Bone Fracture Detection Research Articles

Correlation of Temporal Bone Fracture on Computed Tomography Scan with Hearing Loss in Posttraumatic Patients

Introduction: Temporal bone fractures in adults are invariably due to motor vehicle accidents or road traffic accidents. Hearing loss is a common complaint following temporal bone fractures, but attention to it is frequently overlooked as there may be other life-threatening complications associated with it that may require immediate attention of the caregiver. Immediate detection of temporal bone fracture and its complications helps in providing early and effective treatment. Aim: The main objective of our study is to observe various types of fractures on multidetector computed tomography (CT), difference between various types, and classification of fractures of temporal bone with correlation between types of fracture and clinical hearing loss. Methods: Two-year (2019–2021) prospective study of head injured patients with temporal bone fracture presented to the Department of Radio-diagnosis (AVBRH, DMIMS, Wardha) with complaints of hearing loss was subjected for study. Temporal bone fracture patients satisfying inclusion and exclusion criteria having hearing loss were evaluated audiologically after a gap of 3 months following the initial injury once the patient was stable. Age and gender distribution, cause of injury, radiological findings, and clinical presentations were analyzed. Data were entered into Microsoft Excel data sheet and were analyzed using SPSS 22 version software. Results: Out of 173 patients having hearing loss with temporal bone fracture, majority of the patients were male (84.97%) and were between 20 and 39 years (46.24%) with a mean age of 41 years. The major cause of injury was motor vehicle accidents (84.39%). The right side was involved (49.1%) more than the left side (46.0%). Longitudinal type fracture was most frequent (64.74%). Otic capsule involvement was present in 9.25%. Conductive hearing loss was more common in otic capsule sparing and sensorineural hearing loss was more common in otic capsule-involved fractures. Otic capsule sparing was more common in (95.54%) longitudinal type of fracture. Otic capsule violation was more common in (26.09%) transverse type of fracture. Conclusion: This study suggests that image analysis of high-resolution CT can be used in fracture of temporal bone either to detect the hearing loss or to know the type and classify the fracture or to find the correlation between the types of fracture and clinical hearing loss.

Long Bone Fracture Detection By Using Image Processing and Machine Learning

In this work, the researcher presents an automatic system to detect the presence of long bone fractures by using clinical images obtained from X-Ray for diagnostic purposes. The procedure for the diagnosis of the bone fractures is considered to be a very critical step based on factors to identify this image as normal or abnormal to save the effort and time spent to detect bone fractures. Trained radiologists often identify rare diseases with high accuracy such as fractures. However, tests examining the accuracy of someone have shown that when reading X-Rays with several errors, the error rate may rise in some cases. Accurate diagnosis of the bone fraction is important. The Histogram Oriented Gradients (HOG) and Local Binary Pattern Algorithm (LBP) are used for features extraction. This study used two different classifiers. The first classification is Support Vector Machine (SVM), which provides accuracy of 97.85 percent by Radial basis kernel function (RBF) and the second classifier is Multilayer Perceptron (MLP), which gives accuracy of 99.15 percent, then the accuracy of the classifiers are compared with each other. Consequently, Multilayer Perceptron algorithm has the highest accuracy of 99.15 percent. We obtained the best results by MLP using LBP which has the best results as Sensitivity, Specificity and Accuracy are 100, 98.35 and 99.15 percent. As a result, long-term bone marrow transplantation is a major problem in bone and radiology, and it is suggested that a new computer-assisted discovery program could help reduce the risk of long-term bone detection loss.
 The study presents a discussion and discovery of a computer-based long bone fracture detection system by MATLAB, that had been used as the programming tool for loading files, image processing.
 The purpose of this work is to provide insight into the related activities of research conducted. In addition, the researcher proposed long bone fraction detection system by using a computer-supported program. Furthermore, the researcher has mentioned a brief overview of classifiers used in the detection of long bone fractures.

Leveraging Machine Learning Tools and Techniques for the Pre-Emptive Detection, Classification and Diagnosis of Bone-Fractures

Technologies that are developing quickly are constantly emerging in several fields, particularly the medical one. However, certain old-fashioned techniques are still frequently employed and productive. This is one of these approaches. X-rays are used to spot broken bones. The number of fractures can, however, occasionally be negligible and obscure. Systems that are effective and intelligent should be developed. In this investigation, a synthetic categorization system is being developed to classify bone fractures. The system that has been created consists of two main steps. The images of In the first stage, the fractures are processed using several image processing algorithms to determine their location and forms. The back propagation neural network is trained on the processed images before being used in the classification step, which comes next. The experiment tested the method on various images of bone fractures, and the results show high performance and a rate of categorization.

