Visinity: Visual Spatial Neighborhood Analysis for Multiplexed Tissue Imaging Data

psudo: Exploring Multi-Channel Biomedical Image Data with Spatially and Perceptually Optimized Pseudocoloring

Over the past century, multichannel fluorescence imaging has been pivotal in myriad scientific breakthroughs by enabling the spatial visualization of proteins within a biological sample. With the shift to digital methods and visualization software, experts can now flexibly pseudocolor and combine image channels, each corresponding to a different protein, to explore their spatial relationships. We thus propose psudo, an interactive system that allows users to create optimal color palettes for multichannel spatial data. In psudo, a novel optimization method generates palettes that maximize the perceptual differences between channels while mitigating confusing color blending in overlapping channels. We integrate this method into a system that allows users to explore multi-channel image data and compare and evaluate color palettes for their data. An interactive lensing approach provides on-demand feedback on channel overlap and a color confusion metric while giving context to the underlying channel values. Color palettes can be applied globally or, using the lens, to local regions of interest. We evaluate our palette optimization approach using three graphical perception tasks in a crowdsourced user study with 150 participants, showing that users are more accurate at discerning and comparing the underlying data using our approach. Additionally, we showcase psudo in a case study exploring the complex immune responses in cancer tissue data with a biologist.

Spatial Patterning Analysis of Cellular Ensembles (SPACE) discovers complex spatial organization at the cell and tissue levels

Spatial patterns of cells and other biological elements drive both physiologic and pathologic processes within tissues. While many imaging and transcriptomic methods document tissue organization, discerning these patterns is challenging, especially when they involve multiple elements in complex arrangements. To address this challenge, we present Spatial Patterning Analysis of Cellular Ensembles (SPACE), an R package for analysis of high-plex spatial data. SPACE is compatible with any data collection modality that records values (i.e., categorical cell/structure types or quantitative expression levels) at fixed spatial coordinates (i.e., 2d pixels or 3d voxels). SPACE detects not only broad patterns of co-occurrence but also context-dependent associations, quantitative gradients and orientations, and other organizational complexities. Via a robust information theoretic framework, SPACE explores all possible ensembles of tissue elements - single elements, pairs, triplets, and so on - and ranks the most strongly patterned ensembles. For single images, rankings reflect patterns that differ from random assortment. For sets of images, rankings reflect patterns that differ across sample groups (e.g., genotypes, treatments, timepoints, etc.). Further tools then thoroughly characterize the nature of each pattern for intuitive interpretation. We validate SPACE and demonstrate its advantages using murine lymph node images for which ground truth has been defined. We then use SPACE to detect new patterns across varied datasets, including tumors and tuberculosis granulomas.

DASS Good: Explainable Data Mining of Spatial Cohort Data

Developing applicable clinical machine learning models is a difficult task when the data includes spatial information, for example, radiation dose distributions across adjacent organs at risk. We describe the co-design of a modeling system, DASS, to support the hybrid human-machine development and validation of predictive models for estimating long-term toxicities related to radiotherapy doses in head and neck cancer patients. Developed in collaboration with domain experts in oncology and data mining, DASS incorporates human-in-the-loop visual steering, spatial data, and explainable AI to augment domain knowledge with automatic data mining. We demonstrate DASS with the development of two practical clinical stratification models and report feedback from domain experts. Finally, we describe the design lessons learned from this collaborative experience.