用于DeepLesion检测、分割及简短报告生成的统一二维框架
A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation
浏览论文内容
中文总结 AI 辅助
本研究开发了一个整合LLM推理、病变检测、分割及报告生成的统一二维框架，在DeepLesion数据集上取得了各项指标提升，解决了其分割难题并开源了相关资源。
中文摘要 AI 辅助
在过往工作中，我们基于ULS23 DeepLesion数据集，结合报告中的简短发现，将大语言模型（LLMs）整合入病变分割模型。本研究中，我们开发了一个统一的二维病变分析框架，整合了基于LLM的推理、病变边界框检测、分割以及从原始DeepLesion数据集生成放射学报告。测试阶段，我们取得了较高的病变边界框检测准确率，mAP50为70.1%，mAP50-95为46.4%；病变分割性能的Dice分数为62.6%；简短报告生成准确率的BLEU_1分数为64.3%，BLEU_4分数为49.6%，METEOR为34.7%，ROUGE_L为60.1%。本研究解决了原始DeepLesion数据集中极具挑战性的分割问题，相较于nnUNet病变分割模型，实现了28.5%的Dice分数提升。我们还将空间和解剖学上下文整合入DeepLesion简短报告生成中，并在Github上发布了实现代码、数据集及模型。
英文摘要
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