Feasibility of Bone Fracture Detection Using Microwave Imaging

This paper studies the feasibility of Microwave Imaging (MWI) for detection of fractures in superficial bones like the tibia, using a simple and practical setup. First-responders could use it for fast preliminary diagnosis in emergency locations, where X-Rays are not available. It may prove valuable also for cases where X-ray are not recommended, e.g., length pregnant women or children. The method is inspired on the synthetic aperture radar technique. A single Vivaldi antenna is used to linearly scan the bone in the 8.3-11.1 GHz frequency range and collect the scattered fields. The system is operated in air, without the need for impractical impedance-matching immersion liquids. The image is reconstructed using a Kirchhoff migration algorithm. A Singular Value Decomposition (SVD) strategy is used to remove skin and background artifacts. To test this technique, a set of full-wave simulations and experiments were conducted on a multilayer phantom and on an ex-vivo animal bone. Results show that the system can detect and locate bone transverse fractures as small as 1 mm width and 13 mm deep, even when the bone is wrapped by 2 mm thick skin.

COMPARISON OF SEGMENTATION METHODS USED FOR BONE FRACTURE IMAGES

Abstract. The usage of computers and software in the biomedical field has been increasing and applications for doctors, clinicians, scientists and other users have been developed in the recent times. Manual, semi-automatic and fully automatic applications developed for bone fracture detection are one of the important studies in this field. Image segmentation, which is one of the image preprocessing steps in bone fracture detection, is an important step to obtain successful results with high accuracy. In this study, Otsu thresholding method, active contour method, k-means method, fuzzy c-mean method, Niblack thresholding method and max min thresholding range (MMTR) method are used on bone images obtained by Karabük University Training and Research Hospital. When any filters are not applied on images to remove noises, the most successful method is obtained by K-means method based on specificity and accuracy as 89,55% and 83,31% respectively. Niblack thresholding method has the highest sensitivity result as 92,45%.

Comparative Analysis of Deep Convolutional Neural Network Models for Humerus Bone Fracture Detection

Deep learning plays a key role in medical image processing. One of the applications of deep learning models in this domain is bone fracture detection from X-ray images. Convolutional neural network and its variants are used in wide range of medical image processing applications. MURA Dataset is commonly used in various studies that detect bone fractures and this work also uses that dataset, in specific the Humerus bone radiograph images. The humerus dataset in the MURA dataset contains both images with fracture and without fracture. The image with fracture includes images with metals which are removed in this work. Experimental analysis was made with two variants of convolutional neural network, DenseNet169 Model and the VGG Model. In case of the DenseNet169 model, a model with the pre trained weights of ImageNet and one without it is experimented. Results obtained with these variants of CNN are comparedand it shows that DenseNet169 model that uses pre-trained weights of ImageNet model performs better than the other two models.

Modified deep learning ResNeXt model for Human long bone fracture detection and classification

The field of medical science is going to take advantage of Machine learning. It has increased dramatically over the last decade. Nowadays, you can see other innovations used in medical sciences, such as machine learning and deep learning. They can help to diagnose the illness or cause. It can also aid in the healing process by keeping notes. At a similar pace, an upper hand has been provided to the physicians for image processing by incorporating computers. Bone fractures are normal these days, and the identification of fractures is a critical part of orthopedic X-ray imaging. The automated technique lets the doctor quickly begin medical treatment. Using Machine Learning and CNN (Convolutional Neural Network), we suggest a new deep learning model perform bone diagnosis by eliminating discontinuity followed by segmentation of the image in a system that detects bone fractures. It overcomes the shortcomings of the previous approach that operates only on examination of the texture features. The proposed deep learning modified ResNeXt model performs much better than the state-of arts.

