Biology subjects

Thomas, O. O.

Publications and source records attributed to Thomas, O. O..

4 recordsLinked to original sources

bioRxiv2025

Trustworthy detection of exencephaly in high-throughput micro-CT embryo screens with focal-loss transformers

1.Lethal and sub-viable knockout mouse lines require whole-embryo 3D imaging to connect genotype to phenotype (Dickinson et al., 2016; Cacheiro et al., 2022). There are often far fewer samples of in-class (e.g., homozygous knockouts) than wildtype or normative samples. Such extreme subject-level imbalance degrades both statistical anatomy and deep learning, often yielding saliency maps that highlight noise rather than lesion-specific signal (Adebayo et al., 2018; Buda et al., 2018; Johnson & Khoshgoftaar, 2019). We therefore asked whether focal loss (Lin et al., 2017) in combination with model-capacity control and seed ensembling can stabilize explanations without compromising classification accuracy. Exencephaly is an neural tube defect characterized by incomplete closure of the cephalic neural tube and dorsally exposed,disorganized neural tissue (Greene & Copp, 2014; Noden & de Lahunta, 1985). In our late-gestation screen, approximately 10% of embryos had exencephaly, creating severe class imbalance and underscoring the need for interpretable automation. As a test case for imbalance-aware, interpretable phenotyping, we analyzed 253 diceCT scans of E15.5 embryos (24 with exencephaly). A self-supervised transformer was fine-tuned with three regimes: cross-entropy (CE-Large), focal-loss equal-capacity (FL-Large) and focal-loss reduced-capacity (FL-Small). Five random seeds per regime yielded 15 models. Integrated Gradients saliency was quantified, and explanation quality was measured by saliency entropy (sparsity), cross-seed Dice/Jaccard similarity (reproducibility), and expert visual inspection. All 15 models achieved near perfect phenotype recognition on held-out data with 0.996 {+/-} 0.002 mean accuracy with some seeds/regimens reached 1.000. Focal loss reduced saliency entropy by up to 1.5 bits and doubled cross-seed Dice overlap, concentrating attribution on the malformed cranial vault. Ensemble-averaged heat-maps show that both focal-loss regimes concentrate attribution on the malformed cranial vault while suppressing spurious body-wide signals. Focal loss, modest capacity, and seed ensembling within a modified M3T transformer yielded sparse, reproducible, anatomically focused attribution while preserving perfect sensitivity. This supports trustworthy high-throughput phenotyping in severely imbalanced embryo screens. The workflow relies only on standard atlas registration and image pre-processing, requires no voxel-level annotations, and is readily adaptable to other structural malformations and developmental stages.

developmental biology↗

bioRxiv2025

SlicerMorph Photogrammetry: An Open-Source Photogrammetry Workflow for Reconstructing 3D Models

1. ContextAccurate three-dimensional (3D) models of skeletal and other biological specimens are crucial for ecological and evolutionary research and teaching. Here, we present a streamlined, open-source workflow for 3D photogrammetry that allows researchers to construct 3D models using the 3D Slicer and the SlicerMorph ecosystem. 2. Objectives and MethodsWe present an updated photogrammetry pipeline within the 3D Slicer ecosystem that combines advanced image masking via Segment Anything Model (SAM) with the open-source ODM reconstruction engine. Our approach systematically reduces artifacts in delicate cranial regions by automating background removal. We validate this pipeline against micro-CT references using multiple rodent skull specimens, quantifying accuracy through mean distance, root mean square error (RMSE), Hausdorff distance, and Chamfer distance. 3. ResultsOur method consistently reduces average surface error by 10-15% compared to a previous open-source photogrammetry workflow. This gain is particularly pronounced around thin or fenestrated anatomical structures such as zygomatic arches, where the previous workflow created the most noise. Although occasional increases in Hausdorff distance reflect localized photography gaps, improved mean distance and RMSE underscore improved overall fidelity. 4. Main ConclusionsThe 3D Slicer Photogrammetry extension provides a robust, fully open-source solution for generating high-quality 3D reconstructions from photographs. The streamlined pipeline lowers technical barriers to collecting reliable 3D data and fosters reproducible research across diverse biological collections.

