Abstract White matter tractography, based on diffusion-weighted magnetic resonance images, is currently the only available in vivo method to gather information on the structural brain connectivity. The low resolution of diffusion MRI data suggests to employ probabilistic methods for streamline reconstruction, i.e., for fiber crossings. We propose a general probabilistic model for spherical regression based on the Fisher-von-Mises distribution, which efficiently estimates maximum entropy posteriors of local streamline directions with machine learning methods. The optimal precision of posteriors for streamlines is determined by an information-theoretic technique, the expected log-posterior agreement concept. It relies on the requirement that the posterior distributions of streamlines, inferred on retest measurements of the same subject, should yield stable results within the precision determined by the noise level of the data source.

Microplastics pollution has been recognized as a serious environmental concern, with research efforts underway to determine primary causes. Experiments typically generate bright-field images of microplastic fibers that are filtered from water. Environmental decision making in process engineering critically relies on accurate quantification of mi-croplastic fibers in these images. To satisfy the required standards, images are often analyzed manually, resulting in a highly tedious process, with thousands of fiber instances per image. While the shape of individual fibers is relatively simple, it is difficult to separate them in highly crowded scenes with significant overlap. We propose a fiber instance detection pipeline, which decomposes the fiber detection and segmentation into manageable sub-problems. Well separated instances are identified with robust image processing techniques, such as adaptive thresholding, and morphological skeleton analysis, while tangled fibers are separated by an algorithm based on deep pixel embeddings. Moreover, we present a modified Intersection-over-Union metric as a more appropriate similarity metric for elongated shapes. Our approach improves significantly on out-of-sample data, in particular for difficult cases of intersecting fibers.