整合检测、分割与报告生成的统一框架，提升肺结节分析效率。
A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation
- 基于2D图像构建端到端框架，融合大模型推理与医学图像分析
- 检测mAP50达70.1%，分割Dice提升至62.6%，报告生成指标全面领先
- 首次在原始DeepLesion数据上实现多任务统一建模，适合临床辅助诊断
此前工作将大语言模型（LLMs）集成到基于ULS23 DeepLesion数据集的病灶分割模型中，利用报告中的简要发现。本研究开发了一个统一的2D病灶分析框架，整合了基于大模型的推理、病灶边界框检测、分割以及从原始DeepLesion数据集生成放射科报告。测试阶段，病灶边界框检测的mAP50为70.1%，mAP50-95为46.4%；病灶分割的Dice分数为62.6%；短报告生成的BLEU_1为64.3%，BLEU_4为49.6%，METEOR为34.7%，ROUGE_L为60.1%。本研究解决了原始DeepLesion数据集中的分割难题，相比nnUNet模型，Dice分数提升了28.5%。同时，将空间与解剖上下文引入短报告生成。代码、数据集和模型已开源于GitHub。
原文摘要 · Abstract (English)
In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using short-form findings from the reports. In this study, we developed a unified 2D lesion analysis framework that integrates LLM-based reasoning, lesion bounding box detection, segmentation, and radiology report generation from the original DeepLesion dataset. In the testing phase, we achieved relatively high lesion bounding box detection accuracy with mAP50 of 70.1%, mAP50-95 of 46.4%; Lesion segmentation performance with a Dice score of 62.6%; short report generation accuracy with BLEU_1 score of 64.3%, BLEU_4 score of 49.6%, METEOR of 34.7%, and ROUGE_L of 60.1%. In this work, we address the challenging issue of segmentation in the original DeepLesion dataset and achieve a 28.5% Dice score improvement over the nnUNet lesion segmentation model. We also integrated spatial and anatomical context into the DeepLesion short report generation. We released the implementation, dataset, and models on Github. https://github.com/ruida/2D_DeepLesion_Foundation
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。