalities of breast cancer treatment is surgery. Breast surgery can cause visual alterations to the breasts, due to scars and asymmetries. To enable an informed choice of treatment, the patient must be adequately informed of the aesthetic outcomes of each treatment plan. In this work, we propose an inpainting approach to manipulate breast shape and nipple position in breast images, for the purpose of predicting the aesthetic outcomes of breast cancer treatment. We perform experiments with various model architectures for the inpainting task, including invertible networks capable of manipulating breasts in the absence of ground-truth breast contour and nipple annotations. Experiments on two breast datasets show the proposed models' ability to realistically alter a patient's breasts, enabling a faithful reproduction of breast asymmetries of post-operative patients in pre-operative images.