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

2025-02-08

AI Summary

This study addresses the clinical need for preoperative aesthetic assessment in breast cancer surgery by proposing an unsupervised image inpainting method to simulate post-surgical breast asymmetry under alternative surgical plans, thereby supporting informed patient decision-making. Methodologically, we introduce the first anatomy-constrained editing framework based on invertible neural networks (INNs), which localizes breast contours and nipple positions accurately without annotated data and enables controllable shape and positional editing. Anatomical plausibility is enforced via embedded anatomical priors, ensuring clinically realistic outputs. Evaluated on two real-world breast imaging datasets, our method achieves high-fidelity reconstruction of asymmetric postoperative morphology, with visual quality meeting clinical usability standards. To our knowledge, this is the first interpretable, fully unsupervised, and anatomically consistent generative paradigm for personalized preoperative aesthetic prediction.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

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.

Problem

• Predict aesthetic outcomes of breast cancer surgery
• Manipulate breast shape and nipple position
• Reproduce breast asymmetries in pre-operative images

Innovation

• Inpainting approach predicts aesthetic outcomes
• Manipulates breast shape and nipple position
• Uses invertible networks without ground-truth annotations