ParallelNet: multiple backbone network for detection tasks on thigh bone fracture

Wang, Mengxuan; Yao, Jinkun; Zhang, Guoshan; Guan, Bin; Wang, Xinbo; Zhang, Yueming

doi:10.1007/s00530-021-00783-9

Cited by 21 publications

(13 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, deep learning-based object detection methods [8,10,11,[15][16][17] have made great progress in medical image fracture detection. Zhang et al [8] proposed a point-based annotation scheme and Window Loss for the inherent visual ambiguity of pelvic fractures, which achieved an area under the curve (AUC) of 0.983.…”

Section: Object Detection Methodsmentioning

confidence: 99%

See 1 more Smart Citation

MPFracNet: A Deep Learning Algorithm for Metacarpophalangeal Fracture Detection with Varied Difficulties

Geng¹,

Luo²,

Li³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Due to small size and high occult, metacarpophalangeal fracture diagnosis displays a low accuracy in terms of fracture detection and location in X-ray images. To efficiently detect metacarpophalangeal fractures on Xray images as the second opinion for radiologists, we proposed a novel onestage neural network named MPFracNet based on RetinaNet. In MPFracNet, a deformable bottleneck block (DBB) was integrated into the bottleneck to better adapt to the geometric variation of the fractures. Furthermore, an integrated feature fusion module (IFFM) was employed to obtain more in-depth semantic and shallow detail features. Specifically, Focal Loss and Balanced L1 Loss were introduced to respectively attenuate the imbalance between positive and negative classes and the imbalance between detection and location tasks. We assessed the proposed model on the test set and achieved an AP of 80.4% for the metacarpophalangeal fracture detection. To estimate the detection performance for fractures with different difficulties, the proposed model was tested on the subsets of metacarpal, phalangeal and tiny fracture test sets and achieved APs of 82.7%, 78.5% and 74.9%, respectively. Our proposed framework has state-of-the-art performance for detecting metacarpophalangeal fractures, which has a strong potential application value in practical clinical environments.

show abstract

Section: Object Detection Methodsmentioning

confidence: 99%

“…The average accuracy (AP) on 358 test thigh images reaches 82.1%. Wang et al [11] designed multiple parallel backbone networks and a feature fusion connection structure to detect and locate thigh fractures. The framework achieved 87.8% AP50 and 49.3% AP75.…”

Section: Object Detection Methodsmentioning

confidence: 99%

MPFracNet: A Deep Learning Algorithm for Metacarpophalangeal Fracture Detection with Varied Difficulties

Geng¹,

Luo²,

Li³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…The highest result of fracture detection performed by Guan et al, on approximately 4000 arm fracture X-ray images in a musculoskeletal radiograph (MURA) dataset, 62.04% AP, was obtained using proposed two-stage region-based convolutional neural networks (R-CNN) method [ 4 ]. The AP50 score achieved by Wang et al, was 87.8% with the ParallelNet method developed for fracture detection in a dataset of 3842 thigh fracture X-ray images, using a TripleNet backbone network [ 5 ]. Using a part of the dataset of 1052 bone images in total, Ma and Luo carried out fracture detection with Faster R-CNN, followed by fracture/non-fracture classification with the proposed CrackNet model using the entire dataset, achieving an accuracy of 90.11% [ 6 ].…”

Section: Related Workmentioning

confidence: 99%

Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models

Hardalaç

Uysal

Peker

et al. 2022

Sensors

View full text Add to dashboard Cite

Hospitals, especially their emergency services, receive a high number of wrist fracture cases. For correct diagnosis and proper treatment of these, images obtained from various medical equipment must be viewed by physicians, along with the patient’s medical records and physical examination. The aim of this study is to perform fracture detection by use of deep-learning on wrist X-ray images to support physicians in the diagnosis of these fractures, particularly in the emergency services. Using SABL, RegNet, RetinaNet, PAA, Libra R-CNN, FSAF, Faster R-CNN, Dynamic R-CNN and DCN deep-learning-based object detection models with various backbones, 20 different fracture detection procedures were performed on Gazi University Hospital’s dataset of wrist X-ray images. To further improve these procedures, five different ensemble models were developed and then used to reform an ensemble model to develop a unique detection model, ‘wrist fracture detection-combo (WFD-C)’. From 26 different models for fracture detection, the highest detection result obtained was 0.8639 average precision (AP50) in the WFD-C model. Huawei Turkey R&D Center supports this study within the scope of the ongoing cooperation project coded 071813 between Gazi University, Huawei and Medskor.

show abstract

“…Their method classifies healthy and fractured bone with a classification accuracy of 90.14%. In similar research, a new Parallel Net approach for classifying fractured bone has been proposed using the two-scale method proposed by Wang et al [ 21 ].…”

Section: Related Workmentioning

confidence: 99%

“…Wang et al [ 20 ] developed a two-stage deep CNN based method for bone fracture diagnosis and achieved an accuracy of 87.8%. Yahalomi et al [ 21 ] and Abbas et al [ 22 ] applied faster-RCNN for bone diagnosis and achieved an accuracy of 96% and 97%, respectively. Sasidhar et al [ 45 ] evaluated the performance of VGG19, DenseNet121, and DenseNet169.…”

Section: Comparative Analysismentioning

confidence: 99%

Hybrid SFNet Model for Bone Fracture Detection and Classification Using ML/DL

Yadav

Sharma

Athithan

et al. 2022

Sensors

View full text Add to dashboard Cite

An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consuming process. The development of machine learning (ML), as well as deep learning (DL), has set a new path in medical image diagnosis. In this study, we proposed a novel multi-scale feature fusion of a convolution neural network (CNN) and an improved canny edge algorithm that segregate fracture and healthy bone image. The hybrid scale fracture network (SFNet) is a novel two-scale sequential DL model. This model is highly efficient for bone fracture diagnosis and takes less computation time compared to other state-of-the-art deep CNN models. The innovation behind this research is that it works with an improved canny edge algorithm to obtain edges in the images that localize the fracture region. After that, grey images and their corresponding canny edge images are fed to the proposed hybrid SFNet for training and evaluation. Furthermore, the performance is also compared with the state-of-the-art deep CNN models on a bone image dataset. Our results showed that SFNet with canny (SFNet + canny) achieved the highest accuracy, F1-score and recall of 99.12%, 99% and 100%, respectively, for bone fracture diagnosis. It showed that using a canny edge algorithm improves the performance of CNN.

show abstract

ParallelNet: multiple backbone network for detection tasks on thigh bone fracture

Cited by 21 publications

References 25 publications

MPFracNet: A Deep Learning Algorithm for Metacarpophalangeal Fracture Detection with Varied Difficulties

MPFracNet: A Deep Learning Algorithm for Metacarpophalangeal Fracture Detection with Varied Difficulties

Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models

Hybrid SFNet Model for Bone Fracture Detection and Classification Using ML/DL

Contact Info

Product

Resources

About