-
Fa Yi Xue Za Zhi Aug 2023The artificial intelligence-aided diagnosis model of rib fractures based on YOLOv3 algorithm was established and applied to practical case to explore the application...
OBJECTIVES
The artificial intelligence-aided diagnosis model of rib fractures based on YOLOv3 algorithm was established and applied to practical case to explore the application advantages in rib fracture cases in forensic medicine.
METHODS
DICOM format CT images of 884 cases with rib fractures caused by thoracic trauma were collected, and 801 of them were used as training and validation sets. A rib fracture diagnosis model based on YOLOv3 algorithm and Darknet53 as the backbone network was built. After the model was established, 83 cases were taken as the test set, and the precision rate, recall rate, 1-score and radiology interpretation time were calculated. The model was used to diagnose a practical case and compared with manual diagnosis.
RESULTS
The established model was used to test 83 cases, the fracture precision rate of this model was 90.5%, the recall rate was 75.4%, 1-score was 0.82, the radiology interpretation time was 4.4 images per second and the identification time of each patient's data was 21 s, much faster than manual diagnosis. The recognition results of the model was consistent with that of the manual diagnosis.
CONCLUSIONS
The rib fracture diagnosis model in practical case based on YOLOv3 algorithm can quickly and accurately identify fractures, and the model is easy to operate. It can be used as an auxiliary diagnostic technique in forensic clinical identification.
Topics: Humans; Rib Fractures; Artificial Intelligence; Thoracic Injuries; Algorithms; Radiography; Retrospective Studies
PubMed: 37859472
DOI: 10.12116/j.issn.1004-5619.2023.230308 -
European Cells & Materials Jan 2019Congenital spine deformities may be influenced by movements in utero, but the effects of foetal immobility on spine and rib development remain unclear. The purpose of...
Congenital spine deformities may be influenced by movements in utero, but the effects of foetal immobility on spine and rib development remain unclear. The purpose of the present study was to determine (1) critical time-periods when rigid paralysis caused the most severe disruption in spine and rib development and (2) how the effects of an early, short-term immobilisation were propagated to the different features of spine and rib development. Chick embryos were immobilised once per single embryonic day (E) between E3 and E6 and harvested at E9. To assess the ontogenetic effects following single-day immobilisation, other embryos were immobilised at E4 and harvested daily between E5 and E9. Spinal curvature, vertebral shape and segmentation and rib development were analysed by optical projection tomography and histology. The results demonstrated that periods critical for movement varied for different aspects of spine and rib development. Single-day immobilisation at E3 or E4 resulted in the most pronounced spinal curvature abnormalities, multiple wedged vertebrae and segmentation defects, while single-day immobilisation at E5 led to the most severe rib abnormalities. Assessment of ontogenetic effects following single-day immobilisation at E4 revealed that vertebral segmentation defects were subsequent to earlier vertebral body shape and spinal curvature abnormalities, while rib formation (although delayed) was independent from thoracic vertebral shape or curvature changes. A day-long immobilisation in chicks severely affected spine and rib development, highlighting the importance of abnormal foetal movements at specific time-points and motivating targeted prenatal monitoring for early diagnosis of congenital scoliosis.
Topics: Animals; Chick Embryo; Disease Progression; Fetus; Immobilization; Lumbar Vertebrae; Ribs; Spinal Curvatures; Spine; Thoracic Vertebrae; Time Factors
PubMed: 30644077
DOI: 10.22203/eCM.v037a03 -
EBioMedicine Dec 2020Diagnosis of rib fractures plays an important role in identifying trauma severity. However, quickly and precisely identifying the rib fractures in a large number of CT...
BACKGROUND
Diagnosis of rib fractures plays an important role in identifying trauma severity. However, quickly and precisely identifying the rib fractures in a large number of CT images with increasing number of patients is a tough task, which is also subject to the qualification of radiologist. We aim at a clinically applicable automatic system for rib fracture detection and segmentation from CT scans.
METHODS
A total of 7,473 annotated traumatic rib fractures from 900 patients in a single center were enrolled into our dataset, named RibFrac Dataset, which were annotated with a human-in-the-loop labeling procedure. We developed a deep learning model, named FracNet, to detect and segment rib fractures. 720, 60 and 120 patients were randomly split as training cohort, tuning cohort and test cohort, respectively. Free-Response ROC (FROC) analysis was used to evaluate the sensitivity and false positives of the detection performance, and Intersection-over-Union (IoU) and Dice Coefficient (Dice) were used to evaluate the segmentation performance of predicted rib fractures. Observer studies, including independent human-only study and human-collaboration study, were used to benchmark the FracNet with human performance and evaluate its clinical applicability. A annotated subset of RibFrac Dataset, including 420 for training, 60 for tuning and 120 for test, as well as our code for model training and evaluation, was open to research community to facilitate both clinical and engineering research.
