0% found this document useful (0 votes)
13 views4 pages

6.Bone_Fracture_Detection_Based_on_Faster_R-CNN_with_Bi-Directional_Feature_Pyramid_Module

Uploaded by

Piyush Verma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
13 views4 pages

6.Bone_Fracture_Detection_Based_on_Faster_R-CNN_with_Bi-Directional_Feature_Pyramid_Module

Uploaded by

Piyush Verma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

2024 7th International Conference on Artificial Intelligence and Big Data

Bone Fracture Detection Based on Faster R-CNN


with Bi-directional Feature Pyramid Module
Wenlong Wu Yang Qian Zhihao Su *
Computer Science College, La Consolacion University Philippines, Corresponding author
Guangzhou College of Applied Science City of Malolos, Bulacan Computer Science College,
and Technology, Graduate Studies Department Guangzhou College of Applied Science
2024 7th International Conference on Artificial Intelligence and Big Data (ICAIBD) | 979-8-3503-8510-6/24/$31.00 ©2024 IEEE | DOI: 10.1109/ICAIBD62003.2024.10604621

Guangzhou, China Philippines and Technology,


[email protected] [email protected] Guangzhou, China
[email protected]
*Corresponding author

Abstract—With the widespread application of deep learning In medical image analysis, especially fracture detection,
technology in the field of medical image processing, research on traditional machine learning methods such as support vector
using convolutional neural networks for fracture detection has machines (SVM) and random forests are recognized for their
gradually increased. This paper proposes a Faster R-CNN low computational complexity and reasonable performance on
network based on a bidirectional feature transfer mechanism (Bi- small-scale data sets, but they suffer from automatic features
FPM), aiming to improve the accuracy of fracture detection. The shortcomings in extracting and processing high-
Through experimental comparison on the Kaggle Bone fracture dimensional data are obvious compared with deep learning
dataset, this study explores the performance of different feature methods [3]. Deep learning methods, especially convolutional
pyramid structures in the Faster R-CNN framework. Using
neural networks (CNN) and their derived structures such as U-
ResNext-101 as the backbone, the proposed Bi-FPM method
improves the accuracy by 5.8% in the fracture detection task
Net, AlexNet, VGG, and ResNet, stand out for their powerful
compared to the baseline Faster R-CNN, and is higher than the feature learning capabilities and high accuracy on large data sets.
traditional Feature Pyramid Network (FPN) Out 4.1%. Although these models Usually require a large amount of
Experimental results show that Bi-FPM's bidirectional feature annotated data and high computing resources [4]. Region
transfer mechanism can effectively integrate deep and shallow proposal networks such as Faster R-CNN perform well at
features, improve the model's ability to identify fracture features locating key regions in images but can have difficulty processing
and achieve better performance in fracture detection tasks. dense or small objects and are not real-time enough. Feature
Through testing on the Kaggle Bone fracture dataset containing Pyramid Network (FPN) and its variants effectively capture
350 test samples and 150 training samples, this paper confirms the multi-scale features by combining different levels of semantic
effectiveness and superiority of the proposed method. (Abstract) and detailed information. Although the model structure may be
more complex, it shows advantages in the detection of targets of
Keywords—Deep learning; bone fracture detection; feature different sizes. Therefore, when selecting an applicable
pyramid; detection algorithm algorithm, researchers must comprehensively consider the
application scenario, data volume, computing resources, and
I. INTRODUCTION
performance requirements, as well as the algorithm's ability to
In the field of medical imaging, accurately detecting and provide interpretable medical diagnostic results [5].
diagnosing fractures is critical to patient treatment and recovery.
In recent years, the application of deep learning technology in In our study, we adopt a novel bidirectional feature transfer
medical image analysis has made significant progress, among method to enhance feature extraction through a forward feature
which region-based convolutional neural network (R-CNN) and transfer pyramid and a backward feature transfer pyramid. The
its variants, such as Faster R-CNN, have become the mainstream forward feature transfer pyramid transfers detailed information
method for target detection tasks [1]. one. However, when in layer-by-layer decreasing feature maps through down-
processing medical images with complex textures and different sampling and element-wise addition operations, while the
sizes, especially in the fine-grained task of fracture detection, the backward feature transfer pyramid transfers contextual
performance of traditional Faster R-CNN is often limited by the information in layer-by-layer increasing feature maps through
effectiveness of feature extraction and the generalization ability upsampling. The combination of these two feature maps
of the model. In addition, although the existing feature pyramid provides Faster R-CNN with rich feature representation to
network (FPN) can extract multi-scale features, there is still improve the accuracy of fracture detection. Finally, non-
room for improvement in feature fusion and information transfer. maximum suppression technology is used to optimize the
To solve these problems, this study proposes a Faster R-CNN detected candidate areas to ensure high accuracy and efficiency
model based on two-way feature transfer, aiming to improve the of detection results [6].
accuracy of fracture detection through a more efficient feature We selected the Kaggle Bone Fracture data set as the
fusion mechanism [2]. research object. This data set contains 150 training samples and

