Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This paper addresses the challenge of training cerebral microbleed (CMB) detection models due to data scarcity by developing a synthetic CMB generation pipeline. Models trained exclusively on synthetic data achieved 87% of the sensitivity of real-trained models, demonstrating the viability of synthetic data for this task. However, a performance gap persists, and effective synthetic-to-real transfer is shown to be highly dependent on the chosen downstream detection architecture.
Synthetic data alone can achieve 87% of real-data performance for cerebral microbleed detection, but architecture choice critically determines transferability.
The development of automated cerebral microbleed (CMB) detection models is hindered by the low prevalence of CMBs and the high cost of expert annotation. To address this limitation, we developed a synthetic CMB generation pipeline and investigated the effectiveness of synthetic lesions for training deep learning detectors. Models trained solely on synthetic data achieved substantial detection performance, reaching approximately 87% of the lesion sensitivity of their real-trained counterparts. We further investigated the complementary roles of synthetic and real data under different training paradigms, revealing that a significant performance gap remains. Moreover, we found that successful synthetic-to-real transfer is strongly dependent on the downstream detection architecture, providing new insight into both the potential and limitations of synthetic data for CMB detection.