Artifact Augmentation for Enhanced Tissue Detection in Microscope Scanner Systems.

As the field of routine pathology transitions into the digital realm, there is a surging demand for the full automation of microscope scanners, aiming to expedite the process of digitizing tissue samples, and consequently, enhancing the efficiency of case diagnoses. The key to achieving seamless automatic imaging lies in the precise detection and segmentation of tissue sample regions on the glass slides. State-of-the-art approaches for this task lean heavily on deep learning techniques, particularly U-Net convolutional neural networks. However, since samples can be highly diverse and prepared in various ways, it is almost impossible to be fully prepared for and cover every scenario with training data. We propose a data augmentation step that allows artificially modifying the training data by extending some artifact features of the available data to the rest of the dataset. This procedure can be used to generate images that can be considered synthetic. These artifacts could include felt pen markings, speckles of dirt, residual bubbles in covering glue, or stains. The proposed approach achieved a 1-6% improvement for these samples according to the F1 Score metric.

Black Hole Disks in Galactic Nuclei.

Gravitational torques among objects orbiting a supermassive black hole drive the rapid reorientation of orbital planes in nuclear star clusters (NSCs), a process known as vector resonant relaxation. In this Letter, we determine the statistical equilibrium of systems with a distribution of masses, semimajor axes, and eccentricities. We average the interaction over the apsidal precession time and construct a Monte Carlo Markov chain method to sample the microcanonical ensemble of the NSC. We examine the case of NSCs formed by 16 episodes of star formation or globular cluster infall. We find that the massive stars and stellar mass black holes form a warped disk, while low mass stars resemble a spherical distribution with a possible net rotation. This explains the origin of the clockwise disk in the Galactic center and predicts a population of black holes (BHs) embedded within this structure. The rate of mergers among massive stars, tidal disruption events of massive stars by BHs, and BH-BH mergers are highly increased in such disks. The first two may explain the origin of the observed G1 and G2 clouds, the latter may be important for gravitational wave detections with LIGO and VIRGO. More generally, black holes are expected to settle in disks in all dense spherical stellar systems assembled by mergers of smaller systems including globular clusters.