Ultrasound image despeckling is an important research field since it can improve the interpretability of one of the main categories of medical imaging. Many techniques have been tried over the years for ultrasound despeckling, and more recently, a great deal of attention has been focused on patch-based methods, such as non-local means (NLM) and block-matching collaborative filtering (BM3D). A common idea in these recent methods is the measure of distance between patches, originally proposed as the Euclidean distance, for filtering additive white Gaussian noise. In this work, we derive new stochastic distances for the Fisher-Tippett distribution, based on well-known statistical divergences, and use them as patch distance measures in a modified version of the BM3D algorithm for despeckling logcompressed ultrasound images. State-of-the-art results in filtering simulated, synthetic, and real ultrasound images confirm the potential of the proposed approach.

Many recent ultrasound image processing methods are based on patch comparison, such as filtering and segmentation. Identifying similar patches in noise-corrupted images is a key factor for the performance of these methods. While the Euclidean distance is ideal to handle the patch comparison under additive Gaussian noise, finding good measures to compare patches corrupted by multiplicative noise is still an open research. In this paper, we deduce several new geodesic distances, arising from parametric probabilistic spaces, and suggest them as similarity measures to process RF and log-compressed ultrasound images in patch-based methods. We provide practical examples using these measures in the fields of ultrasound image filtering and segmentation, with results that confirm the potential of the technique.

Accurate brain tumor segmentation in the early stages of the disease is crucial for the treatment’s effectiveness, avoiding exhaustive visual inspection of a qualified specialist on 3D MR brain images of multiple protocols (e.g., T1, T2, T2-FLAIR, T1-Gd). Several networks exist for Glioma segmentation, being nnU-Net one of the best. In this work, we evaluate self-calibrated convolutions in different parts of the nnU-Net network to demonstrate that self-calibrated modules in skip connections can significantly improve the enhanced-tumor and tumor-core segmentation accuracy while preserving the wholetumor segmentation accuracy.