Bridging the Skill Gap in Clinical CBCT Interpretation with CBCTRepD

2026-03-11

AI Summary

This study addresses the challenges in oral and maxillofacial cone-beam computed tomography (CBCT) report generation, which are primarily constrained by the scarcity of high-quality paired data and the complexity of interpreting three-dimensional images. To overcome these limitations, the authors propose CBCTRepD, a bilingual CBCT reporting system built upon 7,408 high-quality CBCT–report pairs covering 55 distinct pathologies. The system introduces a clinically oriented, multi-level human–AI collaborative workflow, integrating generative artificial intelligence with large-scale medical image–text training. A comprehensive clinical evaluation framework combining automated metrics and radiologist assessments demonstrates that CBCTRepD generates draft reports comparable in quality to those produced by mid-level radiologists. Moreover, when integrated into clinical practice, the system significantly enhances diagnostic performance across all experience levels, reduces omissions, and improves detection of coexisting lesions.

Technology Category

• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Generative AI has advanced rapidly in medical report generation; however, its application to oral and maxillofacial CBCT reporting remains limited, largely because of the scarcity of high-quality paired CBCT-report data and the intrinsic complexity of volumetric CBCT interpretation. To address this, we introduce CBCTRepD, a bilingual oral and maxillofacial CBCT report-generation system designed for integration into routine radiologist-AI co-authoring workflows. We curated a large-scale, high-quality paired CBCT-report dataset comprising approximately 7,408 studies, covering 55 oral disease entities across diverse acquisition settings, and used it to develop the system. We further established a clinically grounded, multi-level evaluation framework that assesses both direct AI-generated drafts and radiologist-edited collaboration reports using automatic metrics together with radiologist- and clinician-centered evaluation. Using this framework, we show that CBCTRepD achieves superior report-generation performance and produces drafts with writing quality and standardization comparable to those of intermediate radiologists. More importantly, in radiologist-AI collaboration, CBCTRepD provides consistent and clinically meaningful benefits across experience levels: it helps novice radiologists improve toward intermediate-level reporting, enables intermediate radiologists to approach senior-level performance, and even assists senior radiologists by reducing omission-related errors, including clinically important missed lesions. By improving report structure, reducing omissions, and promoting attention to co-existing lesions across anatomical regions, CBCTRepD shows strong and reliable potential as a practical assistant for real-world CBCT reporting across multi-level care settings.

Problem

• CBCT interpretation
• skill gap
• medical report generation
• oral and maxillofacial radiology
• AI-assisted diagnosis

Innovation

• CBCT report generation
• generative AI
• radiologist-AI collaboration
• clinical evaluation framework
• paired medical imaging dataset