Contrastive Learning Approach for Assessment of Phonological Precision in Patients with Tongue Cancer Using MRI Data.

Magnetic Resonance Imaging (MRI) allows analyzing speech production by capturing high-resolution images of the dynamic processes in the vocal tract. In clinical applications, combining MRI with synchronized speech recordings leads to improved patient outcomes, especially if a phonological-based approach is used for assessment. However, when audio signals are unavailable, the recognition accuracy of sounds is decreased when using only MRI data.

Quantifying articulatory variations across phonological environments: An atlas-based approach using dynamic magnetic resonance imaging.

Identification and quantification of speech variations in velar production across various phonological environments have always been an interesting topic in speech motor control studies. Dynamic magnetic resonance imaging has become a favorable tool for visualizing articulatory deformations and providing quantitative insights into speech activities over time. Based on this modality, it is proposed to employ a workflow of image analysis techniques to uncover potential deformation variations in the human tongue caused by changes in phonological environments by altering the placement of velar consonants in utterances.

Temperate Intertidal Ecosystems are Functionally Richer but More Vulnerable to Loss Than Tropical Ecosystems.

Gastropods are major contributors to a range of key ecosystem services on intertidal rock platforms, supporting trophic structure in both terrestrial and marine contexts and manipulating habitat complexity. However, the functional structure of these assemblages is rarely examined across broad spatial scales. Here, we describe patterns in gastropod functional diversity, redundancy and vulnerability to functional loss across a latitudinal gradient following the west coast of Australia (18° S-34° S).

Pushing the limits of zero-shot self-supervised super-resolution of anisotropic MR images.

Magnetic resonance images are often acquired as several 2D slices and stacked into a 3D volume, yielding a lower through-plane resolution than in-plane resolution. Many super-resolution (SR) methods have been proposed to address this, including those that use the inherent high-resolution (HR) in-plane signal as HR data to train deep neural networks. Techniques with this approach are generally both self-supervised and internally trained, so no external training data is required.

A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond.

Deep learning technologies have dramatically reshaped the field of medical image registration over the past decade. The initial developments, such as regression-based and U-Net-based networks, established the foundation for deep learning in image registration. Subsequent progress has been made in various aspects of deep learning-based registration, including similarity measures, deformation regularizations, network architectures, and uncertainty estimation.