Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with a Structured Output (SLSO) Framework.
诸如GPT（生成式预训练Transformer）等视觉语言模型（VLMs）在医学图像解读方面已展现出潜力；然而，在临床实践中生成可靠的放射学所见仍面临挑战，牙科病变即为典型例证。本研究提出一种结构化输出自校正循环（SLSO）框架，作为一种集成处理方法，以提高AI生成的颌骨囊肿牙科全景放射影像所见的准确性和可靠性。研究使用伴有颌骨囊肿的牙科全景放射影像，实施了一套包含图像分析、结构化数据生成、牙位编号提取、一致性检查和迭代再生成的10步集成处理框架。该框架作为GPT输出的外部验证机制发挥作用。研究将性能与传统的思维链（CoT）方法在七个评估项目上进行了比较：透明度、内部结构、边界、牙根吸收、牙齿移位、与其他结构的关系以及牙位编号。与CoT方法相比，SLSO框架在多个项目上提高了输出准确性，其中最显著的改善见于牙位编号识别、牙齿移位检测和牙根吸收评估。在成功案例中，经过最多五次再生成后获得了结构一致的输出。该框架强制进行明确的阴性所见描述并抑制了幻觉，尽管对跨越多个牙齿的广泛病变的准确识别仍然有限。本研究证实了所提出的集成处理方法的可行性，并为未来使用更大、更多样化数据集开展验证研究奠定了基础。
Vision-language models (VLMs) such as GPT (Generative Pre-Trained Transformer) have shown potential for medical image interpretation; however, challenges remain in generating reliable radiological findings in clinical practice, as exemplified by dental pathologies. This study proposes a Self-correction Loop with Structured Output (SLSO) framework as an integrated processing methodology to enhance the accuracy and reliability of AI-generated findings for jaw cysts in dental panoramic radiographs. Dental panoramic radiographs with jaw cysts were used to implement a 10-step integrated processing framework incorporating image analysis, structured data generation, tooth number extraction, consistency checking, and iterative regeneration. The framework functioned as an external validation mechanism for GPT outputs. Performance was compared against the conventional Chain-of-Thought (CoT) method across seven evaluation items: transparency, internal structure, borders, root resorption, tooth displacement, relationships with other structures, and tooth number. The SLSO framework improved output accuracy for multiple items compared to the CoT method, with the most notable improvements observed in tooth number identification, tooth displacement detection, and root resorption assessment. In successful cases, consistently structured outputs were achieved after up to five regenerations. The framework enforced explicit negative finding descriptions and suppressed hallucinations, although accurate identification of extensive lesions spanning multiple teeth remained limited. This investigation established the feasibility of the proposed integrated processing methodology and provided a foundation for future validation studies with larger, more diverse datasets.
Nanaka Hosokawa, Ryo Takahashi, Tomoya Kitano, Yukihiro Iida, Chisako Muramatsu, Tatsuro Hayashi, et al. Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with a Structured Output (SLSO) Framework.. Diagnostics (Basel, Switzerland). 2026; doi:10.3390/diagnostics16071096.
Nanaka Hosokawa, Ryo Takahashi, Tomoya Kitano, Yukihiro Iida, Chisako Muramatsu, Tatsuro Hayashi, et al (2026). Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with a Structured Output (SLSO) Framework.. Diagnostics (Basel, Switzerland). https://doi.org/10.3390/diagnostics16071096
Nanaka Hosokawa, Ryo Takahashi, Tomoya Kitano, Yukihiro Iida, Chisako Muramatsu, Tatsuro Hayashi, et al. Generating Findings for Jaw Cysts in Dental Panoramic Radiographs Using a GPT-Based VLM: A Preliminary Study on Building a Two-Stage Self-Correction Loop with a Structured Output (SLSO) Framework.[J]. Diagnostics (Basel, Switzerland), 2026 doi:10.3390/diagnostics16071096.
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出