bioRxiv Science⌕ Search

Biology subjects

Mulqueeney, J. M.

Publications and source records attributed to Mulqueeney, J. M..

3 recordsLinked to original sources

Introducing SPROUT (Semi-automated Parcellation of Region Outputs Using Thresholding): an adaptable computer vision tool to generate 3D segmentations

The segmentation of fine-grained and complex structures from volumetric data, such as 3D biomedical images, is a manually intensive process, with performance hindered by limited training data and the difficulty of adapting AI models for specialised datasets. Here, we introduce SPROUT, a user-friendly and interpretable segmentation framework that leverages domain-specific priors, enabling experts to translate their knowledge into reproducible, high-quality segmentations across diverse imaging modalities without the need for training data. Its adaptive design facilitates parameter transferability and improves generalisation across similar datasets. Implemented as scripts and a napari plugin, it supports interactive editing and scalable batch processing, lowering the technical barrier for domain experts. We applied SPROUT to datasets spanning different imaging modalities, anatomical complexities, postures, and target structures, producing high-quality segmentations across 2D and 3D tasks. Quantitative comparisons with other methods on a representative dataset showed SPROUT achieved results comparable to expert-corrected interpolation while requiring substantially less manual input. In scenarios where SPROUT achieved high-quality results, supervised models often struggled to reach similar accuracy, highlighting the challenge of deep learning methods in complex domains. We also explored integration with foundation models to accelerate segmentation in high-contrast datasets, illustrating potential for hybrid workflows.

evolutionary biology↗

Assessing the application of landmark-free morphometrics to macroevolutionary analyses

The study of phenotypic evolution has been transformed by methods allowing three-dimensional quantification of anatomical form. The present state-of-the-art 3D geometric morphometrics, which relies heavily on manual landmarking, is time-consuming, prone to operator bias, and cannot effectively compare disparate shapes. Emerging automated approaches, notably landmark-free techniques, offer promise but have only been applied to closely related species. Here, we compare landmark-free approaches with high-density geometric morphometric methods on 322 mammals across 180 families. Leveraging the benefits of Poisson meshes, which combine open and closed projections, we show how landmark-free methods have greater power to differentiate major taxonomic groups. Although there is coarse correspondence in shape variation between the two methods, the finer features of the landmark-free approach likely reflect its broader sampling of the surface structure. Our study underscores the robustness of landmark-free methods for large-scale comparative analysis and helps propel morphometrics into a new era of bigger data.

evolutionary biology↗

How many specimens make a sufficient training set for automated 3D feature extraction?

Deep learning has emerged as a robust tool for automating feature extraction from 3D images, offering an efficient alternative to labour-intensive and potentially biased manual image segmentation methods. However, there has been limited exploration into the optimal training set sizes, including assessing whether artificial expansion by data augmentation can achieve consistent results in less time and how consistent these benefits are across different types of traits. In this study, we manually segmented 50 planktonic foraminifera specimens from the genus Menardella to determine the minimum number of training images required to produce accurate volumetric and shape data from internal and external structures. The results reveal unsurprisingly that deep learning models improve with a larger number of training images and that data augmentation can enhance network accuracy by up to 8.0%. Notably, predicting both volumetric and shape measurements for the internal structure poses a greater challenge compared to the external structure, due to low contrast between different materials and increased geometric complexity. These results provide novel insight into optimal training set sizes for precise image segmentation of diverse traits and highlight the potential of data augmentation for enhancing multivariate feature extraction from 3D images. Subject CategoryLife Sciences - Computer Science Subject Areascomputational biology, Artificial Intelligence

evolutionary biology↗