Markerless Tracking-Based Registration for Medical Image Motion Correction

Our study focuses on isolating swallowing dynamics from interfering patient motion in videofluoroscopy, an X-ray technique that records patients swallowing a radiopaque bolus. These recordings capture multiple motion sources, including head movement, anatomical displacements, and bolus transit. To enable precise analysis of swallowing physiology, we aim to eliminate distracting motion, particularly head movement, while preserving essential swallowing-related dynamics. Optical flow methods fail due to artifacts like flickering and instability, making them unreliable for distinguishing different motion groups. We evaluated markerless tracking approaches (CoTracker, PIPs++, TAP-Net) and quantified tracking accuracy in key medical regions of interest. Our findings show that even sparse tracking points generate morphing displacement fields that outperform leading registration methods such as ANTs, LDDMM, and VoxelMorph. To compare all approaches, we assessed performance using MSE and SSIM metrics post-registration. We introduce a novel motion correction pipeline that effectively removes disruptive motion while preserving swallowing dynamics and surpassing competitive registration techniques. Code will be available after review.

SpokeN-100: A Cross-Lingual Benchmarking Dataset for The Classification of Spoken Numbers in Different Languages

Benchmarking plays a pivotal role in assessing and enhancing the performance of compact deep learning models designed for execution on resource-constrained devices, such as microcontrollers. Our study introduces a novel, entirely artificially generated benchmarking dataset tailored for speech recognition, representing a core challenge in the field of tiny deep learning. SpokeN-100 consists of spoken numbers from 0 to 99 spoken by 32 different speakers in four different languages, namely English, Mandarin, German and French, resulting in 12,800 audio samples. We determine auditory features and use UMAP (Uniform Manifold Approximation and Projection for Dimension Reduction) as a dimensionality reduction method to show the diversity and richness of the dataset. To highlight the use case of the dataset, we introduce two benchmark tasks: given an audio sample, classify (i) the used language and/or (ii) the spoken number. We optimized state-of-the-art deep neural networks and performed an evolutionary neural architecture search to find tiny architectures optimized for the 32-bit ARM Cortex-M4 nRF52840 microcontroller. Our results represent the first benchmark data achieved for SpokeN-100.