FINDINGS
Our method achieved a detection sensitivity of 92.9% with 5.27 false positives per scan and a segmentation Dice of 71.5%on the test cohort. Human experts achieved much lower false positives per scan, while underperforming the deep neural networks in terms of detection sensitivities with longer time in diagnosis. With human-computer collobration, human experts achieved higher detection sensitivities than human-only or computer-only diagnosis.
INTERPRETATION
The proposed FracNet provided increasing detection sensitivity of rib fractures with significantly decreased clinical time consumed, which established a clinically applicable method to assist the radiologist in clinical practice.
FUNDING
A full list of funding bodies that contributed to this study can be found in the Acknowledgements section. The funding sources played no role in the study design; collection, analysis, and interpretation of data; writing of the report; or decision to submit the article for publication .
Topics: Algorithms; Deep Learning; Humans; Image Processing, Computer-Assisted; Neural Networks, Computer; ROC Curve; Reproducibility of Results; Rib Fractures; Software; Tomography, X-Ray Computed
PubMed: 33186809
DOI: 10.1016/j.ebiom.2020.103106 -
Chinese Journal of Traumatology =... Aug 2017Rib fractures are the most common skeletal thoracic injuries resulting from blunt chest trauma. Half of the rib fractures are not detected upon a precise physical... (Comparative Study)
Comparative Study
PURPOSE
Rib fractures are the most common skeletal thoracic injuries resulting from blunt chest trauma. Half of the rib fractures are not detected upon a precise physical evaluation and radiographs. Recently ultrasonography (USG) has been investigated to detect rib fractures. But based on literature the usefulness of USG varies widely. This study was conducted to investigate the role of USG in the detection of possible rib fractures in comparison with radiography.
METHODS
In this cross-sectional study, consecutive patients with minor blunt chest trauma and suspected rib fractures presenting in Imam Reza Hospital located in Mashhad-Iran, between April 2013 and October 2013 were assessed by USG and radiography. The radiography was performed in a posteroanterior (PA) chest projection and oblique rib view centered over the area of trauma. The time duration spent in taking USG and radiography were recorded. The prevalence and location of fractures revealed by USG and radiography were compared.
RESULTS
Sixty-one suspected patients were assessed. The male to female ratio was 2.4:1 (43 men and 18 women) with a mean ± SD age of (44.3 ± 19.7) years. There were totally 59 rib fractures in 38 (62.3%) patients based on radiography and USG, while 23 (37.7%) patients had no diagnostic evidence of rib lesions. USG revealed 58 rib fractures in 33 (54.1%) of 61 suspected patients and radiographs revealed 32 rib fractures in 20 (32.8%) of 61 patients. A total of 58 (98.3%) rib fractures were detected by USG, whereas oblique rib view and PA chest radiography showed 27 (45.8%) and 24 (40.7%) rib fractures, respectively. The average duration of USG was (12 ± 3) min (range 7-17 min), whereas the duration of radiography was (27 ± 6) min (range 15-37 min). The kappa coefficient showed a low level of agreement between both USG and PA chest radiography (kappa coefficient = 0.28), and between USG and oblique rib view (kappa coefficient = 0.32).
CONCLUSION
USG discloses more fractures than radiography in most patients presenting with suspected rib fractures. Moreover USG requires significantly less time than radiography.
Topics: Adolescent; Adult; Aged; Aged, 80 and over; Cross-Sectional Studies; Female; Humans; Male; Middle Aged; Rib Fractures; Ultrasonography; Young Adult
PubMed: 28687342
DOI: 10.1016/j.cjtee.2016.04.010 -
Evidence-based Complementary and... 2022Rib fracture is the most common thoracic clinical trauma. Most patients have multiple different types of rib fracture regions, so accurate and rapid identification of...
Rib fracture is the most common thoracic clinical trauma. Most patients have multiple different types of rib fracture regions, so accurate and rapid identification of all trauma regions is crucial for the treatment of rib fracture patients. In this study, a two-stage rib fracture recognition model based on nnU-Net is proposed. First, a deep learning segmentation model is trained to generate candidate rib fracture regions, and then, a deep learning classification model is trained in the second stage to classify the segmented local fracture regions according to the candidate fracture regions generated in the first stage to determine whether they are fractures or not. The results show that the two-stage deep learning model proposed in this study improves the accuracy of rib fracture recognition and reduces the false-positive and false-negative rates of rib fracture detection, which can better assist doctors in fracture region recognition.
PubMed: 35251210
DOI: 10.1155/2022/5841451 -
Clinical Biomechanics (Bristol, Avon) Dec 2020High rates of morbidity and mortality following flail chest rib fractures are well publicized. Standard of care has been supportive mechanical ventilation, but serious...
