Missed rib fractures on evaluation of initial chest CT for trauma patients: pattern analysis and diagnostic value of coronal multiplanar reconstruction images with multidetector row CT

Intelligent detection and grading diagnosis of fresh rib fractures based on deep learning

BACKGROUND

Accurate detection and grading of fresh rib fractures are crucial for patient management but remain challenging due to the complexity of rib structures on CT images.

METHODS

Chest CT images from 383 patients with rib fractures were retrospectively analyzed. The dataset was divided into a training set (n = 306) and an internal testing set (n = 77). An external testing set of 50 patients from the public RibFrac dataset was included. Fractures were classified into severe and non-severe categories. A modified YOLO-based deep learning model was developed for detection and grading. Performance was compared with thoracic surgeons using precision, recall, mAP50, and F1 score.

RESULTS

The deep learning model showed excellent performance in diagnosing fresh rib fractures. For all fractures types in internal test set, the precision, recall, mAP50, and F1 score were 0.963, 0.934, 0.972, and 0.948, respectively. The model outperformed thoracic surgeons of varying experience levels (all p < 0.01).

CONCLUSION

The proposed deep learning model can automatically detect and grade fresh rib fractures with accuracy comparable to that of physicians. This model helps improve diagnostic accuracy, reduce physician workload, save medical resources, and strengthen health care in resource-limited areas.

CLINICAL TRIAL NUMBER

Not applicable.

Diagnostic Accuracy of Artificial Intelligence for Detection of Rib Fracture on X-ray and Computed Tomography Imaging: A Systematic Review

Rib pathology is uniquely difficult and time-consuming for radiologists to diagnose. AI can reduce radiologist workload and serve as a tool to improve accurate diagnosis. To date, no reviews have been performed synthesizing identification of rib fracture data on AI and its diagnostic performance on X-ray and CT scans of rib fractures and its comparison to physicians. The objectives of this study are to analyze the performance of artificial intelligence in diagnosing rib fracture on X-ray and computed tomography (CT) scan using multiple clinical studies and to compare it to that of physicians findings of rib fracture. A literature search was conducted on PubMed and Embase for articles regarding the use of artificial intelligence for the detection of rib fractures up until July 2024. AI model, number of cases, sensitivity, and comparison to physicians data was collected. A total of 29 studies, comprising 125,364 cases, were included in this review. The pooled sensitivity of AI models was 0.853. Nineteen of these studies compared their results to radiologists, orthopedic surgeons, or anesthesiologists, totalling 61 physicians. Of these 19 studies, the radiologists had a pooled sensitivity of 0.750. The sensitivity of AI in these studies by comparison was 0.840. The results suggest that artificial intelligence has a promising role in detecting rib fractures on X-ray and CT scans. In our interpretation, the performance of artificial intelligence is similar to, or better than, that of physicians, alluding to its encouraging potential in a clinical setting as it may reduce physician workload, improve reading efficiency, and lead to better patient outcomes.

AI-assisted radiologists vs. standard double reading for rib fracture detection on CT images: A real-world clinical study

To evaluate the diagnostic accuracy of artificial intelligence (AI) assisted radiologists and standard double-reading in real-world clinical settings for rib fractures (RFs) detection on CT images. This study included 243 consecutive chest trauma patients (mean age, 58.1 years; female, 166) with rib CT scans. All CT scans were interpreted by two radiologists. The CT images were re-evaluated by primary readers with AI assistance in a blinded manner. Reference standards were established by two musculoskeletal radiologists. The re-evaluation results were then compared with those from the initial double-reading. The primary analysis focused on demonstrate superiority of AI-assisted sensitivity and the noninferiority of specificity at patient level, compared to standard double-reading. Secondary endpoints were at the rib and lesion levels. Stand-alone AI performance was also assessed. The influence of patient characteristics, report time, and RF features on the performance of AI and radiologists was investigated. At patient level, AI-assisted radiologists significantly improved sensitivity by 25.0% (95% CI: 10.5, 39.5; P < 0.001 for superiority), compared to double-reading, from 69.2% to 94.2%. And, the specificity of AI-assisted diagnosis (100%) was noninferior to double-reading (98.2%) with a difference of 1.8% (95% CI: -3.8, 7.4; P = 0.999 for noninferiority). The diagnostic accuracy of both radiologists and AI was influenced by patient gender, rib number, fracture location, and fracture type. Radiologist performance was affected by report time, whereas AI's diagnostic accuracy was influenced by patient age and the side of the rib involved. AI-assisted additional-reader workflow might be a feasible strategy to instead of traditional double-reading, potentially offering higher sensitivity and specificity compared to standard double-reading in real-word clinical practice.

CPR related injuries of the chest wall: direct and indirect fractures

BACKGROUND

Rib and sternum fractures are common injuries associated with cardiopulmonary resuscitation (CPR). The fracture mechanism is either direct by application of force on sternum and anterior ribs or indirect by bending through compression of the thorax. The aim of this study was to determine morphologies of rib fractures after CPR and to reevaluate prior findings on fracture localisation, type and degree of dislocation.

METHODS

The present study was based on all inpatients treated for chest wall fractures after non traumatic cardiac arrest at a Level 1 Trauma Centre from 2010 to 2016 who had received CT scans. Each fracture was analyzed for location, degree of dislocation and fracture type classified according to AO/OTA and CWIS. We also analysed Fracture Line orientation.

RESULTS

We enrolled 40 patients with a total of 423 rib fractures. We found most fractures anterolaterally between the 3rd to 6th rib symmetrically on both sides of the thorax. We found sternum fractures in 30% of the patients, 50% being located at the at the corpus sterni between rib 3 and 4. All patients with sternum fractures suffered from rib fractures and most had fractures of the cartilage or osteochondral junction. All cartilage fractures were straight, undisplaced type A fractures. Most indirect fractures occurred anterolaterally between 50 and 60° in the axial plane. More than 90% of those fractures were classified as type A, 70% showed a straight fracture line and 60% were undisplaced. There was no difference in degree of dislocation between straight and oblique fracture lines. We found 143 incomplete fractures.

CONCLUSION

We confirmed prior findings regarding fracture patterns in CPR related injuries. We observed approximately 2-3 times as many straight-lined fractures as oblique ones following indirect trauma. One third of all fractures are incomplete, these highlights the special characteristics like high elasticity of ribs.

Detection of Costal Cartilage Fractures on CT Images With Computer-aided Detection System for Rib Fractures

BACKGROUND/AIM

Costal cartilage fractures are associated with poor prognosis in patients with blunt chest trauma. A Computer-Aided Detection (CAD) system for detecting rib fractures has been used in practice, but it is unclear whether this system recognizes costal cartilage fractures. This study investigated whether the CAD system for rib fracture can detect costal cartilage fractures.

PATIENTS AND METHODS

A total of 89 patients with costal cartilage fractures from participating hospitals over an 18-year period were included in the study. The presence of a costal cartilage fracture was determined by three radiologists. We reviewed fracture location, cartilage calcification, dislocation, and callus formation. The percentage of agreement between the radiologists and the CAD system (Rib fracture CAD, Fujifilm Medical Co., Ltd) was assessed.

RESULTS

We detected 246 costal cartilage fractures in 89 patients. The costal cartilage of rib 7 was injured most frequently. Costal cartilage fractures were categorized as either mid-chondral, costochondral, or chondro-sternal. The CAD system detected 33 lesions; 16 were consistent with the costal cartilage fractures determined by the radiologists (costochondral junction 13, mid-chondral 2, chondro-sternal 1).

CONCLUSION

The CAD system for rib fracture can detect costal cartilage fractures at the costochondral junction but is not sufficiently sensitive to detect costal cartilage fractures without calcification. The CAD system for rib fracture needs further development before it can be used to detect rib cartilage fractures.