Evaluation of ultrashort echo-time (UTE) and fast-field-echo (FRACTURE) sequences for skull bone visualization and fracture detection – A postmortem study

Background and PurposeCT is considered the modality of choice in the assessment of the skull due to the fast and accurate depiction of bone structures. Nevertheless, MRI has evolved into a possible alternative due to optimal soft tissue contrast and recent advances with the ability to visualize tissues with shortest T2 times, such as osseous structures. In this study we compare skull bone visualization and fracture detection across two MRI sequences to CT as reference standard. Material and MethodsTwenty subjects underwent CT and MRI with less than 72 h between examination. The MRI protocol included a 2D ultrashort echo time (UTE) and a 3D multi-echo in-phase fast-field-echo (FRACTURE) sequence. Independent raters evaluated qualitative characteristics and fracture detectability in different skull subregions (skull vault, skull base and viscerocranium). Interrater and intermodality agreement was evaluated by calculating intraclass coefficients (ICC). ResultsFRACTURE ICC indicated a good agreement in all subregions (ICC = 0.83 – 0.88), whereas UTE had excellent results calculated in the skull vault and viscerocranium (ICC = 0.91 – 0.94). At the skull vault, both MRI sequences received an overall good rating (UTE: 2.63 ± 0.42 FRACTURE. 2.81 ± 0.32). Fracture detection using MRI sequences for the skull vault, was highest compared to other subregions. ConclusionsBoth MRI sequences may provide an alternative e.g. for surgical planning or follow up exams of the osseous neurocranium; although, at the skull base and viscerocranium bone visualization with MRI bone imaging sequences perform inferior to CT standard imaging.

Augmenting Osteoporosis Imaging with Machine Learning.

In this paper, we discuss how recent advancements in image processing and machine learning (ML) are shaping a new and exciting era for the osteoporosis imaging field. With this paper, we want to give the reader a basic exposure to the ML concepts that are necessary to build effective solutions for image processing and interpretation, while presenting an overview of the state of the art in the application of machine learning techniques for the assessment of bone structure, osteoporosis diagnosis, fracture detection, and risk prediction. ML effort in the osteoporosis imaging field is largely characterized by "low-cost" bone quality estimation and osteoporosis diagnosis, fracture detection, and risk prediction, but also automatized and standardized large-scale data analysis and data-driven imaging biomarker discovery. Our effort is not intended to be a systematic review, but an opportunity to review key studies in the recent osteoporosis imaging research landscape with the ultimate goal of discussing specific design choices, giving the reader pointers to possible solutions of regression, segmentation, and classification tasks as well as discussing common mistakes.

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

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%.

Window Loss for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation

Object detection methods are widely adopted for computer-aided diagnosis using medical images. Anomalous findings are usually treated as objects that are described by bounding boxes. Yet, many pathological findings, e.g., bone fractures, cannot be clearly defined by bounding boxes, owing to considerable instance, shape and boundary ambiguities. This makes bounding box annotations, and their associated losses, highly ill-suited. In this work, we propose a new bone fracture detection method for X-ray images, based on a labor effective and flexible annotation scheme suitable for abnormal findings with no clear object-level spatial extents or boundaries. Our method employs a simple, intuitive, and informative point-based annotation protocol to mark localized pathology information. To address the uncertainty in the fracture scales annotated via point(s), we convert the annotations into pixel-wise supervision that uses lower and upper bounds with positive, negative, and uncertain regions. A novel Window Loss is subsequently proposed to only penalize the predictions outside of the uncertain regions. Our method has been extensively evaluated on 4410 pelvic X-ray images of unique patients. Experiments demonstrate that our method outperforms previous state-of-the-art image classification and object detection baselines by healthy margins, with an AUROC of 0.983 and FROC score of 89.6%.