979-8-3503-8510-6/24/$31.00 ©2024 IEEE 374


Authorized licensed use limited to: VIT University- Chennai Campus. Downloaded on August 21,2024 at 19:26:36 UTC from IEEE Xplore. Restrictions apply.
350 test samples, covering different types and degrees of research can focus on developing new models that are not only
fractures. To verify the effectiveness of the proposed method, capable of processing large-scale and high-dimensional medical
we conducted a series of comparative experiments to compare image data but also remain efficient and accurate in
the performance of different feature pyramid structures on the environments with limited computing resources. At the same
fracture detection task. Experimental results show that the Bi- time, improving the interpretability of algorithms will also
directional Feature Transfer Pyramid (Bi-FPM) using ResNext- provide medical professionals with more valuable decision-
101 as the backbone has improved by 5.8% compared to the making support [16].
baseline Faster R-CNN model on the Kaggle fracture data set,
and has improved compared to the classic FPN 4.1%. This III. MOTIVATION
significant performance improvement is attributed to the In today's medical practice, accurate diagnosis of fractures is
optimization of feature fusion and transfer of the Bi-FPM crucial for timely treatment and recovery of patients. Although
structure [7, 8]. traditional medical image analysis relies on the professional
judgment of radiologists, this process can be time-consuming
II. LITERATURE REVIEW and limited by subjective experience, especially in medical
In the field of medical image analysis, especially for fracture settings with high patient volumes or limited resources.
detection applications, a variety of algorithms have been Additionally, different types of fractures may require different
developed, each with different advantages and disadvantages. treatments, and subtle cracks or complex fractures may not be
Traditional machine learning methods, such as support vector easily distinguished on imaging. Therefore, it is particularly
machines (SVM) and random forests [9], have attracted urgent to develop an automated and high-precision fracture
attention due to their applicability in computing resource- detection method [17].
constrained environments and good performance on small-scale
data sets. However, these methods are limited in automatic With the advancement of artificial intelligence technology,
feature extraction and often perform worse than deep learning especially the successful application of deep learning in the field
models when dealing with high-dimensional data [10]. of image recognition, new possibilities have been provided for
medical image analysis. Deep learning models, such as CNN
Deep learning methods, including convolutional neural and Faster R-CNN, have proven to have excellent performance
networks (CNN) and U-Net, have shown superior performance in many medical image analysis tasks, but when it comes to
in processing complex medical images due to their powerful fracture detection, these models still face the problem of large
capabilities of automatic feature learning [11]. These methods data volume requirements, high computational resource
can extract key information from large-scale data sets and consumption, and difficulty in processing multiple tasks.
improve accuracy and robustness. However, they require large Challenges such as scale characteristics. In addition, existing
amounts of annotated data and large computing resources, which algorithms still need to find a better balance between the
may be an obstacle in resource-limited situations [12]. accuracy, real-time performance, and resource consumption of
fracture detection [18].
Variants of CNN, such as AlexNet, VGG, and ResNet,
provide strong adaptability to specific tasks through their Therefore, the motivation of this study is to develop a novel
adjustable depth and complexity, and hierarchical feature fracture detection algorithm that aims to overcome the
extraction mechanisms capable of capturing multi-level features limitations of existing technologies and improve the accuracy
from edges to complex textures. Nonetheless, deeper network and efficiency of fracture detection by optimizing feature
structures can sometimes lead to overfitting, and on small-scale extraction and enhancing the generalization ability of the model.
datasets, it may be necessary to rely on data augmentation or We expect this approach to provide physicians with a powerful
transfer learning strategies [13]. aid without adding additional computational burden so that they
can diagnose various types of fractures more quickly and
Region proposal networks such as Faster R-CNN have accurately, thereby improving patient outcomes [19, 20].
become an important milestone in the field of object detection
through their end-to-end training strategy that can effectively IV. METHOD
locate regions of interest in images and perform accurate object
detection. However, its performance may suffer when dealing In the proposed Faster R-CNN model based on bidirectional
with a large number of small or dense objects, and the high feature transfer, the feature extraction and bidirectional transfer
computational load of the region proposal step also affects its mechanism is an innovative structure designed to capture rich
real-time performance [14]. image features to improve the accuracy of fracture detection.
This mechanism consists of two complementary pyramid
Feature Pyramid Network (FPN) and its variants structurally structures: the forward feature transfer pyramid and the
integrate high-level semantic information and low-level detailed backward feature transfer pyramid, which are shown as Figure
information, which can capture features of different scales and 1 and Figure 2. The forward feature transfer pyramid reduces the
are particularly effective for detecting fracture targets of various feature map size layer by layer through downsampling and
sizes. However, this approach may cause the model to become integrates high-level abstract semantic information with low-
more complex, and the choice of feature fusion strategy can level detailed texture information, while the reverse feature
greatly affect model performance [15]. transfer pyramid increases the feature map size layer by layer
through upsampling. , which strengthens the representation
In summary, the choice of fracture detection algorithm needs
ability of contextual information. The two-way operation of
to be determined based on the specific application background,
these two pyramids on spatial resolution and feature depth not
available resources, and performance requirements. Future