Analysis of risk factors for poor healing and long-duration pain in conservative treatment of rib fractures

Rib fractures are a common injury following blunt chest trauma, accounting for approximately 10% of all traumatic injuries and up to 50% of blunt chest trauma cases. These fractures are associated with a high risk of complications, such as pneumothorax, hemothorax, and pulmonary infections, and can significantly impact respiratory function. This study analyzes the risk factors for poor healing and long-duration pain in the conservative treatment of rib fractures, providing a reference for clinicians in choosing conservative treatment and formulating treatment plans. A retrospective analysis was conducted on 342 patients who underwent conservative treatment for rib fractures from January 2023 to May 2024. Baseline data, clinical data, and follow-up data were collected. Comparisons were made between the poor healing group and the good healing group, as well as between the long-duration pain group and the short-duration pain group in the conservative treatment of rib fractures. Univariate and multivariate logistic regression analyses were performed to identify risk factors for poor healing and long-duration pain. In patients undergoing conservative treatment for rib fractures, the average duration of pain was 12.18 ± 10.78 days, with an incidence of pulmonary complications of 59.06% (202/342) and poor healing rate of 6.43% (22/342). Significant differences were observed between the good and poor healing groups in terms of age (P = .018), presence of coronary heart disease (CHD, P = .023), chronic obstructive pulmonary disease (COPD, P < .001), blood calcium (P = .007), and alkaline phosphatase (P < .001). Similarly, significant differences were found between the long-duration and short-duration pain groups in age (P = .039), presence of diabetes (P < .001), CHD (P < .001), COPD (P < .001), and alkaline phosphatase (P < .001). Multivariate analysis identified COPD (P = .015), blood calcium (P = .013), and alkaline phosphatase (P = .006) as independent risk factors for poor healing, while diabetes (P = .001), CHD (P = .014), and alkaline phosphatase (P < .001) were independent risk factors for prolonged pain duration. COPD, blood calcium, and alkaline phosphatase are independent risk factors for poor healing in conservative treatment of rib fractures. Diabetes, CHD, and alkaline phosphatase are independent risk factors for long-duration pain in conservative treatment of rib fractures.

Computed tomography versus radiography for the detection of rib and skull fractures in paediatric suspected physical abuse: a systematic review

The diagnosis of suspected physical abuse (SPA) remains a continuous challenge to paediatric healthcare. Several studies have reported that computed tomography (CT) improves the evaluation of SPA. This study aims to systematically review the diagnostic performance of CT compared to radiography in investigating skull and chest fractures for SPA. Multiple databases were searched, using PRISMA methods, from 2008 to August 2024 for relevant studies in English. Two reviewers independently screened and selected relevant studies using Covidence software. The QUADAS-2 tool was used for the quality assessment of the included papers. Sensitivity, specificity and the effective radiation dose of CT and radiography from the included studies were extracted. Pooled sensitivity and specificity were calculated with their respective 95% confidence intervals (CI). GRADE criteria were used to appraise the overall quality of the synthesis. Of the 4057 identified papers, 10 met the inclusion criteria; all 10 included skull and/or chest. The overall sensitivity and specificity of CT were 96.5% (95% CI, 94.9-97.7%) and 99.5% (95% CI, 99.1-99.8%), respectively. Compared to the sensitivity and specificity of radiography, 59.8% (95% CI, 56.2-63.3%) and 99.7% (95% CI, 99.3-99.8%), respectively. Conclusion: CT sensitivity is significantly higher than radiography in detecting rib and skull fractures for SPA. The effective dose for chest LDCT is comparable to that of radiography. Therefore, LDCT should be considered a potential replacement to radiography in SPA investigations for the chest and skull. What is Known • CT shows higher diagnostic performance than radiography in detecting skull and rib fractures in the diagnosis of SPA. What is New • When a head CT scan is acquired for SPA diagnosis at any age, the two-view skull radiograph can be safely eliminated from the Skeletal Survey protocol, likewise, Chest CT can replace chest radiography for SPA diagnosis of rib fractures. • The effective dose and image quality of low-dose chest CT is comparable to that of two-view chest radiography for SPA diagnosis.

Performance of thoracic ultrasonography compared with chest radiography for the detection of rib fractures using computed tomography as a reference standard

OBJECTIVE

Although there is growing evidence that ultrasonography is superior to X-ray for rib fractures' detection, X-ray is still indicated as the most appropriate method. This has partially been attributed to a lack of studies using an appropriate reference modality. We aimed to compare the diagnostic accuracy of ultrasonography and X-ray in the detection of rib fractures, considering CT as the reference standard.

MATERIALS AND METHODS

Within a 2.5-year period, all consecutive patients with clinically suspected rib fracture(s) following blunt chest trauma and available posteroanterior/anteroposterior X-ray and thoracic CT were prospectively studied and planned to undergo thoracic ultrasonography, by a single operator. All imaging examinations were evaluated for cortical rib fracture(s), and their location was recorded. The cartilaginous rib portions were not assessed. CTs and X-rays were evaluated retrospectively. Concomitant thoracic/extra-thoracic injuries were assessed on CT. Comparisons were performed with the Mann-Whitney U test and Fisher's exact test.

RESULTS

Fifty-nine patients (32 males, 27 females; mean age, 53.1 ± 16.6 years) were included. CT, ultrasonography, and X-ray (40 posteroanterior/19 anteroposterior views) diagnosed 136/122/42 rib fractures in 56/54/27 patients, respectively. Ultrasonography and X-ray had sensitivity of 100%/40% and specificity of 89.7%/30.9% for rib fractures' detection. Ultrasound accuracy was 94.9% compared to 35.4% for X-rays (P < .001) in detecting individual rib fractures. Most fractures involved the 4th-9th ribs. Upper rib fractures were most commonly overlooked on ultrasonography. Thoracic cage/spine fractures and haemothorax represented the most common concomitant injuries.

CONCLUSION

Ultrasonography appeared to be superior to X-ray for the detection of rib fractures with regard to a reference CT.

Do we have to redefine type B-fractures of the rib cartilage?

OBJECTIVES

Aim of this work was the evaluation and validation of the AO/OTA classification of the anterior chest wall, here especially for the rib cartilage.

METHODS

Study design was a retrospective analysis of patients who were hospitalized with fractures of the thoracic wall in the years 2010-2016. This resulted in a collective of n = 124 patients. All fractures of the anterior chest wall were classified according to their location, dislocation and fracture type according to the AO classification. An analysis of possible subtypes was carried out.

RESULTS

29.0% (36) of the patients had fractures of the rib cartilage. 23 of the 36 (64%) patients had multiple fractures, the total number of single fractures amounted to 94. 53.2% (50) of these fractures were in the right hemithorax, 46.8% (44) in the left hemithorax. 95.7% (90) of the fractures were A-fractures, 4.3% (4) were C-fractures. There were no B fractures. The C fractures also consisted exclusively of A fractures (AA fractures). 59.6% (56) of the fractures showed a dislocation. 30.9% (29) were avulsion fractures of either the osteochondral (22.3% (21)) or the sternocostal junction (8.5% (8)).

DISCUSSION AND CONCLUSION

The costal cartilage obviously does not show typical B fractures as we know them from shaft fractures of long bones. We have compiled a structured analysis in the attached manuscript and validated the classification proposal. In conclusion, we propose an adaptation of the classification proposal based on our data with redefining type B fractures as fractures of the osteochondral joints.

RibFractureSys: A gem in the face of acute rib fracture diagnoses

Rib fracture patients, common in trauma wards, have different mortality rates and comorbidities depending on how many and which ribs are fractured. This knowledge is therefore paramount to make accurate prognoses and prioritize patient care. However, tracking 24 ribs over upwards 200+ frames in a patient's scan is time-consuming and error-prone for radiologists, especially depending on their experience. We propose an automated, modular, three-stage solution to assist radiologists. Using 9 fully annotated patient scans, we trained a multi-class U-Net to segment rib lesions and common anatomical clutter. To recognize rib fractures and mitigate false positives, we fine-tuned a ResNet-based model using 5698 false positives, 2037 acute fractures, 4786 healed fractures, and 14,904 unfractured rib lesions. Using almost 200 patient cases, we developed a highly task-customized multi-object rib lesion tracker to determine which lesions in a frame belong to which of the 12 ribs on either side; bounding box intersection over union- and centroid-based tracking, a line-crossing methodology, and various heuristics were utilized. Our system accepts an axial CT scan and processes, labels, and color-codes the scan. Over an internal validation dataset of 1000 acute rib fracture and 1000 control patients, our system, assessed by a 3-year radiologist resident, achieved 96.1% and 97.3% correct fracture classification accuracy for rib fracture and control patients, respectively. However, 18.0% and 20.8% of these patients, respectively, had incorrect rib labeling. Percentages remained consistent across sex and age demographics. Labeling issues include anatomical clutter being mislabeled as ribs and ribs going unlabeled.

[Diagnosis of Rib Fracture Using Artificial Intelligence on Chest CT Images of Patients with Chest Trauma]

Purpose

To determine the pros and cons of an artificial intelligence (AI) model developed to diagnose acute rib fractures in chest CT images of patients with chest trauma.

Materials and Methods

A total of 1209 chest CT images (acute rib fracture [n = 1159], normal [n = 50]) were selected among patients with chest trauma. Among 1159 acute rib fracture CT images, 9 were randomly selected for AI model training. 150 acute rib fracture CT images and 50 normal ones were tested, and the remaining 1000 acute rib fracture CT images was internally verified. We investigated the diagnostic accuracy and errors of AI model for the presence and location of acute rib fractures.