evolutionary biology↗

bioRxiv2024

Leveraging Descriptor Learning and Functional Map-based Shape Matching for Automatic Landmark Acquisition

Geometric morphometrics is widely employed across the biological sciences for the quantification of morphological traits. However, the scalability of these methods to large datasets is hampered by the requisite placement of landmarks, which can be laborious and time consuming if done manually. Additionally, the selected landmarks embody a particular hypothesis regarding the critical geometry pertinent to the biological inquiry at hand. Modifying this hypothesis lacks flexibility, necessitating the acquisition of an entirely new set of landmarks on the entire dataset to reflect any theoretical adjustments. In our research, we investigate the precision and accuracy of landmarks derived from the comprehensive set of functional correspondences acquired through the functional map framework of geometry processing. We use a deep functional map network to learn shape descriptors that effectively yield functional map-based and point-to-point correspondences between the specimens in our dataset. We then interrogate these maps to identify corresponding landmarks given manually placed landmarks from the entire dataset. We assess our method by automating the landmarking process on a dataset comprising mandibles from various rodent species, comparing its efficacy against MALPACA, a cutting-edge technique for automatic landmark placement. Compared to MALPACA, our model is notably faster and maintains competitive accuracy. The Root Mean Square Error (RMSE) analysis reveals that while MALPACA generally exhibits the lowest RMSE, our models perform comparably, especially with smaller training datasets, suggesting strong generalizability. Visual evaluations confirm the precision of our landmark placements, with deviations remaining within an acceptable range. These findings underscore the potential of unsupervised learning models in anatomical landmark placement, providing a viable and efficient alternative to traditional methods.

bioinformatics↗

bioRxiv2021

Automated morphological phenotyping using learned shape descriptors and functional maps: A novel approach to geometric morphometrics

The methods of geometric morphometrics are commonly used to quantify morphology in a broad range of biological sciences. The application of these methods to large datasets is constrained by manual landmark placement limiting the number of landmarks and introducing observer bias. To move the field forward, we need to automate morphological phenotyping in ways that capture comprehensive representations of morphological variation with minimal observer bias. Here, we present Morphological Variation Quantifier (morphVQ), a shape analysis pipeline for quantifying, analyzing, and exploring shape variation in the functional domain. morphVQ uses descriptor learning to estimate the functional correspondence between whole triangular meshes in lieu of landmark configurations. With functional maps between pairs of specimens in a dataset we can analyze and explore shape variation. morphVQ uses Consistent ZoomOut refinement to improve these functional maps and produce a new representation of shape variation, area-based and conformal (angular) latent shape space differences (LSSDs). We compare this new representation of shape variation to shape variables obtained via manual digitization and auto3DGM, an existing approach to automated morphological phenotyping. We find that LSSDs compare favorably to modern 3DGM and auto3DGM while being more computationally efficient. By characterizing whole surfaces, our method incorporates more morphological detail in shape analysis. We can classify known biological groupings, such as Genus affiliation with comparable accuracy. The shape spaces produced by our method are similar to those produced by modern 3DGM and to auto3DGM, and distinctiveness functions derived from LSSDs show us how shape variation differs between groups. morphVQ can capture shape in an automated fashion while avoiding the limitations of manually digitized landmarks, and thus represents a novel and computationally efficient addition to the geometric morphometrics toolkit. Author summaryThe quantification of biological shape variation has relied on expert placement of relatively small subsets of landmarks and their analysis using tools of geometric morphometrics (GM). This paper introduces morphVQ, a novel, automated, learning-based approach to shape analysis that approximates the non-rigid correspondence between surface models of bone. With accurate functional correspondence between bones, we can characterize the shape variation within a dataset. Our results demonstrate that morphVQ performs similarly to manual digitization and to an existing automated phenotyping approach, auto3DGM. morphVQ has the advantages of greater computational efficiency and while capturing shape variation directly from surface model representations of bone. We can classify biological shapes to the Genus level with comparable accuracy to previous approaches, and we can demonstrate which aspects of bone shape differ most between groups. The ability to provide comparable accuracy in a Genus level classification with features extracted from morphVQ further guarantees the validity of this approach.

bioinformatics↗