On dataset transferability in medical image classification
This addresses the challenge of improving model transferability for medical image classification, which is incremental as it builds on existing methods but introduces new scenarios and insights.
The paper tackled the problem of suboptimal transferability estimation methods for medical image classification by proposing a novel metric that combines feature quality and gradients to evaluate source model suitability and adaptability, showing it outperforms existing metrics in new scenarios like source dataset and cross-domain transferability.
Current transferability estimation methods designed for natural image datasets are often suboptimal in medical image classification. These methods primarily focus on estimating the suitability of pre-trained source model features for a target dataset, which can lead to unrealistic predictions, such as suggesting that the target dataset is the best source for itself. To address this, we propose a novel transferability metric that combines feature quality with gradients to evaluate both the suitability and adaptability of source model features for target tasks. We evaluate our approach in two new scenarios: source dataset transferability for medical image classification and cross-domain transferability. Our results show that our method outperforms existing transferability metrics in both settings. We also provide insight into the factors influencing transfer performance in medical image classification, as well as the dynamics of cross-domain transfer from natural to medical images. Additionally, we provide ground-truth transfer performance benchmarking results to encourage further research into transferability estimation for medical image classification. Our code and experiments are available at https://github.com/DovileDo/transferability-in-medical-imaging.