Results

Sensitivity, specificity, positive and negative predictive values, and accuracy for diagnosing acute rib fractures in chest CT images were 93.3%, 94%, 97.9%, 82.5%, and 95.6% respectively. However, the accuracy of the location of acute rib fractures was low at 76% (760/1000). The cause of error in the diagnosis of acute rib fracture seemed to be a result of considering the scapula or clavicle that were in the same position (66%) or some ribs that were not recognized (34%).

Conclusion

The AI model for diagnosing acute rib fractures showed high accuracy in detecting the presence of acute rib fractures, but diagnosis of the exact location of rib fractures was limited.

Feasibility of rib fracture detection in low-dose computed tomography images with a large, multicenter datasets-based model

Purpose

To evaluate the feasibility of rib fracture detection in low-dose computed tomography (CT) images with a RetinaNet-based approach and to evaluate the potential of lowdose CT for rib fracture detection compared with regular-dose CT images.

Materials and methods

The RetinaNet-based deep learning model was trained using 7300 scans with 50,410 rib fractures that were used as internal training datasets from four multicenter. The external test datasets consisted of both regular-dose and low-dose chest-abdomen CT images of rib fractures; the MICCAI 2020 RibFrac Challenge Dataset was used as the public dataset. Radiologists' interpretations were used as reference standards. The performance of the model in rib fracture detection was compared with the radiologists' interpretation.

Results

In total, 728 traumatic rib fractures of 100 patients [60 men (60 %); mean age, 53.45 ± 11.19 (standard deviation (SD)); range, 18-77 years] were assessed in the external datasets. In these patients, the regular-dose group had a mean CT dose index volume (CTDIvol) of 7.18 mGy (SD: 2.22) and a mean dose length product (DLP) of 305.38 mGy cm (SD: 95.31); the low-dose group had a mean CTDIvol of 2.79 mGy (SD: 1.11) and a mean DLP of 131.52 mGy cm (SD: 55.58). The sensitivity of the RetinaNet-based model and that of the radiologists was 0.859 and 0.721 in the low-dose CT images and 0.886 and 0.794 in the regular-dose CT images, respectively.

Conclusions

These findings indicate that the RetinaNet-based model can detect rib fractures in low-dose CT images with a robust performance, indicating its feasibility in assisting radiologists with rib fracture diagnosis.

Diagnostic Accuracy for Acute Rib Fractures: A Cross-sectional Study Utilizing Automatic Rib Unfolding and 3D Volume-Rendered Reformation

RATIONALE AND OBJECTIVES

The aim of this study was to compare the use of computed tomography (CT) with automatic rib unfolding and three-dimensional (3D) volume-rendered imaging in the detection and characterization of rib fractures and flail chest.

MATERIALS AND METHODS

A total of 130 patients with blunt chest trauma underwent whole-body CT, and five independent readers assessed the presence and characterization of rib fractures using traditional CT images, automatic rib unfolding, and 3D volume-rendered images in separate readout sessions at least 2 weeks apart. A gold standard was established by consensus among the readers based on the combined analysis of conventional and reformatted images.

RESULTS

Automatic rib unfolding significantly reduced mean reading time by 47.5%-74.9% (P < 0.0001) while maintaining a comparable diagnostic performance for rib fractures (positive predictive value [PPV] of 82.1%-93.5%, negative predictive value [NPV] of 96.8%-98.2%, and 69.4%-94.2% and 96.9%-99.1% for conventional axial images and 70.4%-85.1% and 95.2%-96.6% for 3D images) and better interobserver agreement (kappa of 0.74-0.87). For flail chest, automatic rib unfolding showed a PPV of 85.7%-100%, NPV of 90.4%-99.0%, and 80.0%-100% and 89.7%-100% for conventional axial images and 76.9%-100% and 89.0%-92.1% for 3D images.

CONCLUSION

Automatic rib unfolding demonstrated equivalent diagnostic performance to conventional images in detecting acute rib fractures and flail chest, with good interobserver agreement and time-saving benefits.

The Role of Artificial Intelligence in the Identification and Evaluation of Bone Fractures

Artificial intelligence (AI), particularly deep learning, has made enormous strides in medical imaging analysis. In the field of musculoskeletal radiology, deep-learning models are actively being developed for the identification and evaluation of bone fractures. These methods provide numerous benefits to radiologists such as increased diagnostic accuracy and efficiency while also achieving standalone performances comparable or superior to clinician readers. Various algorithms are already commercially available for integration into clinical workflows, with the potential to improve healthcare delivery and shape the future practice of radiology. In this systematic review, we explore the performance of current AI methods in the identification and evaluation of fractures, particularly those in the ankle, wrist, hip, and ribs. We also discuss current commercially available products for fracture detection and provide an overview of the current limitations of this technology and future directions of the field.

Chest wall injury fracture patterns are associated with different mechanisms of injury: a retrospective review study in the United States

Purpose

Research on rib fracture management has exponentially increased. Predicting fracture patterns based on the mechanism of injury (MOI) and other possible correlations may improve resource allocation and injury prevention strategies. The Chest Injury International Database (CIID) is the largest prospective repository of the operative and nonoperative management of patients with severe chest wall trauma. The purpose of this study was to determine whether the MOI is associated with the resulting rib fracture patterns. We hypothesized that specific MOIs would be associated with distinct rib fracture patterns.

Methods

The CIID was queried to analyze fracture patterns based on the MOI. Patients were stratified by MOI: falls, motor vehicle collisions (MVCs), motorcycle collisions (MCCs), automobile-pedestrian collisions, and bicycle collisions. Fracture locations, associated injuries, and patient-specific variables were recorded. Heat maps were created to display the fracture incidence by rib location.

Results

The study cohort consisted of 1,121 patients with a median RibScore of 2 (range, 0-3) and 9,353 fractures. The average age was 57±20 years, and 64% of patients were male. By MOI, the number of patients and fractures were as follows: falls (474 patients, 3,360 fractures), MVCs (353 patients, 3,268 fractures), MCCs (165 patients, 1,505 fractures), automobile-pedestrian collisions (70 patients, 713 fractures), and bicycle collisions (59 patients, 507 fractures). The most commonly injured rib was the sixth rib, and the most common fracture location was lateral. Statistically significant differences in the location and patterns of fractures were identified comparing each MOI, except for MCCs versus bicycle collisions.

Conclusions

Different mechanisms of injury result in distinct rib fracture patterns. These different patterns should be considered in the workup and management of patients with thoracic injuries. Given these significant differences, future studies should account for both fracture location and the MOI to better define what populations benefit from surgical versus nonoperative management.

Evaluating AI rib fracture detections using follow-up CT scans

PURPOSE

This study compares the results of Artificial Intelligence (AI) diagnosis of rib fractures using initial CT and follow-up CT as the final diagnostic criteria, and studies AI-assisted diagnosis in improving the detection rate of rib fractures.

METHODS

A retrospective study was conducted on 113 patients who underwent initial and follow-up CT scans due to trauma. The initial and follow-up CT were used as diagnostic criteria, respectively. All images were transmitted to the AI software (V2.1.0, Huiying Medical Technology Co., Beijing, China) for rib fracture detection. The radiologist group (Group 1), AI group (Group 2), and Radiologist with AI group (Group 3) reviewed CT images at an interval of one month, recorded and compared the differences in the sensitivity and specificity for diagnosing rib fractures.

RESULTS

589 and 712 rib fractures were diagnosed by the initial and follow-up CT, respectively. The initial CT diagnosis failed to detect 127 rib fractures, resulting in a missed rate of 17.84%. In addition, four normal ribs were mistakenly identified as being fractured. The follow-up CT was regarded as the diagnostic standard for rib fractures. The sensitivity and specificity were 82.16% and 99.80% for Group 1, 79.35% and 84.90% for Group 2, and 91.57% and 99.70% for Group 3. The sensitivity of Group 3 was higher than that of Group 1 and Group 2 (p < 0.05). The specificity was lower for Group 2 compared with Group 1 and Group 3 (p < 0.05).

CONCLUSION

AI-assisted diagnosis improved the detection rate of rib fractures, the follow-up CT should be used for the diagnosis standard of rib fractures, and AI misdiagnoses can be greatly reduced when a radiologist reviews the diagnosis.

