Analysis of cellularity in H&E-stained rat bone marrow tissue via deep learning.

Our objective was to develop an automated deep-learning-based method to evaluate cellularity in rat bone marrow hematoxylin and eosin whole slide images for preclinical safety assessment. We trained a shallow CNN for segmenting marrow, 2 Mask R-CNN models for segmenting megakaryocytes (MKCs), and small hematopoietic cells (SHCs), and a SegNet model for segmenting red blood cells. We incorporated the models into a pipeline that identifies and counts MKCs and SHCs in rat bone marrow. We compared cell segmentation and counts that our method generated to those that pathologists generated on 10 slides with a range of cell depletion levels from 10 studies. For SHCs, we compared cell counts that our method generated to counts generated by Cellpose and Stardist. The median Dice and object Dice scores for MKCs using our method vs pathologist consensus and the inter- and intra-pathologist variation were comparable, with overlapping first-third quartile ranges. For SHCs, the median scores were close, with first-third quartile ranges partially overlapping intra-pathologist variation. For SHCs, in comparison to Cellpose and Stardist, counts from our method were closer to pathologist counts, with a smaller 95% limits of agreement range. The performance of the bone marrow analysis pipeline supports its incorporation into routine use as an aid for hematotoxicity assessment by pathologists. The pipeline could help expedite hematotoxicity assessment in preclinical studies and consequently could expedite drug development. The method may enable meta-analysis of rat bone marrow characteristics from future and historical whole slide images and may generate new biological insights from cross-study comparisons.

An automated mapping method for Nissl-stained mouse brain histologic sections.

BACKGROUND: Histologic evaluation of the central nervous system is often a critical endpoint in in vivo efficacy studies, and is considered the essential component of neurotoxicity assessment in safety studies. Automated image analysis is a powerful tool that can radically reduce the workload associated with evaluating brain histologic sections. NEW METHOD: We developed an automated brain mapping method that identifies neuroanatomic structures in mouse histologic coronal brain sections. The method utilizes the publicly available Allen Brain Atlas to map brain regions on digitized Nissl-stained sections. RESULTS: The method's accuracy was first assessed by comparing the mapping results to structure delineations from the Franklin and Paxinos (FP) mouse brain atlas. Brain regions mapped from FP Nissl-stained sections and calculated volumes were similar to structure delineations and volumes derived from corresponding FP illustrations. We subsequently applied our method to mouse brain sections from an in vivo study where the hippocampus was the structure of interest. Nissl-stained sections were mapped and hippocampal boundaries transferred to adjacent immunohistochemically stained sections. Optical density quantification results were comparable to those from time-consuming, manually drawn hippocampal delineations on the IHC-stained sections. COMPARISON WITH EXISTING METHODS: Compared to other published methods, our method requires less manual input, and has been validated comprehensively using a secondary atlas, as well as manually annotated brain IHC sections from 68 study mice. CONCLUSIONS: We propose that our automated brain mapping method enables greater efficiency and consistency in mouse neuropathologic assessments.

Semiautomated segmentation of blood vessels using ellipse-overlap criteria: method and comparison to manual editing.

Two-dimensional intensity-based methods for the segmentation of blood vessels from computed-tomography-angiography data often result in spurious segments that originate from other objects whose intensity distributions overlap with those of the vessels. When segmented images include spurious segments, additional methods are required to select segments that belong to the target vessels. We describe a method that allows experts to select vessel segments from sequences of segmented images with little effort. Our method uses ellipse-overlap criteria to differentiate between segments that belong to different objects and are separated in plane but are connected in the through-plane direction. To validate our method, we used it to extract vessel regions from volumes that were segmented via analysis of isolabel-contour maps, and showed that the difference between the results of our method and manually-edited results was within inter-expert variability. Although the total editing duration for our method, which included user-interaction and computer processing, exceeded that of manual editing, the extent of user interaction required for our method was about a fifth of that required for manual editing.

Interactive specification of regions of interest on brain surfaces.

We describe Surface Editor-a tool for interactive specification of regions of interest (ROIs) on brain surfaces. The tool allows users to define subsurfaces by tracing around areas within a triangle-mesh brain surface. The input to the program is a triangle-mesh representation of a brain volume and a set of user-defined input points on the mesh. The program connects each pair of successive input points with a polyline that results from the intersection of the mesh with a plane that is approximately normal to the mesh. The polyline comprises coplanar line segments. The boundary of an ROI is a connected set of polylines that intersects triangle edges to form a continuous path. To validate Surface Editor we demonstrated that the program could be used to interactively delineate gyri on brain surfaces, and we showed that paths that the program generated were comparable to paths that a user generated and to shortest paths.