375
Authorized licensed use limited to: VIT University- Chennai Campus. Downloaded on August 21,2024 at 19:26:36 UTC from IEEE Xplore. Restrictions apply.
only improves the expressive power of features but also provides In the Faster R-CNN model based on bidirectional feature
more comprehensive information for the detection algorithm, transfer that we studied, the model architecture is carefully
thereby effectively improving the performance of Faster R-CNN designed to enhance the accuracy of fracture detection. The
in the fracture detection task. Through this two-way feature architecture uses ResNext-101 as the basic network, which is
transfer, the model can more accurately locate and identify responsible for extracting original features from images. Next
fractures of different types and sizes, ensuring efficient and are two innovative pyramid structures, the forward feature
reliable detection results. transfer pyramid and the reverse feature transfer pyramid, which
are respectively responsible for downsampling and merging
high-level semantic information into low-level features, and
upsampling and enhancing low-level detailed information to
high-level features. Hierarchical features ensure the effective
representation of features at different scales. The Region
Proposal Network (RPN) further locates potential fracture
regions on these fused features and generates candidate
detection frames. Subsequently, ROI Pooling converts these
candidate boxes into fixed-size feature maps for use by
classifiers and bounding box regressors to classify fracture types
and accurately locate fracture areas. Finally, non-maximum
suppression (NMS) technology is used to screen out the optimal
detection frames and eliminate overlaps to form the final
Fig. 1. Forward feature transfer pyramid. detection results, which is shown in Figure 3 and Figure 4. This
overall architecture optimizes the information flow, making the
model not only improved in fracture detection performance but
also more efficient in processing speed.
V. EXPERIMENT
The experiment compared the performance of different
feature pyramid structures combined with Faster R-CNN on the
Kaggle fracture data set. The evaluation metrics used include
average accuracy (AP) as a percentage at IoU=0.5 (AP_0.5), and
frames processed per second (FPS). It can be seen that whether
Fig. 2. Backward feature transfer pyramid. using ResNet-50, ResNet-101, or ResNext-101 as the backbone,
the performance of the proposed bidirectional feature transfer
pyramid (Bi-FPM) structure is better than the baseline Faster R-
CNN model and the traditional feature pyramid Network (FPN).