Automated Rib Fracture Detection on Chest X-Ray Using Contrastive Learning

To develop a deep learning-based model for detecting rib fractures on chest X-Ray and to evaluate its performance based on a multicenter study. Chest digital radiography (DR) images from 18,631 subjects were used for the training, testing, and validation of the deep learning fracture detection model. We first built a pretrained model, a simple framework for contrastive learning of visual representations (simCLR), using contrastive learning with the training set. Then, simCLR was used as the backbone for a fully convolutional one-stage (FCOS) objective detection network to identify rib fractures from chest X-ray images. The detection performance of the network for four different types of rib fractures was evaluated using the testing set. A total of 127 images from Data-CZ and 109 images from Data-CH with the annotations for four types of rib fractures were used for evaluation. The results showed that for Data-CZ, the sensitivities of the detection model with no pretraining, pretrained ImageNet, and pretrained DR were 0.465, 0.735, and 0.822, respectively, and the average number of false positives per scan was five in all cases. For the Data-CH test set, the sensitivities of three different pretraining methods were 0.403, 0.655, and 0.748. In the identification of four fracture types, the detection model achieved the highest performance for displaced fractures, with sensitivities of 0.873 and 0.774 for the Data-CZ and Data-CH test sets, respectively, with 5 false positives per scan, followed by nondisplaced fractures, buckle fractures, and old fractures. A pretrained model can significantly improve the performance of the deep learning-based rib fracture detection based on X-ray images, which can reduce missed diagnoses and improve the diagnostic efficacy.

Quantitative evaluation of bone marrow characteristics in occult and subtle rib fractures by spectral CT

PURPOSE

The present study aimed to determine whether the water content change in the medullary cavity of occult rib fractures by spectral computed tomography (CT).

METHODS

The material decomposition (MD) images were reconstructed using the water-hydroxyapatite basis material pairs from spectral CT. The water contents of the medullary cavity in subtle or occult rib fractures and the symmetrical sites of the contralateral ribs were measured, and their difference was calculated. The absolute value of the water content difference was compared to patients without trauma. An independent samples t-test was adopted to compare the consistency of the water content in the medullary cavity of the normal ribs. Intergroup and pairwise comparisons were applied to the difference in water content among the subtle/occult fractures and normal ribs, followed by receiver operating characteristic curve calculations. p < 0.05 was considered to have a statistically significant difference.

RESULTS

A total of 100 subtle fractures, 47 occult fractures, and 96 pairs of normal ribs were included in this study. The water content of the medullary cavity in the subtle and occult fractures was both higher than that in their symmetrical sites with the difference value of 31.06 ± 15.03 mg/cm3 and 27.83 ± 11.40 mg/cm3, respectively. These difference values between the subtle and occult fractures were not statistically significant (p = 0.497). For the normal ribs, the bilateral water contents were not statistically different (p > 0.05) with a difference value of 8.05 ± 6.13 mg/cm3. The increased water content of fractured ribs was higher than that of normal ribs (p < 0.001). According to the classification based on whether the ribs were fractured, the area under the curve was 0.94.

CONCLUSIONS

The water content measured on MD images in spectral CT in the medullary cavity increased as a response to subtle/occult rib fractures.

Oblique Axis Rib Stretch and Curved Planar Reformats in Patients for Rib Fracture Detection and Characterization: Feasibility and Clinical Application

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 Az value of OARS1,2 was 0.98, which is higher than CPRs1,2 0.91, and CR 0.90 (all p < 0.01). The Az value for detecting rib fractures using CPRs1,2 and CR has no statistical difference (p = 0.14 and 0.29). More misdiagnosed patients were found using CPRs1,2 (42 and 44 cases) than OARS1,2 (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.

[Value of artificial intelligence in the improvement of diagnostic consistency of radiology residents]

OBJECTIVE

To explore the value of artificial intelligence (AI) in improving the detection rate of traumatic rib fractures by radiologist residents and the consistency among different readers.

METHODS

Chest CT images of 393 patients with acute trauma from China-Japan Union Hospital of Jilin University (hospital 02) and Shanghai Ninth People' s Hospital (hospital 03) were collected in this research. The consensus achieved by three radiology experts was regarded as the reference standard. All the images assigned to three hospitals: Peking University First Hospital (hospital 01), hospital 02 and hospital 03, and were then randomly divided into two groups (group A and group B: group A included 197 patients, and group B included 196 patients). Each group was read by one radiologist resident from each hospital for rib fracture detection. Each case was read twice by the same radiologist, with and without the assistance of the AI ["radiologist-only" reading and "radiologist + AI" reading]. The detection rates of different types of rib fractures (displaced fractures and occult fractures) were compared between "radiologist-only" reading and "radiologist + AI" reading. The consistencies of different radiologists with different reading methods were evaluated.

RESULTS

The detection rates of displaced rib fractures and occult rib fractures by "radiologist + AI" reading were significantly higher than those read by "radiologist-only" reading (94.56% vs. 78.40%, 76.60% vs. 49.42%, P < 0.001). For "radiologist-only reading", the Kappa coefficients of the radiologists between hospital 01 and hospital 03 were slightly greater than 0.4 (indicating moderate consistency), the coefficients of the radiologists between hospital 01/hospital 02 and hospital 02/hospital 03 were less than 0.4 (indicating poor consistency). The Phi coefficients of the radiologists among different hospitals were all less than 0.6 (indicating moderate correlation). With "radiologist + AI" reading, the Kappa and Phi coefficient among the radiologists in dif-ferent hospitals were greater than or equal to 0.6 (indicating good consistency and correlation).

CONCLUSION

AI software can be used to automatically detect suspected rib fracture lesions, which helps to improve the detection rate of fracture lesions and the consistency among different readers.

Application of preoperative 3D printing in the internal fixation of posterior rib fractures with embracing device: a cohort study

BACKGROUND

To explore the impact of preoperative 3D printing on the fixation of posterior rib fractures utilizing a memory alloy embracing device of rib under thoracoscopy.

METHODS

The enrolled patients were divided into the 3D printing (11 patients) and the non-3D printing (18 patients) groups, based on whether a 3D model of ribs was prepared prior to surgery. Analysis was conducted comparing the average fixation time per fracture, postoperative fixation loss, and poor reduction of fractured end between the two groups.

RESULTS

The average fixation time of each fracture was 27.2 ± 7.7 min in the 3D printing group and 29.3 ± 8.2 min in the non-3D printing group, with no statistically significant difference observed between the two groups (P > 0.05). The incidence of poor fracture fixation in the 3D printing group was statistically lower than that in the non-3D printing group (12.9% vs. 44.7%, P < 0.05). Further stratified analysis revealed that the off-plate rate in the 3D printing group and the non-3D group was (3.2% vs. 12.8%, P > 0.05), and the dislocation rate of the fractured end was (9.7% vs. 31.9%, P < 0.05).

CONCLUSIONS

The application of 3D printing technology to prepare the rib model before surgery is proves beneficial in reducing the occurrence of poor fixation of fractures and achieving precise and individualized treatment.

Watch Out for the Early Killers: Imaging Diagnosis of Thoracic Trauma

Radiologists and trauma surgeons should monitor for early killers among patients with thoracic trauma, such as tension pneumothorax, tracheobronchial injuries, flail chest, aortic injury, mediastinal hematomas, and severe pulmonary parenchymal injury. With the advent of cutting-edge technology, rapid volumetric computed tomography of the chest has become the most definitive diagnostic tool for establishing or excluding thoracic trauma. With the notion of "time is life" at emergency settings, radiologists must find ways to shorten the turnaround time of reports. One way to interpret chest findings is to use a systemic approach, as advocated in this study. Our interpretation of chest findings for thoracic trauma follows the acronym "ABC-Please" in which "A" stands for abnormal air, "B" stands for abnormal bones, "C" stands for abnormal cardiovascular system, and "P" in "Please" stands for abnormal pulmonary parenchyma and vessels. In the future, utilizing an artificial intelligence software can be an alternative, which can highlight significant findings as "warm zones" on the heatmap and can re-prioritize important examinations at the top of the reading list for radiologists to expedite the final reports.

Deep convolutional neural network for rib fracture recognition on chest radiographs

Introduction

Rib fractures are a prevalent injury among trauma patients, and accurate and timely diagnosis is crucial to mitigate associated risks. Unfortunately, missed rib fractures are common, leading to heightened morbidity and mortality rates. While more sensitive imaging modalities exist, their practicality is limited due to cost and radiation exposure. Point of care ultrasound offers an alternative but has drawbacks in terms of procedural time and operator expertise. Therefore, this study aims to explore the potential of deep convolutional neural networks (DCNNs) in identifying rib fractures on chest radiographs.

Methods

We assembled a comprehensive retrospective dataset of chest radiographs with formal image reports documenting rib fractures from a single medical center over the last five years. The DCNN models were trained using 2000 region-of-interest (ROI) slices for each category, which included fractured ribs, non-fractured ribs, and background regions. To optimize training of the deep learning models (DLMs), the images were segmented into pixel dimensions of 128 × 128.

Results

The trained DCNN models demonstrated remarkable validation accuracies. Specifically, AlexNet achieved 92.6%, GoogLeNet achieved 92.2%, EfficientNetb3 achieved 92.3%, DenseNet201 achieved 92.4%, and MobileNetV2 achieved 91.2%.

