The introduction of YOLOv9, the latest version of the you only look once (YOLO) series, has led to its widespread adoption across various scenarios. This paper is the first to apply the YOLOv9 algorithm model to the fracture detection task as computer‐assisted diagnosis to help radiologists and surgeons to interpret X‐ray images. Specifically, this paper trained the model on the GRAZPEDWRI‐DX dataset and extended the training set using data augmentation techniques to improve the model performance. Experimental results demonstrate that compared to the mAP 50–95 of the current state‐of‐the‐art model, the YOLOv9 model increased the value from 42.16% to 43.73%, with an improvement of 3.7%. The implementation code is publicly available at https://github.com/RuiyangJu/YOLOv9‐Fracture‐Detection .
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 surgery based on the analysis of the radiologists. 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) tools. Ultralytics presented the latest version of the YOLO models in 2023, which has been employed for detecting fractures across various parts of the body. Attention mechanism is one of the most popular methods to improve the model performance. This work proposes YOLOv8-AM, which incorporates the attention modules into the YOLOv8 architecture. Specifically, we respectively employ four different attention modules, ResBlock with Convolutional Block Attention Module (ResCBAM), Shuffle Attention (SA), Efficient Channel Attention (ECA), and ResBlock with Global Attention Mechanism (ResGAM), to improve the model architecture, and train these models on the GRAZPEDWRI-DX dataset. Experimental results demonstrate that the mean Average Precision at IoU 50 (mAP@50) of one of the variants of YOLOv8-AM model (i.e., YOLOv8+ResCBAM) increased from 63.6% to 65.8%, which achieves the state-of-the-art (SOTA) performance. In addition, the proposed YOLOv8-AM models can detect the single-label category “fracture” with mAP@50 value of 95.7% in pediatric wrist trauma X-ray images. The implementation code for this work is available on GitHub at https://github.com/RuiyangJu/Fracture_Detection_Improved_YOLOv8.
18 February 2023 in Journal of Real-Time Image Processing
With the continuous development of neural networks for computer vision tasks, more and more network architectures have achieved outstanding success. As one of the most advanced neural network architectures, DenseNet shortcuts all feature maps to solve the model depth problem. Although this network architecture has excellent accuracy with low parameters, it requires an excessive inference time. To solve this problem, HarDNet reduces the connections between the feature maps, making the remaining connections resemble harmonic waves. However, this compression method may result in a decrease in the model accuracy and an increase in the parameters and model size. This network architecture may reduce the memory access time, but its overall performance can still be improved. Therefore, we propose a new network architecture, ThreshNet, using a threshold mechanism to further optimize the connection method. Different numbers of connections for different convolution layers are discarded to accelerate the inference of the network. The proposed network has been evaluated with image classification using CIFAR 10 and SVHN datasets under platforms of NVIDIA RTX 3050 and Raspberry Pi 4. The experimental results show that, compared with HarDNet68, GhostNet, MobileNetV2, ShuffleNet, and EfficientNet, the inference time of the proposed ThreshNet79 is 5%, 9%, 10%, 18%, and 20% faster, respectively. The number of parameters of ThreshNet95 is 55% less than that of HarDNet85. The new model compression and model acceleration methods can speed up the inference time, enabling network models to operate on mobile devices.