CSCS is a dataset-aware method for cold-start active learning in 3D medical image segmentation. Given a fully unlabeled pool, CSCS selects an initial labeled set L₀ by combining SSL embeddings, ...

It means that the use of the query-guided attention method allows for efficient feature extraction without a significant increase in complexity. The application of an ensemble method further enhances ...

9 ) applied a fast Fuzzy C-Means (FCM) clustering algorithm for liver segmentation in CT images. While their method was efficient and accurate on a small dataset of 20 images, it remains limited by ...