Discussion

By integrating DCNN models capable of rib fracture recognition into clinical decision support systems, the incidence of missed rib fracture diagnoses can be significantly reduced, resulting in tangible decreases in morbidity and mortality rates among trauma patients. This innovative approach holds the potential to revolutionize the diagnosis and treatment of chest trauma, ultimately leading to improved clinical outcomes for individuals affected by these injuries. The utilization of DCNNs in rib fracture detection on chest radiographs addresses the limitations of other imaging modalities, offering a promising and practical solution to improve patient care and management.

Patterns of symptoms and insufficiency fractures in patients with tumour-induced osteomalacia

The aim of this study was to report the patterns of symptoms and insufficiency fractures in patients with tumour-induced osteomalacia (TIO) to allow the early diagnosis of this rare condition. The study included 33 patients with TIO who were treated between January 2000 and June 2022. The causative tumour was detected in all patients. We investigated the symptoms and evaluated the radiological patterns of insufficiency fractures of the rib, spine, and limbs. The mean age of the patients was 57 years (24 to 87), and the mean duration of pain from onset to time of presentation was 3.9 years (0.75 to 23). The primary symptoms were low back pain (ten patients), chest wall pain (eight patients), and hip pain (eight patients). There were symptoms at more sites at the time of presentation compared with that at the time of the onset of symptoms. Bone scans showed the uptake of tracer in the rib (100%), thoracic and lumbar vertebrae (83%), proximal femur (62%), distal femur (66%), and proximal tibia (72%). Plain radiographs or MRI scans identified femoral neck fractures in 14 patients, subchondral insufficiency fractures of the femoral head and knee in ten and six patients, respectively, distal femoral fractures in nine patients, and proximal tibial fractures in 12 patients. Thoracic or lumbar vertebral fractures were identified in 23 of 29 patients (79.3%) when using any imaging study, and a biconcave deformity was the most common type of fracture. Insufficiency fractures in patients with TIO caused spinal pain, chest wall pain, and periarticular pain in the lower limbs. Vertebral fractures tended to be biconcave deformities, and periarticular fractures of the hips and knees included subchondral insufficiency fractures and epiphyseal or metaphyseal fractures. In patients with a tumour, the presence of one or more of these symptoms and an insufficiency fracture should suggest the diagnosis of TIO.

Rib Fracture Map in High-Energy Injuries

OBJECTIVES

To use a novel rib unfurling technology to investigate the locations of multiple rib fractures occurring from high-energy trauma to discern if there are reproducible rib fracture patterns.

METHODS

Patients between the ages of 18 and 48 years presenting to a Level 1 academic trauma center with ≥2 rib fractures after a high-energy mechanism of injury between 2017 and 2019 were identified. Curved planar reformatting of CT scans was used to create two-dimensional unfurled rib images by flattening out the view of the ribs from a CT scan. Rib fractures were placed on a template map using a standardized measurement method, and subsequent frequency and heat maps were created.

RESULTS

Among 100 consecutive patients, 534 fractures on 454 ribs were identified. The most common high-energy mechanism of injury was motor vehicle accidents (41%). Flail chest occurred in 8% of patients. The mean number of ribs fractured per patient was 4.54 ± 3.14 and included a mean of 5.34 ± 4.38 total fractures. Among all fractures, 50.9% were located on ribs 4 through 7. The most common fracture location was located in the lateral or anterolateral zone of the rib cage.

CONCLUSIONS

Patients with multiple rib fractures from high-energy trauma have rib fractures with locations of common occurrence. An understanding of location and frequency of rib fractures can help inform surgical approaches, prognosis, indications, classifications, and implant design in the management of a complex population of patients with chest wall injury after trauma.

LEVEL OF EVIDENCE

Diagnostic Level IV. See Instructions for Authors for a complete description of levels of evidence.

Diagnostic accuracy of ultra-low-dose CT compared to standard-dose CT for identification of non-displaced fractures of the shoulder, knee, ankle, and wrist

OBJECTIVES

To compare the performance of ultra-low-dose computed tomography (ULD-CT) with standard-dose computed tomography (SD-CT) for the diagnosis of non-displaced fractures of the shoulder, knee, ankle, and wrist.

METHODS

This prospective study enrolled 92 patients receiving conservative treatment for limb joint fractures who underwent SD-CT followed by ULD-CT at a mean interval of 8.85 ± 1.98 days. Fractures were characterized as displaced or non-displaced. Objective (signal-to-noise ratio, contrast-to-noise ratio) and subjective CT image quality were evaluated. Observer performance for ULD-CT and SD-CT detecting non-displaced fractures was estimated by calculating the area under the receiver operating characteristic (ROC) curve (A_z).

RESULTS

The effective dose (ED) for the ULD-CT protocol was significantly lower than the ED for the SD-CT protocol (F = 422.21~2112.25, p < 0.0001); 56 patients (65 fractured bones) had displaced fractures, and 36 patients (43 fractured bones) had non-displaced fractures. Two non-displaced fractures were missed by SD-CT. Four non-displaced fractures were missed by ULD-CT. Objective and subjective CT image quality was significantly improved for SD-CT compared to ULD-CT. The sensitivity, specificity, PPV, NPV, and diagnostic accuracy of SD-CT and ULD-CT for non-displaced fractures of the shoulder, knee, ankle and wrist were similar: 95.35% and 90.70%; 100% and 100%; 100% and 100%; 99.72% and 99.44%; and 99.74% and 99.47%, respectively. The A_z was 0.98 for SD-CT and 0.95 for ULD-CT (p = 0.32).

CONCLUSION

ULD-CT has utility for the diagnosis of non-displaced fractures of the shoulder, knee, ankle, and wrist and can support clinical decision-making.

Composite Attention Residual U-Net for Rib Fracture Detection

Computed tomography (CT) images play a vital role in diagnosing rib fractures and determining the severity of chest trauma. However, quickly and accurately identifying rib fractures in a large number of CT images is an arduous task for radiologists. We propose a U-net-based detection method designed to extract rib fracture features at the pixel level to find rib fractures rapidly and precisely. Two modules are applied to the segmentation network-a combined attention module (CAM) and a hybrid dense dilated convolution module (HDDC). The features of the same layer of the encoder and the decoder are fused through CAM, strengthening the local features of the subtle fracture area and increasing the edge features. HDDC is used between the encoder and decoder to obtain sufficient semantic information. Experiments show that on the public dataset, the model test brings the effects of Recall (81.71%), F1 (81.86%), and Dice (53.28%). Experienced radiologists reach lower false positives for each scan, whereas they have underperforming neural network models in terms of detection sensitivities with a long time diagnosis. With the aid of our model, radiologists can achieve higher detection sensitivities than computer-only or human-only diagnosis.

Hardware Infection From Surgical Stabilization of Rib Fractures Is Lower Than Previously Reported

Introduction Surgical stabilization of rib fractures (SSRF) is an emerging therapy for the treatment of patients with traumatic rib fractures. Despite the demonstrated benefits of SSRF, there remains a paucity of literature regarding the complications from SSRF, especially those related to hardware infection. Currently, literature quotes hardware infection rates as high as 4%. We hypothesize that the hardware infection rate is much lower than currently published. Methods This is an IRB-approved, four-year multicenter descriptive review of prospectively collected data from January 2016 to June 2022. All patients undergoing SSRF were included in the study. Exclusion criteria included those patients less that 18 years of age. Basic demographics were obtained: age, gender, Injury Severity Score (ISS), Abbreviate Injury Scale-chest (AIS-chest), flail chest (yes/no), delayed SSRF more than two weeks (yes/no), number of patients with a pre-SSRF chest tube, and number of ribs fixated. Primary outcome was hardware infection. Secondary outcomes included mortality rate and hospital length of stay (HLOS). Basic descriptive statistics were utilized for analysis. Results A total of 453 patients met criteria for inclusion in the study. Mean age was 63 ± 15.2 years and 71% were male. Mean ISS was 17.3 ± 8.5 with a mean AIS-chest of 3.2 ± 0.5. Flail chest (three consecutive ribs with two or more fractures on each rib) accounted for 32% of patients. Forty-two patients (9.3%) underwent delayed SSRF. The average number of ribs stabilized was 4.75 ± 0.71. When analyzing the primary outcome, only two patients (0.4%) developed a hardware infection requiring reoperation to remove the plates. Overall HLOS was 10.5 ± 6.8 days. Five patients suffered a mortality (1.1%), all five with ISS scores higher than 15 suggesting significant polytrauma. Conclusion This is the largest case series to date examining SSRF hardware infection. The incidence of SSRF hardware infection is very low (<0.5%), much less than quoted in current literature. Overall, SSRF is a safe procedure with low morbidity and mortality.

