# Generative Image Translation for Data Augmentation of Bone Lesion Pathology

arXiv: https://arxiv.org/abs/1902.02248 · HTML: https://mlsanity.com/paper/1902.02248/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification](https://mlsanity.com/paper/2111.06399/) (2021)
- [Breast Cancer Immunohistochemical Image Generation: a Benchmark Dataset and Challenge Review](https://mlsanity.com/paper/2305.03546/) (2023)
- [Improving Tuberculosis (TB) Prediction using Synthetically Generated Computed Tomography (CT) Images](https://mlsanity.com/paper/2109.11480/) (2021)
- [Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in Segmentation](https://mlsanity.com/paper/2305.19084/) (2023)
- [Knowledge-driven AI-generated data for accurate and interpretable breast ultrasound diagnoses](https://mlsanity.com/paper/2407.16634/) (2024)
- [Adversarial cycle-consistent synthesis of cerebral microbleeds for data augmentation](https://mlsanity.com/paper/2101.06468/) (2021)
- [Deep Learning Approaches for Medical Imaging Under Varying Degrees of Label Availability: A Comprehensive Survey](https://mlsanity.com/paper/2504.11588/) (2025)

## Abstract (arXiv)

Insufficient training data and severe class imbalance are often limiting factors when developing machine learning models for the classification of rare diseases. In this work, we address the problem of classifying bone lesions from X-ray images by increasing the small number of positive samples in the training set. We propose a generative data augmentation approach based on a cycle-consistent generative adversarial network that synthesizes bone lesions on images without pathology. We pose the generative task as an image-patch translation problem that we optimize specifically for distinct bones (humerus, tibia, femur). In experimental results, we confirm that the described method mitigates the class imbalance problem in the binary classification task of bone lesion detection. We show that the augmented training sets enable the training of superior classifiers achieving better performance on a held-out test set. Additionally, we demonstrate the feasibility of transfer learning and apply a generative model that was trained on one body part to another.