FT-ARM:面向压疮严重程度分类的带推理的微调智能体反射多模态语言模型
FT-ARM: Fine-Tuned Agentic Reflection Multimodal Language Model for Pressure Ulcer Severity Classification with Reasoning
AI总结:
针对压疮分期准确率低、可解释性不足的问题,提出带智能体自反射机制的微调多模态模型FT-ARM,在PIID数据集上达85%准确率,支持实时推理与临床解释,提升伤口评估的可靠性与临床适用性。
摘要:
压疮(Pressure ulcers, PUs)是一种严重且普遍的医疗健康问题。准确分类压疮严重程度(I-IV期)对恰当治疗至关重要,但由于视觉差异细微、解读存在主观性,该任务仍具挑战性,会导致临床医生之间的判断存在差异。此前基于卷积神经网络(Convolutional Neural Networks, CNNs)和视觉Transformer(Vision Transformers, ViTs)的AI方法取得了不错的准确率,但可解释性有限。\n我们提出FT-ARM(Fine-Tuned Agentic Reflection Multimodal model,微调智能体反射多模态模型),这是一种带智能体自反射机制的微调多模态大语言模型(multimodal large language model, MLLM),用于压疮严重程度分类。受临床医生式诊断复评思路启发,FT-ARM通过对视觉特征和文本编码的临床知识进行推理,迭代优化预测结果,同时提升了准确率和一致性。\n在公开可用的Pressure Injury Image Dataset(PIID,压疮损伤图像数据集)上,基于LLaMA 3.2 90B微调的FT-ARM在I-IV期压疮分类任务中达到85%的准确率,较此前基于CNN的模型高出4个百分点。与早期仅依赖离线评估的CNN/ViT研究不同,FT-ARM针对实时推理进行设计和测试,贴合实际部署场景。此外,它能生成有临床依据的自然语言解释,提升了可解释性和可信度。通过在多模态输入中整合微调与反射推理,FT-ARM提升了自动化伤口评估系统的可靠性、透明度和临床适用性,满足了对一致且可解释的压疮分期的关键需求,以助力改善患者护理。
英文摘要:
Pressure ulcers (PUs) are a serious and prevalent healthcare concern. Accurate classification of PU severity (Stages I-IV) is essential for proper treatment but remains challenging due to subtle visual distinctions and subjective interpretation, leading to variability among clinicians. Prior AI-based approaches using Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) achieved promising accuracy but offered limited interpretability. We present FT-ARM (Fine-Tuned Agentic Reflection Multimodal model), a fine-tuned multimodal large language model (MLLM) with an agentic self-reflection mechanism for pressure ulcer severity classification. Inspired by clinician-style diagnostic reassessment, FT-ARM iteratively refines its predictions by reasoning over visual features and encoded clinical knowledge from text, enhancing both accuracy and consistency. On the publicly available Pressure Injury Image Dataset (PIID), FT-ARM, fine-tuned from LLaMA 3.2 90B, achieved 85% accuracy in classifying PU stages I-IV, surpassing prior CNN-based models by +4%. Unlike earlier CNN/ViT studies that relied solely on offline evaluations, FT-ARM is designed and tested for live inference, reflecting real-time deployment conditions. Furthermore, it produces clinically grounded natural-language explanations, improving interpretability and trust. By integrating fine-tuning and reflective reasoning across multimodal inputs, FT-ARM advances the reliability, transparency, and clinical applicability of automated wound assessment systems, addressing the critical need for consistent and explainable PU staging to support improved patient care.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。