Thomas L. Athey

Thomas L. Athey, Daniel J. Tward, Ulrich Mueller et al.

Recent advances in brain clearing and imaging have made it possible to image entire mammalian brains at sub-micron resolution. These images offer the potential to assemble brain-wide atlases of neuron morphology, but manual neuron reconstruction remains a bottleneck. Several automatic reconstruction algorithms exist, but most focus on single neuron images. In this paper, we present a probabilistic reconstruction method, ViterBrain, which combines a hidden Markov state process that encodes neuron geometry with a random field appearance model of neuron fluorescence. Our method utilizes dynamic programming to compute the global maximizers of what we call the "most probable" neuron path. Our most probable estimation method models the task of reconstructing neuronal processes in the presence of other neurons, and thus is applicable in images with several neurons. Our method operates on image segmentations in order to leverage cutting edge computer vision technology. We applied our algorithm to imperfect image segmentations where false negatives severed neuronal processes, and showed that it can follow axons in the presence of noise or nearby neurons. Additionally, it creates a framework where users can intervene to, for example, fit start and endpoints. The code used in this work is available in our open-source Python package brainlit.

Tingshan Liu, Thomas L. Athey, Benjamin D. Pedigo et al.

The exponential growth of complex data demands fully automatic clustering. Gaussian mixture models (GMMs) provide uncertainty-aware grouping but often require expertise to specify hyperparameters, e.g., component count and covariance structure. While mclust (R) automates this via Bayesian Information Criterion (BIC), Python lacks a comparable tool. We introduce AutoGMM, an open-source Python package automating GMM via strategic initialization using an agglomerative Mahalanobis heuristic, and parallelized model selection by information criteria. AutoGMM is a drop-in tool that yields strong out-of-the-box performance on classic benchmarks, targeted stress tests, and two real datasets, with favorable runtime scaling. The code is available at https://github.com/neurodata/AutoGMM with tests and reproducible workflows.

Thomas L. Athey, Shashata Sawmya, Nir Shavit

As both computer vision models and biomedical datasets grow in size, there is an increasing need for efficient inference algorithms. We utilize cascade detectors to efficiently identify sparse objects in multiresolution images. Given an object's prevalence and a set of detectors at different resolutions with known accuracies, we derive the accuracy, and expected number of classifier calls by a cascade detector. These results generalize across number of dimensions and number of cascade levels. Finally, we compare one- and two-level detectors in fluorescent cell detection, organelle segmentation, and tissue segmentation across various microscopy modalities. We show that the multi-level detector achieves comparable performance in 30-75% less time. Our work is compatible with a variety of computer vision models and data domains.

Shashata Sawmya, Thomas L. Athey, Gwyneth Liu et al.

Training segmentation models from scratch has been the standard approach for new electron microscopy connectomics datasets. However, leveraging pretrained models from existing datasets could improve efficiency and performance in constrained annotation budget. In this study, we investigate domain adaptation in connectomics by analyzing six major datasets spanning different organisms. We show that, Maximum Mean Discrepancy (MMD) between neuron image distributions serves as a reliable indicator of transferability, and identifies the optimal source domain for transfer learning. Building on this, we introduce NeuroADDA, a method that combines optimal domain selection with source-free active learning to effectively adapt pretrained backbones to a new dataset. NeuroADDA consistently outperforms training from scratch across diverse datasets and fine-tuning sample sizes, with the largest gain observed at $n=4$ samples with a 25-67\% reduction in Variation of Information. Finally, we show that our analysis of distributional differences among neuron images from multiple species in a learned feature space reveals that these domain "distances" correlate with phylogenetic distance among those species.