Zero-shot large vision-language model prompting for automated bone identification in paleoradiology x-ray archives

TL;DR

This paper demonstrates a zero-shot vision-language model approach to automatically identify bones, projection views, and laterality in heterogeneous paleoradiology X-ray images, significantly aiding content navigation and analysis.

Contribution

The study introduces a novel zero-shot prompting pipeline using a large vision-language model for automated bone and view identification in complex archaeological radiographs.

Findings

Achieved 92% accuracy in main bone identification

Attained 80% accuracy in projection view detection

Reached 100% accuracy in laterality recognition

Abstract

Paleoradiology, the use of modern imaging technologies to study archaeological and anthropological remains, offers new windows on millennial scale patterns of human health. Unfortunately, the radiographs collected during field campaigns are heterogeneous: bones are disarticulated, positioning is ad hoc, and laterality markers are often absent. Additionally, factors such as age at death, age of bone, sex, and imaging equipment introduce high variability. Thus, content navigation, such as identifying a subset of images with a specific projection view, can be time consuming and difficult, making efficient triaging a bottleneck for expert analysis. We report a zero shot prompting strategy that leverages a state of the art Large Vision Language Model (LVLM) to automatically identify the main bone, projection view, and laterality in such images. Our pipeline converts raw DICOM files to bone windowed PNGs, submits them to the LVLM with a carefully engineered prompt, and receives structured JSON outputs, which are extracted and formatted onto a spreadsheet in preparation for validation. On a random sample of 100 images reviewed by an expert board certified paleoradiologist, the system achieved 92% main bone accuracy, 80% projection view accuracy, and 100% laterality accuracy, with low or medium confidence flags for ambiguous cases. These results suggest that LVLMs can substantially accelerate code word development for large paleoradiology datasets, allowing for efficient content navigation in future anthropology workflows.