The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network

Objective: Scaphoid fractures, particularly occult and non-displaced fractures, are difficult to detect using traditional X-ray methods because of their subtle appearance and variability in bone density. This study proposes a two-stage CNN approach to detect and classify scaphoid fractures using ant...

Full description

Saved in:
Bibliographic Details
Main Authors: Tai-Hua Yang, Yung-Nien Sun, Rong-Shiang Li, Ming-Huwi Horng
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/21/2425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850193493096398848
author Tai-Hua Yang
Yung-Nien Sun
Rong-Shiang Li
Ming-Huwi Horng
author_facet Tai-Hua Yang
Yung-Nien Sun
Rong-Shiang Li
Ming-Huwi Horng
author_sort Tai-Hua Yang
collection DOAJ
description Objective: Scaphoid fractures, particularly occult and non-displaced fractures, are difficult to detect using traditional X-ray methods because of their subtle appearance and variability in bone density. This study proposes a two-stage CNN approach to detect and classify scaphoid fractures using anterior–posterior (AP) and lateral (LA) X-ray views for more accurate diagnosis. Methods: This study emphasizes the use of multi-view X-ray images (AP and LA views) to improve fracture detection and classification. The multi-view fusion module helps integrate information from both views to enhance detection accuracy, particularly for occult fractures that may not be visible in a single view. The proposed method includes two stages, which are stage 1: detect the scaphoid bone using Faster RCNN and a Feature Pyramid Network (FPN) for region proposal and small object detection. The detection accuracy for scaphoid localization is 100%, with Intersection over Union (IoU) scores of 0.8662 for AP views and 0.8478 for LA views. And stage 2: perform fracture classification using a ResNet backbone and FPN combined with a multi-view fusion module to combine features from both AP and LA views. This stage achieves a classification accuracy of 89.94%, recall of 87.33%, and precision of 90.36%. Results: The proposed model performs well in both scaphoid bone detection and fracture classification. The multi-view fusion approach significantly improves recall and accuracy in detecting fractures compared to single-view approaches. In scaphoid detection, both AP and LA views achieved 100% detection accuracy. In fracture detection, using multi-view fusion, the accuracy for AP views reached 87.16%, and for LA views, it reached 83.83%. Conclusions: The multi-view fusion model effectively improves the detection of scaphoid fractures, particularly in cases of occult and non-displaced fractures. The model provides a reliable, automated approach to assist clinicians in detecting and diagnosing scaphoid fractures more efficiently.
format Article
id doaj-art-22768a4bd6db418394d441fbef8b5c52
institution OA Journals
issn 2075-4418
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-22768a4bd6db418394d441fbef8b5c522025-08-20T02:14:15ZengMDPI AGDiagnostics2075-44182024-10-011421242510.3390/diagnostics14212425The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural NetworkTai-Hua Yang0Yung-Nien Sun1Rong-Shiang Li2Ming-Huwi Horng3Department of Biomedical Engineering, National Cheng Kung University, Tainan 701, TaiwanDepartment of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701, TaiwanDepartment of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701, TaiwanDepartment of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701, TaiwanObjective: Scaphoid fractures, particularly occult and non-displaced fractures, are difficult to detect using traditional X-ray methods because of their subtle appearance and variability in bone density. This study proposes a two-stage CNN approach to detect and classify scaphoid fractures using anterior–posterior (AP) and lateral (LA) X-ray views for more accurate diagnosis. Methods: This study emphasizes the use of multi-view X-ray images (AP and LA views) to improve fracture detection and classification. The multi-view fusion module helps integrate information from both views to enhance detection accuracy, particularly for occult fractures that may not be visible in a single view. The proposed method includes two stages, which are stage 1: detect the scaphoid bone using Faster RCNN and a Feature Pyramid Network (FPN) for region proposal and small object detection. The detection accuracy for scaphoid localization is 100%, with Intersection over Union (IoU) scores of 0.8662 for AP views and 0.8478 for LA views. And stage 2: perform fracture classification using a ResNet backbone and FPN combined with a multi-view fusion module to combine features from both AP and LA views. This stage achieves a classification accuracy of 89.94%, recall of 87.33%, and precision of 90.36%. Results: The proposed model performs well in both scaphoid bone detection and fracture classification. The multi-view fusion approach significantly improves recall and accuracy in detecting fractures compared to single-view approaches. In scaphoid detection, both AP and LA views achieved 100% detection accuracy. In fracture detection, using multi-view fusion, the accuracy for AP views reached 87.16%, and for LA views, it reached 83.83%. Conclusions: The multi-view fusion model effectively improves the detection of scaphoid fractures, particularly in cases of occult and non-displaced fractures. The model provides a reliable, automated approach to assist clinicians in detecting and diagnosing scaphoid fractures more efficiently.https://www.mdpi.com/2075-4418/14/21/2425medical image computer-aided diagnosis systemscaphoid bonescaphoid fracturesmulti-view detection and segmentationconvolutional neural network
spellingShingle Tai-Hua Yang
Yung-Nien Sun
Rong-Shiang Li
Ming-Huwi Horng
The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network
Diagnostics
medical image computer-aided diagnosis system
scaphoid bone
scaphoid fractures
multi-view detection and segmentation
convolutional neural network
title The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network
title_full The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network
title_fullStr The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network
title_full_unstemmed The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network
title_short The Detection and Classification of Scaphoid Fractures in Radiograph by Using a Convolutional Neural Network
title_sort detection and classification of scaphoid fractures in radiograph by using a convolutional neural network
topic medical image computer-aided diagnosis system
scaphoid bone
scaphoid fractures
multi-view detection and segmentation
convolutional neural network
url https://www.mdpi.com/2075-4418/14/21/2425
work_keys_str_mv AT taihuayang thedetectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork
AT yungniensun thedetectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork
AT rongshiangli thedetectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork
AT minghuwihorng thedetectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork
AT taihuayang detectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork
AT yungniensun detectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork
AT rongshiangli detectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork
AT minghuwihorng detectionandclassificationofscaphoidfracturesinradiographbyusingaconvolutionalneuralnetwork