Computer and magnetic resonance imaging for pelvic fractures in children

Introduction. Fractures of pelvic bones in children are rare and make up from 0.3 to 4% of all childhood trauma, 20% of children with polytrauma have pelvic ring injuries. Comparative studies of diagnostic capabilities of MRI and CT in sacral and acetabular fractures showed that about 37% of CT were missed, therefore the authors recommended MRI as the best method in visualizing pelvic fractures.Aim of this study is to show the capabilities of CT and MRI to improve recognition of pelvic fractures.Material and methods. In the period 2010–2019, 790 children with pelvic fractures as part of polytrauma were studied. The age of children was from 8.5 to 17 years, average 10.14 ± 1.4. Computed tomography with three-phase contrast was performed in all 790 patients on Brilliance 16 scanners. MRI was performed (n = 63) on a 3 T tomograph with obtaining multiplanar STIR, T1-, T2- and PD weighted images (VI) with signal suppression factor of adipose tissue, as well as 3D isotropic images.Results. On the polytrauma severity scale (ISS), the assessment of the condition of 790 children ranged from 23.54 to 27.5 (mean 25.77) points. The main mechanism of pelvic injury was road traffic accidents (pedestrian + passenger – 63.54% (n = 502), catatrauma was in second place – 32.66% (n = 258), followed by compression – 2.15% (n = 17) , sports injury – 0.38% (n = 3), other injury – 3.43% (n = 27). 73.26% (n = 578) had multiple pelvic fractures, 20.5% (n = 162) – complicated, – 22.3% (n = 176) unstable In 63 patients with damage to the anterior pelvic ring, according to CT, MRI revealed fractures of the posterior pelvic ring in 79.36% (n = 50).Conclusion. Children with polytrauma must undergo computed tomography to exclude not only all non-muscular-skeletal injuries, but also combined pelvic fractures. We believe that for the detection and assessment of bone fractures and concomitant injuries of other tissues and organs of the pelvis, in most cases, multiphase CT with intravenous contrast is a sufficient method. MRI is important for evaluating pelvic soft tissue structures such as tendons, ligaments, nerves and fascia, as well as detecting hidden / fine bone lesions.

Doğrusal Kutuplu Antenlerle Kemik Kırıklarının Tespit Edilmesi

Bu çalışmada antenlerin medikal görüntüleme alanında kullanılması ve doku altında meydana gelen kemik kırıklarının tespit edilmesi üzerinde çalışılmıştır. Kablosuz haberleşmede vazgeçilmez bir öneme sahip olan antenlerin, birçok farklı disiplinlerde kullanım alanı mevcuttur. Bu alanlardan bir taneside medikal alandır. Bu çalışmanın ana konusu antenlerin de medikal alanda kullanılabileceğini göstermektir. Çalışmada lineer (doğrusal) kutuplu antenler kullanılarak, doku altında yer alan kemik kırıklarının bulunması hedeflenmiştir. İlk olarak kurgulanan sistemi klinik alanda uygulamak ve tıbbi görüntüleme sistemini geliştirmek amacıyla; bağlı oldukları durum içerisinde mikrodalga antenin özelliklerinin bilinmesi gerekir [1]. Çalışmada horn anten ve patch antenler kullanılmış ve bu ikisi arasındaki farklar göz önünde bulundurularak, çalışmada en verimli sonucun hangisinden alındığına karar verilmiştir. Elektromanyetik dalgaların insan vücudu ve dokusu üzerinde yüksek yayılım gösterdiği göz önüne alınırsa [2], bu alanda özel antenlerin seçilmesi çok önemlidir. Seçilen horn ve patch antenler kendi aralarında haberleştirilir, birbirlerine aktarılan enerjiler saçılım parametreleriyle tespit edilir ve haberleşen bu iki anten arasına kemikli doku yerleştirilir. Verici antenin yaydığı elektromanyetik dalgalar doku içinden geçerek, alıcı antene ulaşır ve saçılma parametrelerine göre durum değerlendirilmesi yapılır. Kemik kırığı tespitinde, horn antenler ve patch antenler ayrı ayrı denenerek çalışmalar saçılım parametreleri açısından kıyaslanır ve kırık olma durumunda oluşan değişimler tespit edilmiştir.

Investigation of bone fracture diagnosis system using transverse vibration response.

In this study, a new diagnostic system is developed to easily identify bone fractures in non-medical environments. It is difficult to determine the extent of cracks, fractures, and the healing process inside humans owing to the differences among people and limitations of state-of-the-art medical devices. Thus, various medical techniques, such as X-ray, computed tomography, or fork tuning systems have been developed, and more advanced technologies are emerging in the medical engineering field. In hazardous circumstances, medical devices to detect bone fracture are not available or cannot be easily applied. Thus, there is a need for the rapid detection of bone fractures without medical devices. To this end, this study analyzes the transverse vibration responses of bones because bone fractures cause different mechanical vibration reactions. By comparing the transverse vibration responses of both healthy and fractured bones, the modal assurance criterion can be calculated and applied to detect the existence of bone fractures. The transverse vibration responses at low and high frequencies are different and exhibit different modal assurance criteria depending on whether or not they are abnormal. Then, the virtual spectrogram of the differences between the signals from non-fractured and fractured bones is calculated. With the help of the present criterion with transverse vibration data, this difference can be analyzed quantitatively and effectively. To validate the proposed system, experiments with artificial specimens, animal legs, and a cadaver are performed.

