发表机构
VinUniversity; Vietnam National University Ho Chi Minh City; University of Science（VinUniversity; 胡志明市国家大学; 科学大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低资源牙科记录补全难题，提出实体约束CBCT引导检索框架，其在MMDental任务3验证集与测试集上均优于基线方法，获测试阶段第二名，证实控制多模态证据修改范围比传输完整记录更可靠。
AI 中文摘要
当标注稀缺且不同临床字段由不同类型证据支撑时，从锥形束计算机断层扫描（CBCT）补全牙科记录颇具难度。MMDental任务3要求仅用50个标注CBCT病例完成七字段记录补全，并对结构化FDI（国际牙科联盟）位置与ICD（国际疾病分类）代码的正确性评分；因此，视觉上合理的检索记录若引入未被支撑的实体，仍可能造成危害。我们提出实体约束CBCT引导检索（ECCR），这是一种无参数框架，它将证据可用性与证据权威性分离：首先由语料库衍生的先验提供完整记录，冻结的3D编码器检索图像条件化诊断证据，仅当该证据不扩展先验的FDI或ICD实体集时才会被附加，从而使断言的实体集在构造上保持不变。在公共验证集上，ECCR达到0.3134的加权分数，优于全记录多模态检索（0.2237）和仅静态文本先验（0.2915）；该保护机制拦截了63.3%的检索候选，若不拦截，每个候选都会注入先验中不存在的FDI位置或ICD代码。在最终测试评估中，ECCR在97.4分的可达到最高分中获得11.37分，总体排名第二。该结果表明，在极端低资源场景下，控制多模态证据被允许修改的内容，比传输整个检索记录更可靠。
英文摘要
Completing dental records from cone-beam computed tomography (CBCT) is difficult when annotation is scarce and individual clinical fields are supported by different types of evidence. MMDental Task 3 requires seven-field record completion from only 50 labeled CBCT cases and scores the correctness of structured FDI positions and ICD codes; consequently, a visually plausible retrieved record can still be harmful when it introduces an unsupported entity. We propose Entity-Constrained CBCT-Guided Retrieval (ECCR), a parameter-free framework that separates evidence availability from evidence authority. A corpus-derived prior first supplies the complete record. A frozen 3D encoder retrieves image-conditioned Diagnosis evidence, which is appended only if it does not expand the prior FDI or ICD entity set, so the asserted entity set is invariant by construction. On public validation, ECCR reaches a weighted score of 0.3134, improving on both full-record multimodal retrieval (0.2237) and a static text-only prior (0.2915); the guard blocks 63.3% of retrieved candidates, each of which would otherwise have injected an FDI position or ICD code absent from the prior. On the final test evaluation, ECCR obtains 11.37 of a 97.4-point attainable maximum, securing second place overall. The result indicates that, in an extreme low-resource setting, controlling what multimodal evidence is allowed to modify can be more reliable than transferring an entire retrieved record.
CommentsAccepted at the ODIN 2026 Workshop, MICCAI 2026
