An inpainting approach to manipulate asymmetry in pre-operative breast images
This work addresses the problem of informing patients about aesthetic outcomes of breast cancer treatment, which is significant for patients and medical professionals.
This work tackled the problem of predicting aesthetic outcomes of breast cancer treatment by manipulating breast shape and nipple position in pre-operative images, achieving faithful reproduction of breast asymmetries. The proposed models were tested on two breast datasets.
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.