The Feature Ambiguity Mitigate Operator model helps improve bone fracture detection on X-ray radiograph

This study was performed to propose a method, the Feature Ambiguity Mitigate Operator (FAMO) model, to mitigate feature ambiguity in bone fracture detection on radiographs of various body parts. A total of 9040 radiographic studies were extracted. These images were classified into several body part types including 1651 hand, 1302 wrist, 406 elbow, 696 shoulder, 1580 pelvic, 948 knee, 1180 ankle, and 1277 foot images. Instance segmentation was annotated by radiologists. The ResNext-101+FPN was employed as the baseline network structure and the FAMO model for processing. The proposed FAMO model and other ablative models were tested on a test set of 20% total radiographs in a balanced body part distribution. To the per-fracture extent, an AP (average precision) analysis was performed. For per-image and per-case, the sensitivity, specificity, and AUC (area under the receiver operating characteristic curve) were analyzed. At the per-fracture level, the controlled experiment set the baseline AP to 76.8% (95% CI: 76.1%, 77.4%), and the major experiment using FAMO as a preprocessor improved the AP to 77.4% (95% CI: 76.6%, 78.2%). At the per-image level, the sensitivity, specificity, and AUC were 61.9% (95% CI: 58.7%, 65.0%), 91.5% (95% CI: 89.5%, 93.3%), and 74.9% (95% CI: 74.1%, 75.7%), respectively, for the controlled experiment, and 64.5% (95% CI: 61.3%, 67.5%), 92.9% (95% CI: 91.0%, 94.5%), and 77.5% (95% CI: 76.5%, 78.5%), respectively, for the experiment with FAMO. At the per-case level, the sensitivity, specificity, and AUC were 74.9% (95% CI: 70.6%, 78.7%), 91.7%% (95% CI: 88.8%, 93.9%), and 85.7% (95% CI: 84.8%, 86.5%), respectively, for the controlled experiment, and 77.5% (95% CI: 73.3%, 81.1%), 93.4% (95% CI: 90.7%, 95.4%), and 86.5% (95% CI: 85.6%, 87.4%), respectively, for the experiment with FAMO. In conclusion, in bone fracture detection, FAMO is an effective preprocessor to enhance model performance by mitigating feature ambiguity in the network.

Hybrid Microwave Medical Imaging Approach Combining Quantitative and Qualitative Algorithms

This letter proposes a hybrid microwave medical imaging (MMI) approach to reconstruct the inner structure of the human body with improved accuracy on mapping the dielectric permittivities. Specifically, the results of the quantitative and qualitative MMI are employed to act as the a priori information for each other through an iterative process. Hence, the hybrid MMI approach combines the advantages from both the quantitative and qualitative algorithms to visualize simultaneously the inner body structure with clear tissue boundaries and the positions of strong scatterers. This proposed approach is evaluated by considering the medical scenario of bone fracture detection. The resultant image shows that the relative error of the reconstructed permittivity can drop by 33% for the scanned body area when compared to the one generated by the conventional quantitative MMI, whereas the position of a bone fracture can still be precisely indicated.

Artificial intelligence application in bone fracture detection

The interest of researchers, clinicians, and industry in artificial intelligence (AI) continues to grow, especially with recent deep-learning (DL) advances. Recent published reports have shown the utility of DL for bone fracture diagnosis in the radiological examination. It is important for practicing physicians to recognize the current scope of DL as it may impact the clinical practices in the near future. This article will give an insight to the practicing clinician of the current advances in AI fracture diagnosis by reviewing the current literature on this participant. Electronic databases were searched for relevant articles relating to AI applications in bone fracture detection. We included all published work in PubMed, Medline, and Cross-references, which satisfied the inclusion criteria. The search identified 104 references. Of those, 13 articles were eligible for the analysis. AI advancements in fracture imaging applications can be divided into the categories of fracture detection, classification, segmentation, and noninterpretive tasks. Despite the potential work presented in the literature, there are many challenges in the form of clinical translation and its widespread uses. These challenges range from the proof of safety to clearance from the regulatory agencies.

