[论文解读] YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection

Chun‐Tse Chien, Rui‐Yang Ju+3 more|arXiv (Cornell University)|Feb 14, 2024

Bone fractures and treatments被引用 10

一句话总结

引入 YOLOv8-AM，在 YOLOv8 中整合四个注意力模块用于儿科腕部骨折检测，在 GRAZPEDWRI-DX 上达到最先进的 mAP50。

ABSTRACT

Wrist trauma and even fractures occur frequently in daily life, particularly among children who account for a significant proportion of fracture cases. Before performing surgery, surgeons often request patients to undergo X-ray imaging first and prepare for it based on the analysis of the radiologist. With the development of neural networks, You Only Look Once (YOLO) series models have been widely used in fracture detection as computer-assisted diagnosis (CAD). In 2023, Ultralytics presented the latest version of the YOLO models, which has been employed for detecting fractures across various parts of the body. Attention mechanism is one of the hottest methods to improve the model performance. This research work proposes YOLOv8-AM, which incorporates the attention mechanism into the original YOLOv8 architecture. Specifically, we respectively employ four attention modules, Convolutional Block Attention Module (CBAM), Global Attention Mechanism (GAM), Efficient Channel Attention (ECA), and Shuffle Attention (SA), to design the improved models and train them on GRAZPEDWRI-DX dataset. Experimental results demonstrate that the mean Average Precision at IoU 50 (mAP 50) of the YOLOv8-AM model based on ResBlock + CBAM (ResCBAM) increased from 63.6% to 65.8%, which achieves the state-of-the-art (SOTA) performance. Conversely, YOLOv8-AM model incorporating GAM obtains the mAP 50 value of 64.2%, which is not a satisfactory enhancement. Therefore, we combine ResBlock and GAM, introducing ResGAM to design another new YOLOv8-AM model, whose mAP 50 value is increased to 65.0%. The implementation code for this study is available on GitHub at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.

研究动机与目标

• 通过使用注意力增强的 YOLOv8 来提升儿科腕部 X 光片的骨折检测效果。
• 研究不同注意力机制对检测性能的影响。
• 确定该任务的高性能注意力模块组合。
• 提供可实现的模型和用于在 GRAZPEDWRI-DX 数据集上复现实验的开源代码。

提出的方法

• 将四个注意力模块（CBAM、GAM、ECA、SA）整合到 YOLOv8 架构中以创建增强模型。
• 尝试使用 ResBlock 的变体来形成 ResCBAM 和 ResGAM 模型。
• 在 GRAZPEDWRI-DX 儿科腕部数据集上进行训练和评估，以测量 mAP@50。
• 比较注意力模块及其组合，以确定最佳性能的配置。
• 在 GitHub 上提供实现代码以确保可复现性。

实验结果

研究问题

• RQ1 在 YOLOv8 中加入注意力机制是否能提升儿科腕部 X 光片的骨折检测性能？
• RQ2 哪种注意力模块或组合在 GRAZPEDWRI-DX 上能得到最佳的 mAP@50？
• RQ3 基于 ResBlock 的设计在该任务中如何与 YOLOv8 的注意力模块相互作用？
• RQ4 所提出的最佳模型是否在该数据集上实现了最先进的结果？

主要发现

• YOLOv8-AM 与 ResBlock + CBAM（ResCBAM）实现 mAP50 为 65.8%（从 63.6% 提升）。
• 仅使用 GAM 的 YOLOv8-AM 实现 mAP50 为 64.2%。
• 组合的 ResGAM 设计将 mAP50 提升至 65.0%。
• 表现最佳的配置（ResCBAM）在该任务的数据集上达到最先进的性能。
• 用于模型和实验的代码已在 GitHub 上发布，以实现可重复性。