INTRODUCTION
High rates of morbidity and mortality following flail chest rib fractures are well publicized. Standard of care has been supportive mechanical ventilation, but serious complications have been reported. Internal rib fixation has shown improvements in pulmonary function, clinical outcomes, and decreased mortality. The goal of this study was to provide a model defining the biomechanical benefits of internal rib fixation.
METHODS
One human cadaver was prepared with an actuator providing anteroposterior forces to the thorax and rib motion sensors to define interfragmentary motion. Cadaveric model was validated using a prior study which defined costovertebral motion to create a protocol using similar technology and procedure. Ribs 4-6 were fixed with motion sensors anteriorly, laterally and posteriorly. Motion was recorded with ribs intact before osteotomizing each rib anteriorly and laterally. Flail chest motion was record with fractures subsequently plated and analyzed. Motion was recorded in the sagittal, coronal and transverse axes.
FINDINGS
Compared to the intact rib model, the flail chest model demonstrated an 11.3 times increase in sagittal plane motion, which was reduced to 2.1 times the intact model with rib plating. Coronal and sagittal plane models also saw increases of 9.7 and 5.1 times, respectively, with regards to flail chest motion. Both were reduced to 1.2 times the intact model after rib plating.
INTERPRETATION
This study allows quantification of altered ribcage biomechanics after flail chest injuries and suggests rib plating is useful in restoring biomechanics as well as contributing to improving pulmonary function and clinical outcomes.
Topics: Biomechanical Phenomena; Bone Plates; Cadaver; Flail Chest; Fracture Fixation, Internal; Humans; Mechanical Phenomena; Rib Fractures; Thoracic Injuries
PubMed: 33045492
DOI: 10.1016/j.clinbiomech.2020.105191 -
Emergency Medicine International 2023To assess the use of CT with oblique axis rib stretch (OARS) and curved planar reformats (CPRs) for rib fracture detection and characterization.
OBJECTIVE
To assess the use of CT with oblique axis rib stretch (OARS) and curved planar reformats (CPRs) for rib fracture detection and characterization.
METHODS
A total of 108 forensically diagnosed patients with rib fractures were evaluated retrospectively. OARS and CPRs were independently used during the diagnosis in two groups. In each group, the final diagnosis was made after a junior radiologist's initial diagnosis was reviewed by a senior radiologist. The images were evaluated for the presence and characterization of rib fractures.
RESULTS
A total of 2,592 ribs were analyzed, and 326 fractured ribs and 345 fracture sites were diagnosed using reference standard. Two groups of radiologists identified 331 and 333 fracture sites using the OARS method, 291 and 288 fracture sites using the CPRs method, and 274 fracture sites in forensically diagnosed patients (CR: conventional reconstruction), respectively; and all missed diagnoses were nondisplaced rib fractures. The ROC A value of OARS was 0.98, which is higher than CPRs 0.91, and CR 0.90 (all < 0.01). The A value for detecting rib fractures using CPRs and CR has no statistical difference ( = 0.14 and 0.29). More misdiagnosed patients were found using CPRs (42 and 44 cases) than OARS (1 and 2 cases) and CR (2 cases). The displaced fracture detection ratio of all methods showed no difference.
CONCLUSIONS
Doctors using the OARS method could improve diagnostic performance for detecting rib fractures without the requirement of specialized software and workstation when compared with CPRs.
PubMed: 37674861
DOI: 10.1155/2023/4904844 -
Frontiers in Bioengineering and... 2021To evaluate vehicle occupant injury risk, finite element human body models (HBMs) can be used in vehicle crash simulations. HBMs can predict tissue loading levels, and...
To evaluate vehicle occupant injury risk, finite element human body models (HBMs) can be used in vehicle crash simulations. HBMs can predict tissue loading levels, and the risk for fracture can be estimated based on a tissue-based risk curve. A probabilistic framework utilizing an age-adjusted rib strain-based risk function was proposed in 2012. However, the risk function was based on tests from only twelve human subjects. Further, the age adjustment was based on previous literature postulating a 5.1% decrease in failure strain for femur bone material per decade of aging. The primary aim of this study was to develop a new strain-based rib fracture risk function using material test data spanning a wide range of ages. A second aim was to update the probabilistic framework with the new risk function and compare the probabilistic risk predictions from HBM simulations to both previous HBM probabilistic risk predictions and to approximate real-world rib fracture outcomes. Tensile test data of human rib cortical bone from 58 individuals spanning 17-99 years of ages was used. Survival analysis with accelerated failure time was used to model the failure strain and age-dependent decrease for the tissue-based risk function. Stochastic HBM simulations with varied impact conditions and restraint system settings were performed and probabilistic rib fracture risks were calculated. In the resulting fracture risk function, sex was not a significant covariate-but a stronger age-dependent decrease than previously assumed for human rib cortical bone was evident, corresponding to a 12% decrease in failure strain per decade of aging. The main effect of this difference is a lowered risk prediction for younger individuals than that predicted in previous risk functions. For the stochastic analysis, the previous risk curve overestimated the approximate real-world rib fracture risk for 30-year-old occupants; the new risk function reduces the overestimation. Moreover, the new function can be used as a direct replacement of the previous one within the 2012 probabilistic framework.
