Large vision model framework for automated C. elegans analysis: From static morphometry to dynamic neural activity

Quantitative phenotyping of Caenorhabditis elegans is essential across numerous fields, yet data extraction remains a significant analytical bottleneck. Traditional segmentation methods, typically reliant on pixel-intensity thresholding, are highly sensitive to variations in imaging conditions and often fail in the presence of noise, overlaps, or uneven illumination. These failures necessitate meticulous experimental setups, expensive hardware, or extensive manual curation, which reduces throughput and introduces bias. Here, we introduce TWARDIS (Tools for Worm Automated Recognition & Dynamic Imaging System), a modular, Python-based analysis suite that leverages large foundation vision models, specifically the Segment Anything Models (SAM and SAM2) and a fine-tuned vision transformer classifier, to overcome these limitations. We demonstrate the versatility and robustness of our AI compound system across diverse modalities. For static morphological analysis, TWARDIS successfully resolved overlapping worms in noisy images without human intervention, showing a 0.999 correlation with manual segmentation. In behavioral assays (swimming and crawling), the pipeline enabled high-definition postural analysis even in low-resolution, wide-field recordings where the worm occupied only [~]0.25% of the field of view, accurately resolving complex postures without frame rejection. Finally, when applied to calcium imaging of semi-restricted animals, TWARDIS provided precise, frame-by-frame segmentation of neural compartments, reducing the artificial signal flattening common in traditional region-of-interest-based approaches and enabling the extraction of biologically accurate, absolute head positions. The systems hardware-scalable architecture and modular design ensure both current accessibility and future improvements without restructuring. By automating the most time-consuming aspects of image analysis, TWARDIS removes critical bottlenecks and tradeoffs in C. elegans research, enabling researchers to focus on biological questions rather than technical image processing challenges. Author SummaryThe small roundworm Caenorhabditis elegans is widely used by scientists to study fundamental biological questions, such as aging and how the brain works. A crucial part of this research involves analyzing images and videos to measure the worms shape, movement, and neural activity. However, extracting accurate data is a major challenge. Traditional software tools often fail if the lighting is uneven, the image is noisy, or worms overlap. This forces researchers to spend countless hours manually correcting errors or investing in expensive, specialized equipment. To overcome this bottleneck, we developed TWARDIS (Tools for Worm Automated Recognition & Dynamic Imaging System). Our system utilizes recent advances in Artificial Intelligence, harnessing powerful, generalized AI models to automatically and accurately identify the worms, even in challenging images. We demonstrated that TWARDIS reliably analyzes complex behaviors and neural activity without human intervention. Our approach removes the traditional trade-off between data quality and equipment cost, enabling high-precision analysis using simple setups. By automating the most tedious parts of image analysis, TWARDIS allows scientists to focus on biological discovery rather than technical hurdles.