Dual-energy CT in the diagnosis of occult acute scaphoid injury: a direct comparison with MRI

ObjectivesScaphoid injuries occult on plain radiography often require further imaging for definitive diagnosis. We investigate the utility of dual-energy computed tomography (DECT) for the detection of acute bone marrow oedema and fracture of scaphoid compared to MRI.Materials and methodsTwenty patients who presented acutely (without prior injury) to the emergency department with clinically suspected occult scaphoid fracture and had MRI of the wrist were prospectively recruited to have DECT (GE Revolution CT). Material decomposition images of the water-calcium base pair were generated and assessed in conjunction with the monochromatic images to permit correlation of marrow signal changes with any cortical disruption for fracture confirmation. The assessment was performed by two musculoskeletal radiologists blinded from MRI results. The statistical difference of MRI and reviewers’ detection of acute bone oedema (1 = present, 0 = absent) was performed using the Friedman test (SPSS v.16).ResultsMRI showed acute scaphoid fracture and/or bone marrow oedema in 14/20 patients of which 6 also had cortical disruption. On DECT, reviewer A identified oedema in 13 and cortical disruption in 10 patients while reviewer B identified oedema in 10 and cortical disruption in seven of the 14 MRI positive patients. No statistically significant difference in oedema detection on MRI and reviewers of DECT (p value 0.61) but DECT was more sensitive at detecting cortical disruption.ConclusionDECT has the capability to detect acute scaphoid oedema in addition to cortical fractures. However, compared to MRI, DECT has lower contrast resolution and less sensitive in the detection of mild oedema.Key Points• Dual-energy CT is able to detect acute traumatic scaphoid marrow oedema.• Dual-energy CT has greater detection rate of scaphoid fractures than MRI.• Dual-energy CT is an alternative to MRI for occult scaphoid injury.

Machine Learning Solutions for Osteoporosis-A Review.

Osteoporosis and its clinical consequence, bone fracture, is a multifactorial disease that has been the object of extensive research. Recent advances in machine learning (ML) have enabled the field of artificial intelligence (AI) to make impressive breakthroughs in complex data environments where human capacity to identify high-dimensional relationships is limited. The field of osteoporosis is one such domain, notwithstanding technical and clinical concerns regarding the application of ML methods. This qualitative review is intended to outline some of these concerns and to inform stakeholders interested in applying AI for improved management of osteoporosis. A systemic search in PubMed and Web of Science resulted in 89 studies for inclusion in the review. These covered one or more of four main areas in osteoporosis management: bone properties assessment (n= 13), osteoporosis classification (n= 34), fracture detection (n= 32), and risk prediction (n= 14). Reporting and methodological quality was determined by means of a 12-point checklist. In general, the studies were of moderate quality with a wide range (mode score 6, range 2 to 11). Major limitations were identified in a significant number of studies. Incomplete reporting, especially over model selection, inadequate splitting of data, and the low proportion of studies with external validation were among the most frequent problems. However, the use of images for opportunistic osteoporosis diagnosis or fracture detection emerged as a promising approach and one of the main contributions that ML could bring to the osteoporosis field. Efforts to develop ML-based models for identifying novel fracture risk factors and improving fracture prediction are additional promising lines of research. Some studies also offered insights into the potential for model-based decision-making. Finally, to avoid some of the common pitfalls, the use of standardized checklists in developing and sharing the results of ML models should be encouraged. © 2021 American Society for Bone and Mineral Research (ASBMR).

Bone fracture detection through the two-stage system of Crack-Sensitive Convolutional Neural Network

Abstract Automated fracture detection is an essential part in a computer-aided tele-medicine system. Fractures often occur in human's arbitrary bone due to accidental injuries such as slipping. In fact, many hospitals lack experienced surgeons to diagnose fractures. Therefore, computer-aided diagnosis (CAD) reduces the burden on doctors and identifies fracture. We present a new classification network, Crack-Sensitive Convolutional Neural Network (CrackNet), which is sensitive to fracture lines. In this paper, we propose a new two-stage system to detect fracture. Firstly, we use Faster Region with Convolutional Neutral Network (Faster R-CNN) to detect 20 different types of bone regions in X-ray images, and then we recognize whether each bone region is fractured by using CrackNet. Total of 1052 images are used to test our system, of which 526 are fractured images and the rest are non-fractured images. We assess the performance of our proposed system with X-ray images from Haikou People's Hospital, achieving 90.11% accuracy and 90.14% F-measure. And our system is better than other two-stage systems.