Automated fracture screening using an object detection algorithm on whole-body trauma computed tomography

The emergency department is an environment with a potential risk for diagnostic errors during trauma care, particularly for fractures. Convolutional neural network (CNN) deep learning methods are now widely used in medicine because they improve diagnostic accuracy, decrease misinterpretation, and improve efficiency. In this study, we investigated whether automatic localization and classification using CNN could be applied to pelvic, rib, and spine fractures. We also examined whether this fracture detection algorithm could help physicians in fracture diagnosis. A total of 7664 whole-body CT axial slices (chest, abdomen, pelvis) from 200 patients were used. Sensitivity, precision, and F1-score were calculated to evaluate the performance of the CNN model. For the grouped mean values for pelvic, spine, or rib fractures, the sensitivity was 0.786, precision was 0.648, and F1-score was 0.711. Moreover, with CNN model assistance, surgeons showed improved sensitivity for detecting fractures and the time of reading and interpreting CT scans was reduced, especially for less experienced orthopedic surgeons. Application of the CNN model may lead to reductions in missed fractures from whole-body CT images and to faster workflows and improved patient care through efficient diagnosis in polytrauma patients.

Night Radiology Coverage for Trauma: Residents, Teleradiology, or Both?

BACKGROUND

Overnight radiology coverage for trauma patients is often addressed with a combination of on-call radiology residents (RR) and a teleradiology service; however, the accuracy of these 2 readers has not been studied for trauma. We aimed to compare the accuracy of RR versus teleradiologist interpretations of CT scans for trauma patients.

STUDY DESIGN

A retrospective analysis (March 2019 through May 2020) of trauma patients presenting to a single American College of Surgeons Level I trauma center was performed. Patients whose CT scans were performed between 10 pm to 8 am were included, because their scans were interpreted by both a RR and teleradiologist. Interpretations were compared with the final attending faculty radiologist's interpretation and graded for accuracy based on the RADPEER scoring system. Discrepancies were characterized as traumatic injury or incidental findings and missed findings or overcalls. Turnaround time was also compared.

RESULTS

A total of 1,053 patients and 8,226 interpretations were included. Compared with teleradiologists, RR had a lower discrepancy (7.7% vs 9.0%, p = 0.026) and major discrepancy rate (3.8% vs 5.2%, p = 0.003). Among major discrepancies, RR had a lower rate of traumatic injury discrepancies (3.2% vs 4.4%, p = 0.004) and missed findings (3.4% vs 5.1%, p < 0.001), but a higher rate of overcalls (0.5% vs 0.1%, p < 0.001) compared with teleradiologists. The mean turnaround time was shorter for RR (51.3 vs 78.8 minutes, p < 0.001). The combination of both RR and teleradiologist interpretations had a lower overall discrepancy rate than RR (5.0% vs 7.7%, p < 0.001).

CONCLUSIONS

This study identified lower discrepancy rates and a faster turnaround time by RR compared with teleradiologists for trauma CT studies. The combination of both interpreters had an even lower discrepancy rate, suggesting this combination is optimal when an in-house attending radiologist is not available.

Rib Fracture Detection with Dual-Attention Enhanced U-Net

Rib fractures are common injuries caused by chest trauma, which may cause serious consequences. It is essential to diagnose rib fractures accurately. Low-dose thoracic computed tomography (CT) is commonly used for rib fracture diagnosis, and convolutional neural network- (CNN-) based methods have assisted doctors in rib fracture diagnosis in recent years. However, due to the lack of rib fracture data and the irregular, various shape of rib fractures, it is difficult for CNN-based methods to extract rib fracture features. As a result, they cannot achieve satisfying results in terms of accuracy and sensitivity in detecting rib fractures. Inspired by the attention mechanism, we proposed the CFSG U-Net for rib fracture detection. The CSFG U-Net uses the U-Net architecture and is enhanced by a dual-attention module, including a channel-wise fusion attention module (CFAM) and a spatial-wise group attention module (SGAM). CFAM uses the channel attention mechanism to reweight the feature map along the channel dimension and refine the U-Net's skip connections. SGAM uses the group technique to generate spatial attention to adjust feature maps in the spatial dimension, which allows the spatial attention module to capture more fine-grained semantic information. To evaluate the effectiveness of our proposed methods, we established a rib fracture dataset in our research. The experimental results on our dataset show that the maximum sensitivity of our proposed method is 89.58%, and the average FROC score is 81.28%, which outperforms the existing rib fracture detection methods and attention modules.

A Case Study of Multiple Maintenance Efficacy in Gynaecological Surgery Assessed by Deep Learning

Deep learning is a new learning concept and a highly effective way of learning, which is still being explored in the field of nursing education. This paper analyses the effectiveness of interventions in perioperative gynaecological care using humanised care in the operating theatre and the impact of this model of care on patients’ psychological well-being and sleep quality. A deep learning-based vision robot was designed to provide higher quality of care for our human care and simplify our approach to gynaecological surgery. The anxiety and depression scores of the two groups were significantly improved after and before care, and the scores of the observation group were lower than those of the control group, with a statistically significant difference ( $P<0.05$ ). The humanised care for gynaecological surgery patients in the perioperative period is more conducive to the improvement of their negative emotions and at the same time can improve the sleep quality of patients, so it can be further promoted.

Deep learning-based framework for segmentation of multiclass rib fractures in CT utilizing a multi-angle projection network

PURPOSE

Clinical rib fracture diagnosis via computed tomography (CT) screening has attracted much attention in recent years. However, automated and accurate segmentation solutions remain a challenging task due to the large sets of 3D CT data to deal with. Down-sampling is often required to face computer constraints, but the performance of the segmentation may decrease in this case.

METHODS

A new multi-angle projection network (MAPNet) method is proposed for accurately segmenting rib fractures by means of a deep learning approach. The proposed method incorporates multi-angle projection images to complementarily and comprehensively extract the rib characteristics using a rib extraction (RE) module and the fracture features using a fracture segmentation (FS) module. A multi-angle projection fusion (MPF) module is designed for fusing multi-angle spatial features. RESULTS: It is shown that MAPNet can capture more detailed rib fracture features than some commonly used segmentation networks. Our method achieves a better performance in accuracy (88.06 ± 6.97%), sensitivity (89.26 ± 5.69%), specificity (87.58% ± 7.66%) and in terms of classical criteria like dice (85.41 ± 3.35%), intersection over union (IoU, 80.37 ± 4.63%), and Hausdorff distance (HD, 4.34 ± 3.1).

CONCLUSION

We propose a rib fracture segmentation technique to deal with the problem of automatic fracture diagnosis. The proposed method avoids the down-sampling of 3D CT data through a projection technique. Experimental results show that it has excellent potential for clinical applications.

Blunt thoracic trauma: role of chest radiography and comparison with CT - findings and literature review

In the setting of acute trauma where identification of critical injuries is time-sensitive, a portable chest radiograph is broadly accepted as an initial diagnostic test for identifying benign and life-threatening pathologies and guiding further imaging and interventions. This article describes chest radiographic findings associated with various injuries resulting from blunt chest trauma and compares the efficacy of the chest radiograph in these settings with computed tomography (CT). Common chest radiographic findings in blunt thoracic injuries will be reviewed to improve radiologic identification, expedite management, and improve trauma morbidity and mortality. This article discusses demographic information, mechanism of specific injuries, common imaging findings, imaging pearls, and pitfalls and exhibits several classic imaging findings in blunt chest trauma. Thoracic structures commonly injured in blunt trauma that will be discussed in this article include vasculature structures (aortic trauma), the heart (cardiac contusion, pericardial effusion), the esophagus (esophageal perforation), pleural space and airways (pneumothorax, hemothorax, bronchial injury), lungs (pulmonary contusion), the diaphragm (diaphragmatic rupture), and the chest wall (flail chest). Chest radiography plays an important role in the initial evaluation of blunt chest trauma. While CT imaging has a higher sensitivity than chest radiography, it remains a valuable tool due to its ability to provide rapid diagnostic information in time-sensitive trauma situations and is ubiquitously available in the trauma bay. Familiarity with the gamut of injuries that may occur as well as identification of the associated chest radiograph findings can aid in timely diagnoses and prompt management in the setting of acute blunt chest trauma.

Development of an artificial intelligence-assisted computed tomography diagnosis technology for rib fracture and evaluation of its clinical usefulness

Artificial intelligence algorithms utilizing deep learning are helpful tools for diagnostic imaging. A deep learning-based automatic detection algorithm was developed for rib fractures on computed tomography (CT) images of high-energy trauma patients. In this study, the clinical effectiveness of this algorithm was evaluated. A total of 56 cases were retrospectively examined, including 46 rib fractures and 10 control cases from our hospital, between January and June 2019. Two radiologists annotated the fracture lesions (complete or incomplete) for each CT image, which is considered the “ground truth.” Thereafter, the algorithm’s diagnostic results for all cases were compared with the ground truth, and the sensitivity and number of false positive (FP) results per case were assessed. The radiologists identified 199 images with a fracture. The sensitivity of the algorithm was 89.8%, and the number of FPs per case was 2.5. After additional learning, the sensitivity increased to 93.5%, and the number of FPs was 1.9 per case. FP results were found in the trabecular bone with the appearance of fracture, vascular grooves, and artifacts. The sensitivity of the algorithm used in this study was sufficient to aid the rapid detection of rib fractures within the evaluated validation set of CT images.