TABLE I. COMPARISON OF DIFFERENT FEATURE PYRAMIDS WITH


HEADER FASTER-R-CNN ON KAGGLE BONE FRACTURE DATASET
Method Table column subhead Subhead Subhead
ResNet Baseline 79.4 0.3
Fig. 3. The detection header with Bi-FPN -50
FPN 81.1 0.3
The proposed Bi-FPM 85.2 0.3
ResNet Baseline 81.8 0.3
-101
FPN 83.7 0.3
The proposed Bi-FPM 87.2 0.3
ResNex Baseline 82.6 0.3
t-101
FPN 84.3 0.3
The proposed Bi-FPM 88.4 0.3

Simply put, when using ResNet-50, the initial performance


of the model is 79.4%. After adding FPN technology, the
performance improved to 81.1%. However, after introducing the
new Bi FPM technology, the performance is further improved to
85.2%, which is a significant improvement. When the model is
Fig. 4. Faster R-CNN [21]. based on ResNet-101, Bi FPM increases the performance from

376
Authorized licensed use limited to: VIT University- Chennai Campus. Downloaded on August 21,2024 at 19:26:36 UTC from IEEE Xplore. Restrictions apply.
81.8% to 87.2%.". For the ResNext-101 model, Bi FPM algorithms[C]//2022 10th International Conference on Information and
technology can achieve an effect of 88.4%, compared to the Education Technology (ICIET). IEEE, 2022: 53-57.
original 82.6% and 84.3% with added FPN, indicating the [3] Ni L, Huang Q, Ye J, et al. Vocational education development model
based on intelligent management system[C]//2022 11th International
advantage of Bi FPM in improving detection accuracy. Conference on Educational and Information Technology (ICEIT). IEEE,
In all cases, FPS remains unchanged at 0.3, indicating that 2022: 76-79.
although performance has improved, detection speed has not [4] Ni L, Shi J, Han B, et al. Classroom Roll Call System Based on Face
Detection Technology[C]//2022 10th International Conference on
been affected. This shows that the proposed Bi-FPM structure Information and Education Technology (ICIET). IEEE, 2022: 42-46.
can significantly improve the accuracy of fracture detection [5] Jixian L, An G, Zhihao S, et al. Social Media Multimodal Information
without sacrificing speed. These results highlight the advantages Analysis based on the BiLSTM-Attention-CNN-XGBoost Ensemble
of Bi-FPM in feature extraction, especially its ability to capture Neural Network[J]. International Journal of Advanced Computer Science
fracture features in images for effective detection. and Applications, 2022, 13(12).
[6] Yang Q, Wu W, Yang Y, et al. The Improved Fully Convolutional
Mathematical and algorithmic analysis of experimental Network applied in Segmentation and Detection for Pavement
results reveals significant performance improvements of Crack[C]//Proceedings of the 2023 7th International Conference on Deep
Bidirectional Feature Transfer Pyramid (Bi-FPM) over baseline Learning Technologies. 2023: 21-26.
Faster R-CNN and Feature Pyramid Network (FPN). In terms of [7] Chang X, Su Z, Ni L, et al. Person Re-identification Based on Deep
average accuracy (AP_0.5), Bi-FPM demonstrates higher Learning Algorithms with Manual Extracted Colour and Texture
Features[C]//2022 7th International Conference on Big Data Analytics
detection accuracy. From an algorithmic point of view, this is (ICBDA). IEEE, 2022: 243-247.
because it more effectively combines features from different [8] Liu C, Chang X, Cao Z, et al. Welding Seam Recognition Technology of
convolutional layers through mathematical multiple-scale Welding Robot Based on A Novel Multi-Path Neural Network
analysis and feature cascading to enhance the expressive power Algorithm[C]//2022 14th International Conference on Machine Learning
of the model. At the same time, the constant frame rate (FPS) in and Computing (ICMLC). 2022: 407-412.
the experiment shows that the performance improvement has not [9] Ahmad W S H M W, Fauzi M F A, Hasan M J, et al. Multi-configuration
affected the real-time responsiveness of the model. In addition, analysis of densenet architecture for whole slide image scoring of er-
