Impact of synthetic data on training a deep learning model for lesion detection and classification in contrast-enhanced mammography
Year: 2025
Type: article
Abstract: Purpose: Predictive models for contrast-enhanced mammography often perform better at detecting and classifying enhancing masses than (non-enhancing) microcalcification clusters. We aim to investigate whether incorporating synthetic data with simulated microcalcification clusters during training can enhance model performance. Approach: Microcalcification clusters were simulated in low-energy images of lesion-free breasts from 782 patients, considering local texture features. Enhancement was simulated in the corresponding recombined images. A deep learning (DL) model for lesion detection and classification was trained with varying ratios of synthetic and real (850 patients) data. In addition, a handcrafted radiomics classifier was trained using delineations and class labels from real data, and predictions from both models were ensembled. Validation was performed on internal (212 patients) and external (279 patients) real datasets. Results: The DL model trained exclusively with synthetic data detected over 60% of malignant lesions. Adding synthetic data to smaller real training sets improved detection sensitivity for malignant lesions but decreased precision. Performance plateaued at a detection sensitivity of 0.80. The ensembled DL and radiomics models performed worse than the standalone DL model, decreasing the area under this receiver operating characteristic curve from 0.75 to 0.60 on the external validation set, likely due to falsely detected suspicious regions of interest. Conclusions: Synthetic data can enhance DL model performance, provided model setup and data distribution are optimized. The possibility to detect malignant lesions without real data present in the training set confirms the utility of synthetic data. It can serve as a helpful tool, especially when real data are scarce, and it is most effective when complementing real data.
Source: Journal of medical imaging
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G1868941057, G2228389852, G2313721325, G258106459, Optimal treatment for patients with solid tumours in Europe through Artificial intelligence, G3182435129, G340360894, A European Cancer Image Platform Linked to Biological and Health Data for Next-Generation Artificial Intelligence and Precision Medicine in Oncology, G5208378559, The malignant Glioma immuno-oncology matchmaker: towards data-driven precision medicine using spatially resolved radio-multiomics, G6131699335, Accelerating the lab to market transition of AI tools for cancer management, International Clinical Validation of Radiomics Artificial Intelligence for Breast Cancer Treatment Planning, G7770515289, AI powered Data Curation & Publishing Virtual Assistant, G8524325376, Real-world-data Enabled Assessment for heaLth regulatory decision-Making
OpenAlex ID: W4409892829