Quantification of bone marrow edema using dual-energy CT at fracture sites in trauma

PURPOSE

The purpose of our study was to analyze the change in water and fat density within the bone marrow using the GE Revolution dual-energy computed tomography (DECT) platform using two-material decomposition analyses at extremity, spine, and pelvic fracture sites compared to normal bone marrow at equivalent anatomic sites in adult patients who sustained blunt trauma.

METHODS

This retrospective study included 26 consecutive adults who sustained blunt torso trauma and an acute fracture of the thoracolumbar vertebral body, pelvis, or upper and lower extremities with a total of 32 fractures evaluated. Two-material decomposition images were analyzed for quantitative analysis. Statistical analysis was performed using the paired t-test and Shapiro-Wilk test for normality.

RESULTS

There were statistically significant differences in the water and fat densities in the bone marrow at the site of an extremity, vertebral body, or pelvic fracture when compared to the normal anatomic equivalent (p < 0.01).

CONCLUSION

In this preliminary study, DECT basis material images, using water (calcium) and fat (calcium) decomposition illustrated significant differences in water and fat content between fracture sites and normal bone in a variety of anatomical sites.

Rib fracture detection system based on deep learning

Rib fracture detection is time-consuming and demanding work for radiologists. This study aimed to introduce a novel rib fracture detection system based on deep learning which can help radiologists to diagnose rib fractures in chest computer tomography (CT) images conveniently and accurately. A total of 1707 patients were included in this study from a single center. We developed a novel rib fracture detection system on chest CT using a three-step algorithm. According to the examination time, 1507, 100 and 100 patients were allocated to the training set, the validation set and the testing set, respectively. Free Response ROC analysis was performed to evaluate the sensitivity and false positivity of the deep learning algorithm. Precision, recall, F1-score, negative predictive value (NPV) and detection and diagnosis were selected as evaluation metrics to compare the diagnostic efficiency of this system with radiologists. The radiologist-only study was used as a benchmark and the radiologist-model collaboration study was evaluated to assess the model's clinical applicability. A total of 50,170,399 blocks (fracture blocks, 91,574; normal blocks, 50,078,825) were labelled for training. The F1-score of the Rib Fracture Detection System was 0.890 and the precision, recall and NPV values were 0.869, 0.913 and 0.969, respectively. By interacting with this detection system, the F1-score of the junior and the experienced radiologists had improved from 0.796 to 0.925 and 0.889 to 0.970, respectively; the recall scores had increased from 0.693 to 0.920 and 0.853 to 0.972, respectively. On average, the diagnosis time of radiologist assisted with this detection system was reduced by 65.3 s. The constructed Rib Fracture Detection System has a comparable performance with the experienced radiologist and is readily available to automatically detect rib fracture in the clinical setting with high efficacy, which could reduce diagnosis time and radiologists' workload in the clinical practice.

Detection of acute rib fractures on CT images with convolutional neural networks: effect of location and type of fracture and reader's experience

PURPOSE

The evaluation of all ribs on thin-slice CT images is time consuming and it can be difficult to accurately assess the location and type of rib fracture in an emergency. The aim of our study was to develop and validate a convolutional neural network (CNN) algorithm for the detection of acute rib fractures on thoracic CT images and to investigate the effect of the CNN algorithm on radiologists' performance.

METHODS

The dataset for development of a CNN consisted of 539 thoracic CT scans with 4906 acute rib fractures. A three-dimensional faster region-based CNN was trained and evaluated by using tenfold cross-validation. For an observer performance study to investigate the effect of CNN outputs on radiologists' performance, 30 thoracic CT scans (28 scans with 90 acute rib fractures and 2 without rib fractures) which were not included in the development dataset were used. Observer performance study involved eight radiologists who evaluated CT images first without and second with CNN outputs. The diagnostic performance was assessed by using figure of merit (FOM) values obtained from the jackknife free-response receiver operating characteristic (JAFROC) analysis.

RESULTS

When radiologists used the CNN output for detection of rib fractures, the mean FOM value significantly increased for all readers (0.759 to 0.819, P = 0.0004) and for displaced (0.925 to 0.995, P = 0.0028) and non-displaced fractures (0.678 to 0.732, P = 0.0116). At all rib levels except for the 1st and 12th ribs, the radiologists' true-positive fraction of the detection became significantly increased by using the CNN outputs.

CONCLUSION

The CNN specialized for the detection of acute rib fractures on CT images can improve the radiologists' diagnostic performance regardless of the type of fractures and reader's experience. Further studies are needed to clarify the usefulness of the CNN for the detection of acute rib fractures on CT images in actual clinical practice.

Discrepancies in rib fracture severity between radiologist and surgeon: A retrospective review

BACKGROUND

Chest computed tomography (CT) scans are important for the management of rib fracture patients, especially when determining indications for surgical stabilization of rib fractures (SSRFs). Chest CTs describe the number, patterns, and severity of rib fracture displacement, driving patient management and SSRF indications. Literature is scarce comparing radiologist versus surgeon rib fracture description. We hypothesize there is significant discrepancy between how radiologists and surgeons describe rib fractures.

METHODS

This was an institutional review board-approved, retrospective study conducted at a Level I academic center from December 2016 to December 2017. Adult patients (≥18 years of age) suffering rib fractures with a CT chest where included. Basic demographics were obtained. Outcomes included the difference between radiologist versus surgeon description of rib fractures and differences in the number of fractures identified. Rib fracture description was based on current literature: 1, nondisplaced; 2, minimally displaced (<50% rib width); 3, severely displaced (≥50% rib width); 4, bicortically displaced; 5, other. Descriptive analysis was used for demographics and paired t test for statistical analysis. Significance was set at p = 0.05.

RESULTS

Four hundred and ten patients and 2,337 rib fractures were analyzed. Average age was 55.6(±20.6); 70.5% were male; median Injury Severity Score was 16 (interquartile range, 9-22) and chest Abbreviated Injury Scale score was 3 (interquartile range, 3-3). For all descriptive categories, radiologists consistently underappreciated the severity of rib fracture displacement compared with surgeon assessment and severity of displacement was not mentioned for 35% of rib fractures. The mean score provided by the radiologist was 1.58 (±0.63) versus 1.78 (±0.51) by the surgeon (p < 0.001). Radiologists missed 138 (5.9%) rib fractures on initial CT. The sensitivity of the radiologist to identify a severely displaced rib fracture was 54.9% with specificity of 79.9%.

CONCLUSION

Discrepancy exists between radiologist and surgeon regarding rib fracture description on chest CT as radiologists routinely underappreciate fracture severity. Surgeons need to evaluate CT scans themselves to appropriately decide management strategies and SSRF indications.

LEVEL OF EVIDENCE

Prognostic/Diagnostic Test, level III.

Are rib fractures stable? An analysis of progressive rib fracture offset in the acute trauma setting

BACKGROUND

Rib fractures serve as both a marker of injury severity and a guide for clinical decision making for trauma patients. Although recent studies have suggested that rib fractures are dynamic, the degree of progressive offset remains unknown. The purpose of this study was to further characterize the change that takes place in the acute trauma setting.

METHODS

A 4-year (2016-2019) retrospective assessment of adult trauma patients with rib fracture(s) admitted to a level I trauma center was performed. Initial and follow-up computed tomography scans were analyzed to determine the magnitude of offset. Relevant clinical course variables were examined, and location of chest wall instability was examined using the difference of interquartile range of median change. Statistical Product and Services Solutions (Version 25, IBM Corp. Armonk, NY) was then used to generate a neural network-multilayer perceptron that highlighted independent variable importance.

RESULTS

Fifty-three patients met the inclusion criteria for severe injury. Clinical course variables that either trended or significantly predicted the occurrence of progressive offset were Abbreviated Injury Scale Thoracic Scores (3.1 ± 0.4 no progression vs. 3.4 ± 0.6 yes progression; p = 0.121), flail segment (14% no progression vs. 43% yes progression; p = 0.053), and number of ribs fractured (4 [2-8] no progression vs. 7 [5-9] yes progression; p = 0.023). The location of progressive offset largely corresponded to the posterolateral region as demonstrated by the differences of interquartile range of median change. The neural network demonstrated that ribs 4 to 6 (normalized importance [NI], 100%), the posterolateral region (NI, 87.9%), and multiple fractures per rib (NI, 66.6%) were valuable in predicting whether progressive offset occurred (receiver operating characteristic curve - area under the curve = 0.869).

