Analysis on Leg Bone Fracture Detection and Classification Using X-ray Images

Myint, Wint Wah

doi:10.11648/j.mlr.20180303.11

Cited by 33 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the system produces the output results with accurate and reliable performance and less processing time based on the contributed methods. According to the result, best accuracy achieved was 83 % using the Kappa accuracy assessment [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Long Bone X-ray Images using New features and Support Vector Machine

2021

IJATCSE

View full text Add to dashboard Cite

Bones are protecting many organs in the human body such as the lungs, brain, heart and other internal organs. Bone fracture is a common problem in human beings and may occur due to the high pressure that is applied to the bones as a result of an accident or any other reasons. X-ray (radiograph) is the noninvasive medical experimentthat helps doctors diagnose and present medical conditions. X-rays represent the oldest and most often used kind of medical imagery. Medical image processing attempts to enhance the bone fracture diagnosis processes by creating an automated system that can go through a large database of the X-ray images and identify the required diagnosis faster and with high accuracy than the regular diagnosis processes. In this paper, the lower leg bone (Tibia) fracture is studied and many novel features are extracted using various image processing techniques. The purpose of this research is to use new investigated features and classify the X-ray bone images as a fractured and non-fractured bone and make the system more applicable and closer to the user using the Graphical User Interface (GUI). The Tibia bone fracture detection system was developed in three main steps: the preprocessing step, feature extraction using wavelet analysis, gradient analysis, principal components (PCA), and edge detection methods and classification using Support Vector Machine (SVM). The results were produced using four possible outcomes from the confusion matrix which are TP, TN, FP, and FN. The classification process was repeated using different feature groups at a time and the resultant accuracies were ranged between 70%-80%.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In Myint et al (2018) work [8], suggested a Computer-Aided Diagnosis (CAD) technique to automatically recognize and localize the leg bone fracture. Many image processing techniques were used in their paper, they recognized that Harris corner detection was an effective tool to catch the broken points of the leg bone.…”

Section: Introductionmentioning

confidence: 99%

Classification of Long Bone X-ray Images using New features and Support Vector Machine

2021

IJATCSE

View full text Add to dashboard Cite

show abstract

“…Before DCNN became available, conventional machine learning for fracture classi cation in medical images required image pre-processing and feature extraction [10]- [11] before proceeding to the classi cation procedure. Edge detection had to be conducted rst during image pre-processing, such as through a Harris corner detection [11], Gaussian edge detection, or Sobel edge detection [12]. Further extraction of "useful features" that machine learning can learn from is the key step in conventional machine learning.…”

Section: Introductionmentioning

confidence: 99%

Recognition of rib fracture on chest X-ray images with deep learning: a pilot study

Huang

Liu

et al. 2022

Preprint

View full text Add to dashboard Cite

Objectives: Among trauma patients, it is crucial to avoid a delay in providing life-saving procedures owing to a missed diagnosis of a fracture. Unfortunately, missed rib fractures are common in such patients. Ribs have been found to be the locations with the most frequently missed fractures. As shown in previous studies, nearly 50% of rib fractures are missed on radiographs. As a concern, patients with fractured ribs may have higher morbidity and mortality rates than those without fractures. Although arranging more sensitive image studies such as computer tomography for every chest trauma patient is an option, doing so is impractical because of the cost and higher radiation exposure. Point of care ultrasound is another option that is time consuming and operator dependent. The purpose of this study was to identify rib fractures on chest radiographs using deep convolutional neural network (DCNN). Methods: We retrospectively collected chest radiographs with formal image reports of rib fractures during the last 5 years from a single medical center. Then, 2000 region-of-interest (ROI) slices for each category, i.e., fractured rib, non-fracture rib, and background, were segmented into pixel dimensions of 128 × 128 for DCNN model training. Results: The validation accuracy of the trained models was as follows: 91.00% transfer learning with AlexNet and 91.17% transfer learning with GoogLeNet. Both performances of our trained model are remarkable. Conclusions: Further application of rib fracture recognition DCNN models for clinical decision support could significantly improve the clinical workflow and help clinical doctors from missing the diagnosis of rib fractures.

show abstract

“…Likewise, Gray Level Concurrency Matrix (GLCM) features was used in analysis of cancer cells using laser pico-projections images [33] or in detection of bone fractures in X-ray images [34]. Similarly, deep learning with CNN [35], application of K-Nearest Neighbors algorithm (KNN) to decision trees [36] have been applied for the analysis of X-ray image in order to detect and characterize bone fractures. Similar approaches have also been tested in ultrasonic echography.…”

Section: Introductionmentioning

confidence: 99%

Automatic Classifying of Patients With Non-Traumatic Fractures Based on Ultrasonic Guided Wave Spectrum Image Using a Dynamic Support Vector Machine

et al. 2020

View full text Add to dashboard Cite

Bone fractures are caused by diseases or accidents and are a widespread problem throughout the globe. Worldwide, 1.6 millions of hip fractures occur every year and are expected to rise to 6.3 millions in 2050. The current gold standard to assess fracture risk is the Dual-energy X-ray Absorptiometry (DXA), which provides a projected image of the bone from which areal bone mineral density is extracted. Ultrasound techniques have been proposed as non invasive alternatives. Recently, estimates of cortical thickness and porosity, obtained by Bi-Directional Axial Transmission (BDAT) in a pilot clinical study, have been shown to be associated with non-traumatic fractures in post menopausal women. Cortical parameters were derived from the comparison between experimental and theoretical guided modes. This model-based inverse approach failed for the patients associated with poor guided mode information. Moreover, even if the fracture discrimination ability was found similar to DXA, it remained moderate. The goal of this paper is to explore if these two limitations could be overcome by using automatic classification tools, independent of any waveguide model. To this end, a dynamic machine learning approach based on a Support Vector Machine (SVM) has been used to classify ultrasonic guided wave spectrum images measured by BDAT on post menopausal women with or without non-traumatic fractures. This approach has then been improved using parameters tuned by Bat Algorithm Optimization (BOA). The applied methodology focused on the extraction of texture features through a gray level co-occurrence matrix, structural comparison and histograms. The results accuracy was assessed using a confusion matrix. The effectiveness of the learning approach reached an accuracy of 92.31%. INDEX TERMS cortical bone, osteoporosis, fracture discrimination, quantitative ultrasound, guided waves, support vector machine, bat algorithm, guided wave spectrum image.

show abstract

Analysis on Leg Bone Fracture Detection and Classification Using X-ray Images

Cited by 33 publications

References 4 publications

Classification of Long Bone X-ray Images using New features and Support Vector Machine

Classification of Long Bone X-ray Images using New features and Support Vector Machine

Recognition of rib fracture on chest X-ray images with deep learning: a pilot study

Automatic Classifying of Patients With Non-Traumatic Fractures Based on Ultrasonic Guided Wave Spectrum Image Using a Dynamic Support Vector Machine

Contact Info

Product

Resources

About