器官引导轻量多帧整合网络用于腹部超声视频实时病变检测
本研究提出基于YOLOv11的OGLMFI框架,整合器官引导特征过滤与因果多帧融合,用于肝、胆囊、肾脏超声视频中病变统一检测。在205个临床视频测试集上,该框架Recall为0.691,mAP50为0.703,推理速度达52.3帧/秒,优于YOLOv11-L基线。
要点
- OGLMFI可同时检测肝、胆囊、肾脏三类器官的七类病变,适用于腹部超声常规筛查。
- 该框架仅利用历史帧进行因果推断,保持实时推理,速度为52.3帧/秒。
- 与YOLOv11-L基线相比,Recall提升10.7%,mAP50-95提升8.1%。
核心结论
- OGLMFI通过整合器官引导特征过滤和因果多帧特征融合,改善了腹部超声视频中的实时病变检测性能。
- 该框架为三个腹部器官的病变检测提供了统一的实用解决方案,可作为常规腹部超声筛查的计算机辅助工具。
研究设计与样本
- 研究类型为方法学研究,提出基于YOLOv11的器官引导轻量多帧整合(OGLMFI)框架。
- 测试集包含205个临床视频,共12964个标注帧,涉及肝脏、胆囊、肾脏三个器官。
- 框架包含器官引导特征过滤模块,利用器官分割先验抑制背景干扰并增强病变判别。
- 框架包含轻量多帧整合模块,采用双分支融合策略,仅利用历史帧信息进行时序整合以保持因果实时推断。
- 对比基线为YOLOv11-L,评价指标包括Recall、mAP50、mAP50-95及推理速度。
关键影像表现/征象
- 该框架支持对肝脏、胆囊、肾脏超声视频中的病变进行统一检测,不局限于单一器官或静态图像。
- 器官引导特征过滤模块利用器官分割先验来抑制超声图像中的背景干扰,增强病变区域的判别能力。
- 轻量多帧整合模块通过双分支融合策略利用连续帧的历史时序信息,仅依赖历史帧实现因果实时推断。
诊断标准与关键数值
- OGLMFI在测试集上Recall为0.691。
- OGLMFI在测试集上mAP50为0.703,mAP50-95为0.510。
- OGLMFI推理速度为52.3帧/秒。
- 与YOLOv11-L基线相比,Recall提升10.7%,mAP50提升3.2%,mAP50-95提升8.1%。
- 胆囊结石的平均精度(IoU阈值0.5)为66.8%,胆囊息肉为53.7%。
临床应用与阅片要点
- OGLMFI可作为腹部超声常规筛查的计算机辅助工具,为阅片医生提供多器官病变实时检测支持。
- 在低对比度、噪声及连续变化切面下,该框架有助于降低超声检查中对操作者经验的依赖。
局限性
- 原文未报告该框架在外部独立数据集上的泛化验证结果。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: Abdominal ultrasound is widely used for the routine screening of hepatobiliary and renal diseases because it is safe, inexpensive and broadly accessible. In daily clinical practice, however, lesion detection remains highly operator-dependent, particularly when sonographers must identify subtle abnormalities across different abdominal organs under low-contrast, noisy and continuously changing views. Missed or delayed recognition may affect subsequent diagnostic assessment and patient management. Although deep learning has shown promise in ultrasound analysis, most existing methods focus on single-organ or static-image settings, which limits their applicability to real-time abdominal screening. These challenges motivate the development of a unified real-time detection framework that can better support lesion identification in multi-organ ultrasound videos.
METHODS: We propose the Organ-Guided Lightweight Multi-frame Integration (OGLMFI) framework based on YOLOv11 for unified lesion detection across the liver, gallbladder and kidney in ultrasound videos. The framework incorporates an Organ-Guided Feature Filtering module that uses organ segmentation priors to suppress background interference and enhance lesion discrimination. It also includes a Lightweight Multi-frame Integration module, which adopts a dual-branch fusion strategy to efficiently integrate temporal information from consecutive frames using only historical context, thereby preserving causal real-time inference.
RESULTS: On the test set of 205 clinical videos (12,964 annotated frames), OGLMFI achieved a Recall of 0.691, a mean average precision at an intersection-over-union threshold of 0.5 (mAP50) of 0.703, an mAP50-95 of 0.510 and an inference speed of 52.3 frames per second. Compared with the YOLOv11-L baseline, OGLMFI improved Recall by 10.7%, mAP50 by 3.2% and mAP50-95 by 8.1%, while maintaining real-time performance. Among the evaluated methods, OGLMFI achieved the highest Recall, mAP50 and mAP50-95. Category-wise analysis further showed the highest average precision at an intersection-over-union threshold of 0.5 across all seven lesion categories, including 66.8% for gallbladder stone and 53.7% for gallbladder polyp.
CONCLUSION: By integrating organ-guided feature filtering and causal multi-frame feature fusion, OGLMFI improves real-time lesion detection in abdominal ultrasound videos. The proposed framework provides a practical unified solution for lesion detection across three abdominal organs and may serve as a useful computer-aided tool for routine abdominal ultrasound screening.
引用
- Wang, Zhu, Zou, et al. An Organ-Guided Lightweight Multi-frame Integration Network for Real-Time Abdominal Lesion Detection in Ultrasound Video Streams. Ultrasound Med Biol. 2026. PMID: 42570927. doi:10.1016/j.ultrasmedbio.2026.07.002
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。