Selected work

Representative Papers

Analysis of Motor Signatures of Social Adaptation in Autism for Efficient Human-Centric Systems

Aug 12, 2026

This study addresses the identification of social adaptation differences in individuals with autism spectrum disorder (ASD) through movement behavior characteristics, aiming to inform precision medicine and human-computer interaction design. Using 3D motion capture data collected during a dance imitation task, the research compares movement patterns between autistic and neurotypical adults in both solitary and social contexts. It introduces the Social Context Sensitivity Index (SCSI), which—by quantifying how motor variability is modulated by social framing—proposes a novel potential motor biomarker for ASD. Movement consistency is assessed via dynamic time warping, and machine learning models are employed for group classification. Results reveal that neurotypical participants exhibit significantly increased upper- and lower-limb motor variability in social settings, whereas ASD participants maintain stable variability. The classifier achieves a balanced accuracy of 79.2%.

0 citationsRead paper

Glioma C6: A Novel Dataset for Training and Benchmarking Cell Segmentation

Nov 10, 2025

High-quality annotated data for glioma C6 cell instance segmentation is scarce, hindering robust model development and evaluation. Method: We introduce C6Seg—the first open-source, biologist-curated instance segmentation dataset for C6 cells—comprising 75 phase-contrast microscopy images with over 12,000 pixel-accurate cell masks. C6Seg uniquely incorporates morphological classification labels and subcellular annotations (soma vs. pseudopodia), and spans controlled conditions and multi-condition imaging environments to enhance generalizability. Contribution/Results: Using C6Seg, we systematically benchmark state-of-the-art models (e.g., Mask R-CNN, U-Net), revealing performance bottlenecks in highly clustered and small-object scenarios. Transfer learning on C6Seg yields an 8.2% mAP improvement, validating its utility for model refinement and benchmark establishment. C6Seg thus provides a reproducible, high-fidelity resource for quantitative analysis of brain tumor cells.

0 citationsRead paper

Recent publications

Latest Papers

Analysis of Motor Signatures of Social Adaptation in Autism for Efficient Human-Centric Systems

Aug 12, 2026

This study addresses the identification of social adaptation differences in individuals with autism spectrum disorder (ASD) through movement behavior characteristics, aiming to inform precision medicine and human-computer interaction design. Using 3D motion capture data collected during a dance imitation task, the research compares movement patterns between autistic and neurotypical adults in both solitary and social contexts. It introduces the Social Context Sensitivity Index (SCSI), which—by quantifying how motor variability is modulated by social framing—proposes a novel potential motor biomarker for ASD. Movement consistency is assessed via dynamic time warping, and machine learning models are employed for group classification. Results reveal that neurotypical participants exhibit significantly increased upper- and lower-limb motor variability in social settings, whereas ASD participants maintain stable variability. The classifier achieves a balanced accuracy of 79.2%.

0 citationsRead paper

Glioma C6: A Novel Dataset for Training and Benchmarking Cell Segmentation

Nov 10, 2025

High-quality annotated data for glioma C6 cell instance segmentation is scarce, hindering robust model development and evaluation. Method: We introduce C6Seg—the first open-source, biologist-curated instance segmentation dataset for C6 cells—comprising 75 phase-contrast microscopy images with over 12,000 pixel-accurate cell masks. C6Seg uniquely incorporates morphological classification labels and subcellular annotations (soma vs. pseudopodia), and spans controlled conditions and multi-condition imaging environments to enhance generalizability. Contribution/Results: Using C6Seg, we systematically benchmark state-of-the-art models (e.g., Mask R-CNN, U-Net), revealing performance bottlenecks in highly clustered and small-object scenarios. Transfer learning on C6Seg yields an 8.2% mAP improvement, validating its utility for model refinement and benchmark establishment. C6Seg thus provides a reproducible, high-fidelity resource for quantitative analysis of brain tumor cells.

0 citationsRead paper