ihc[J]. IEEE Access, 2023.
the advantages of deeper network architectures such as
ResNext-101 in recognition capabilities compared to ResNet-50 [10] Verma H C, Ahmed T, Rajan S, et al. Development of LR-PCA based
fusion approach to detect the changes in mango fruit crop by using landsat
or ResNet-101 also reflect the importance of higher-level 8 OLI images[J]. IEEE Access, 2022, 10: 85764-85776.
features in deep learning. Overall, these improvements reflect [11] Shahrani S, Zainal N F A, Abd Rahman R, et al. The development of a
the algorithm optimization achieved by Bi-FPM through web-based infographic for the introduction of palm industry to young
effective feature fusion and optimized feature space utilization learners[J]. Journal of ICT in Education, 2023, 10(2): 155-167.
in the fracture detection task. [12] Yang S, Yin B, Cao W, et al. Diagnostic accuracy of deep learning in
orthopaedic fractures: a systematic review and meta-analysis[J]. Clinical
VI. CONCLUSION Radiology, 2020, 75(9): 713. e17-713. e28.
[13] Kalmet P H S, Sanduleanu S, Primakov S, et al. Deep learning in fracture
In this study, we propose a Faster R-CNN framework based detection: a narrative review[J]. Acta orthopaedica, 2020, 91(2): 215-220.
on bidirectional feature transfer, aiming to improve the accuracy
[14] Olczak J, Fahlberg N, Maki A, et al. Artificial intelligence for analyzing
of fracture detection. Through experimental verification on the orthopedic trauma radiographs: deep learning algorithms—are they on par
Kaggle fracture data set, our model structure shows better with humans for diagnosing fractures?[J]. Acta orthopaedica, 2017, 88(6):
performance than traditional Faster R-CNN and Feature 581-586.
Pyramid Network (FPN). Experimental results show that using [15] Ren M, Yi P H. Deep learning detection of subtle fractures using staged
our bidirectional feature transfer pyramid (Bi-FPM) not only algorithms to mimic radiologist search pattern[J]. Skeletal Radiology,
achieves higher average accuracy (AP_0.5) on different 2022: 1-9.
backbone networks but also maintains processing speed (FPS), [16] Badgeley M A, Zech J R, Oakden-Rayner L, et al. Deep learning predicts
hip fracture using confounding patient and healthcare variables[J]. NPJ
reflecting the model A balance between efficiency and digital medicine, 2019, 2(1): 31.
effectiveness. In the future, we want to see if Bi FPM technology [17] Pranata Y D, Wang K C, Wang J C, et al. Deep learning and SURF for
can help other medical image analysis tasks to automate medical automated classification and detection of calcaneus fractures in CT
diagnosis. images[J]. Computer methods and programs in biomedicine, 2019, 171:
27-37.
ACKNOWLEDGMENT [18] Chen W, Liu X, Li K, et al. A deep-learning model for identifying fresh
vertebral compression fractures on digital radiography[J]. European
The Corresponding author is Zhihao Su. The funding is from Radiology, 2022: 1-10.
Yuezhi Yang and Zhihao Su.
[19] Guy S, Jacquet C, Tsenkoff D, et al. Deep learning for the radiographic
diagnosis of proximal femur fractures: Limitations and programming
REFERENCES issues[J]. Orthopaedics & Traumatology: Surgery & Research, 2021,
[1] Su Z, Adam A, Nasrudin M F, et al. Skeletal fracture detection with deep 107(2): 102837.
learning: A comprehensive review[J]. Diagnostics, 2023, 13(20): 3245. [20] Gao Y, Soh N Y T, Liu N, et al. Application of a deep learning algorithm
[2] Shi J, Ni L, Su Z. English-speaking teaching system with natural language in the detection of hip fractures[J]. Iscience, 2023, 26(8).
processing technology based on artificial intelligence [21] Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international

377
Authorized licensed use limited to: VIT University- Chennai Campus. Downloaded on August 21,2024 at 19:26:36 UTC from IEEE Xplore. Restrictions apply.

You might also like