Gianluca Tozzi

BoneGraph combines a SPECTER2-indexed bone corpus, knowledge graph, deterministic physics checks, and user-taught rules in a local five-tab system; oracle passages raise accuracy 42% to 78%.

This paper introduces BoNeRF-HS, a self-calibrated hyperspectral neural radiance field for 3D reconstruction of bone and bone analogues, achieving better reconstruction quality and surface detail preservation.

This paper compares dimensionality reduction strategies for quantum kernel SVMs on synthetic micro-CT trabecular bone data, finding UMAP maintains competitiveness while linear methods show quantum deficits.

The paper evaluates a direct strain prediction method for bone using XCT images, showing improved accuracy and reduced noise compared to displacement-derived strain.

This paper examines how the mechanical behavior of biomimetic porous scaffolds changes with strain by analyzing evolving morphology and stress-strain relationships.

This study develops biomimetic nanofibrous scaffolds with auxetic properties for enthesis regeneration, showing their mechanical behavior matches natural tendon fascicles.

This paper uses hyperspectral imaging to analyze banana peels as a surrogate model for detecting skin changes, demonstrating its potential for dermatology applications.