Analise de Desaprendizado de Maquina em Modelos de Classificacao de Imagens Medicas
This work addresses privacy concerns in medical AI by adapting unlearning techniques to a new domain, but it is incremental as it applies an existing method to medical data.
The paper tackled the problem of applying machine unlearning to medical image classification, evaluating the SalUn model on three datasets and finding it achieves performance close to full retraining.
Machine unlearning aims to remove private or sensitive data from a pre-trained model while preserving the model's robustness. Despite recent advances, this technique has not been explored in medical image classification. This work evaluates the SalUn unlearning model by conducting experiments on the PathMNIST, OrganAMNIST, and BloodMNIST datasets. We also analyse the impact of data augmentation on the quality of unlearning. Results show that SalUn achieves performance close to full retraining, indicating an efficient solution for use in medical applications.