PubMed: 34109166
DOI: 10.3389/fbioe.2021.677768 -
European Journal of Trauma and... Aug 2019Over the years, a trend has evolved towards operative treatment of flail chest although evidence is limited. Furthermore, little is known about operative treatment for... (Comparative Study)
Comparative Study
BACKGROUND
Over the years, a trend has evolved towards operative treatment of flail chest although evidence is limited. Furthermore, little is known about operative treatment for patients with multiple rib fractures without a flail chest. The aim of this study was to compare rib fixation based on a clinical treatment algorithm with nonoperative treatment for both patients with a flail chest or multiple rib fractures.
METHODS
All patients with ≥ 3 rib fractures admitted to one of the two contributing hospitals between January 2014 and January 2017 were retrospectively included in this multicenter cohort study. One hospital treated all patients nonoperatively and the other hospital treated patients with rib fixation according to a clinical treatment algorithm. Primary outcome measures were intensive care length of stay and hospital length of stay for patients with a flail chest and patients with multiple rib fractures, respectively. To control for potential confounding, propensity score matching was applied.
RESULTS
A total of 332 patients were treated according to protocol and available for analysis. The mean age was 56 (SD 17) years old and 257 (77%) patients were male. The overall mean Injury Severity Score was 23 (SD 11) and the average number of rib fractures was 8 (SD 4). There were 92 patients with a flail chest, 37 (40%) had rib fixation and 55 (60%) had non-operative treatment. There were 240 patients with multiple rib fractures, 28 (12%) had rib fixation and 212 (88%) had non-operative treatment. For both patient groups, after propensity score matching, rib fixation was not associated with intensive care unit length of stay (for flail chest patients) nor with hospital length of stay (for multiple rib fracture patients), nor with the secondary outcome measures.
CONCLUSION
No advantage could be demonstrated for operative fixation of rib fractures. Future studies are needed before rib fixation is embedded or abandoned in clinical practice.
Topics: Accidental Falls; Accidents, Traffic; Cohort Studies; Critical Care; Female; Flail Chest; Fracture Fixation; Fractures, Multiple; Hospitalization; Humans; Male; Middle Aged; Rib Fractures; Thoracic Injuries; Treatment Outcome; Wounds, Nonpenetrating
PubMed: 30341561
DOI: 10.1007/s00068-018-1037-1 -
Frontiers in Bioengineering and... 2023Human body models (HBMs) play a key role in improving modern vehicle safety systems to protect broad populations. However, their geometry is commonly derived from...
Human body models (HBMs) play a key role in improving modern vehicle safety systems to protect broad populations. However, their geometry is commonly derived from single individuals chosen to meet global anthropometric targets, thus their internal anatomy may not fully represent the HBM's target demographic. Past studies show sixth rib cross-sectional geometry differences between HBM ribs and population-derived ribs, and corrections to HBM ribs based on these data have improved HBM's abilities to predict rib fracture locations. We measure and report average and standard deviations (SDs) in rib cross-sectional geometric properties derived from live subject CT scans of 240 adults aged 18-90. Male and female results are given as functions of rib number and rib lengthwise position for ribs 2 through 11. Population means/SDs are reported for measures of rib total area, rib cortical bone area, and rib endosteal area, as well as inertial moment properties of these rib sections. These population corridors are compared between males and females, and against the baseline rib geometries defined in six current HBMs. Total cross-sectional area results found average males ribs to be larger than those of females by between approximately 1-2 SDs depending on rib number and position, and larger in cortical bone cross-sectional area by between 0-1 SDs. Inertial moment ratios showed female ribs being between approximately 0-1 SDs more elongated than male ribs, dependent again on rib number and position. Rib cross-sectional areas from 5 of the 6 HBMs were found to be overly large along substantial portions of most ribs when compared to average population corridors. Similarly, rib aspect ratios in HBMs deviated from average population data by up to 3 SDs in regions towards sternal rib ends. Overall, while most HBMs capture overall trends such as reductions in cross-section along shaft lengths, many also exhibit local variation that deviates from population trends. This study's results provide the first reference values for assessing the cross-sectional geometry of human ribs across a wide range of rib levels. Results also further provide clear guidelines to improve rib geometry definitions present in current HBMs in order to better represent their target demographic.
PubMed: 37284235
DOI: 10.3389/fbioe.2023.1158242