CONCLUSION

Rib fractures are not stable, particularly for those patients with multiple fractures in the mid-to-upper ribs localized to the posterolateral region. These findings may identify both trauma patients with worse outcomes and help develop better management strategies for rib fractures.

LEVEL OF EVIDENCE

Prognostic and epidemiological, level III.

Mapping of common rib fracture patterns and the subscapular flail chest associated with operative scapula fractures

BACKGROUND

Rib fractures occur in approximately 10% of trauma patients and are associated with more than 50% of patients with scapula fractures. This study investigates the location and patterns of rib fractures and flail chest occurring in patients with operatively treated scapula fractures. Novel frequency mapping techniques of rib fracture patterns in patients who also injure the closely associated scapula can yield insight into surgical approaches and fixation strategies for complex, multiple injuries patients. We hypothesize that rib fractures have locations of common occurrence when presenting with concomitant scapula fracture that requires operative treatment.

METHODS

Patients with one or more rib fractures and a chest computed tomography scan between 2004 and 2018 were identified from a registry of patients having operatively treated scapula fractures. Unfurled rib images were created using Syngo-CT Bone Reading software (Siemens Inc., Munich, Germany). Rib fracture and flail segment locations were marked and measured for standardized placement on a two-dimensional chest wall template. Location and frequency were then used to create a gradient heat map.

RESULTS

A total of 1,062 fractures on 686 ribs were identified in 86 operatively treated scapula fracture patients. The mean ± SD number of ribs fractured per patient was 8.0 ± 4.1 and included a mean ± SD of 12.3 ± 7.2 total fractures. Rib fractures ipsilateral to the scapula fracture occurred in 96.5% of patients. The most common fracture and flail segment location was ipsilateral and subscapular; 51.4% of rib fractures and 95.7% of flail segments involved ribs 3 to 6.

CONCLUSION

Patients indicated for operative treatment of scapula fractures have a substantial number of rib fractures that tend to most commonly occur posteriorly on the rib cage. There is a pattern of subscapular rib fractures and flail chest adjacent to the thick bony borders of the scapula. This study enables clinicians to better evaluate and diagnose scapular fracture patients with concomitant rib fractures.

LEVEL OF EVIDENCE

Diagnostic test, level IV.

Diagnostic Value of Bone SPECT/CT Using 99mTc-Methylene Diphosphonate in Patients with Unspecified Chest Wall Pain

PURPOSE

We investigated the diagnostic performance of single photon emission computed tomography (SPECT)/computed tomography (CT) as a combination of functional and anatomic imaging, in patients with unspecified chest wall pain.

METHODS

Fifty-two patients with unspecified chest wall pain and no history of recent major traumatic events or cardiac disease were included. The number and location of radioactive chest wall lesions were evaluated on both planar images and SPECT/CT. The clinical diagnosis was made based on all of the clinical and imaging data and follow-up information.

RESULTS

Chest wall diseases were diagnosed in 42 patients (80.8 %). SPECT/CT showed abnormal findings in 35 (67.3 %) patients with positive predictive value (PPV) of 97.1 %. SPECT/CT revealed 56 % more lesions than planar bone scan (P = 0.002) and most of the abnormal radioactive lesions (94.6 %) showed combined morphological changes on the matched CT component. When comparing between age subgroups (< 60 y vs. ≥ 60 y), the prevalence of chest wall disease and diagnosis rate of fracture was significantly higher in the older age group. On SPECT/CT, the older age group showed higher frequency of having abnormal finding (95.8 % vs. 42.9 %, P < 0.001) and significantly more lesions were detected (a total of 189 vs. 32, P = 0.003).

CONCLUSION

SPECT/CT showed good diagnostic performance and proved to have higher sensitivity, detecting 56 % more lesions than planar bone scan. A negative result could be helpful for excluding pathologic chest wall disease. SPECT/CT might be recommended for integration in to the diagnostic workup in patients with unspecified chest wall pain, especially in patients ≥ 60 y of age, considering the high disease prevalence and the high frequency of positive results.

Development and Evaluation of a Deep Learning Algorithm for Rib Segmentation and Fracture Detection from Multicenter Chest CT Images

Purpose

To evaluate the performance of a deep learning-based algorithm for automatic detection and labeling of rib fractures from multicenter chest CT images.

Materials and Methods

This retrospective study included 10 943 patients (mean age, 55 years; 6418 men) from six hospitals (January 1, 2017 to December 30, 2019), which consisted of patients with and without rib fractures who underwent CT. The patients were separated into one training set (n = 2425), two lesion-level test sets (n = 362 and 105), and one examination-level test set (n = 8051). Free-response receiver operating characteristic (FROC) score (mean sensitivity of seven different false-positive rates), precision, sensitivity, and F1 score were used as metrics to assess rib fracture detection performance. Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were employed to evaluate the classification accuracy. The mean Dice coefficient and accuracy were used to assess the performance of rib labeling.

Results

In the detection of rib fractures, the model showed an FROC score of 84.3% on test set 1. For test set 2, the algorithm achieved a detection performance (precision, 82.2%; sensitivity, 84.9%; F1 score, 83.3%) comparable to three radiologists (precision, 81.7%, 98.0%, 92.0%; sensitivity, 91.2%, 78.6%, 69.2%; F1 score, 86.1%, 87.2%, 78.9%). When the radiologists used the algorithm, the mean sensitivity of the three radiologists showed an improvement (from 79.7% to 89.2%), with precision achieving similar performance (from 90.6% to 88.4%). Furthermore, the model achieved an AUC of 0.93 (95% CI: 0.91, 0.94), sensitivity of 87.9% (95% CI: 83.7%, 91.4%), and specificity of 85.3% (95% CI: 74.6%, 89.8%) on test set 3. On a subset of test set 1, the model achieved a Dice score of 0.827 with an accuracy of 96.0% for rib segmentation.

Conclusion

The developed deep learning algorithm was capable of detecting rib fractures, as well as corresponding anatomic locations on CT images.Keywords CT, Ribs© RSNA, 2021.

Precise anatomical localization and classification of rib fractures on CT using a convolutional neural network

OBJECTIVE

To develop a convolutional neural network (CNN) model for the detection, precise anatomical localization (right 1-12th and left 1-12th) and classification (fresh, healing and old fractures) of rib fractures automatically, and to compare the performance with the experienced radiologists.

MATERIALS AND METHODS

A total of 640 rib fracture patients with 340,501 annotations were retrospectively collected from three hospitals. They consisted of a classification training dataset (n = 482), a localization training dataset (n = 30), an internal testing dataset (n = 90) and an external testing dataset (n = 38). RetinaNet with rib localization postprocessing and the result merging technique were employed to structure the CNN model. ROC curve, free-response ROC curve, AUC, precision, recall, and F1-score were calculated to choose the better option between model I (training classification and localization data together) and model II (adding an additional classification model to model I).

RESULTS

The detection and classification performance of rib fractures was better in model II than in model I. The sensitivity of localization reached 97.11% and 94.87% on the right and left ribs, respectively. In the external dataset with different CT scanner and slice thickness, model II showed better diagnostic performance. Moreover, the CNN model was superior in diagnosing fresh and healing fractures to 5 radiologists and consumed shorter diagnosis time.

CONCLUSIONS

Our CNN model was capable of detection, precise anatomical localization, and classification of rib fractures automatically.

A fully automated rib fracture detection system on chest CT images and its impact on radiologist performance

OBJECTIVE

To compare rib fracture detection and classification by radiologists using CT images with and without a deep learning model.

MATERIALS AND METHODS

A total of 8529 chest CT images were collected from multiple hospitals for training the deep learning model. The test dataset included 300 chest CT images acquired using a single CT scanner. The rib fractures were marked in the bone window on each CT slice by experienced radiologists, and the ground truth included 861 rib fractures. We proposed a heterogeneous neural network for rib fracture detection and classification consisting of a cascaded feature pyramid network and a classification network. The deep learning-based model was evaluated based on the external testing data. The precision rate, recall rate, F1-score, and diagnostic time of two junior radiologists with and without the deep learning model were computed, and the Chi-square, one-way analysis of variance, and least significant difference tests were used to analyze the results.

RESULTS

The use of the deep learning model increased detection recall and classification accuracy (0.922 and 0.863) compared with the radiologists alone (0.812 vs. 0.850). The radiologists achieved a higher precision rate, recall rate, and F1-score for fracture detection when using the deep learning model, at 0.943, 0.978, and 0.960, respectively. When using the deep learning model, the radiologist's reading time was decreased from 158.3 ± 35.7 s to 42.3 ± 6.8 s.

CONCLUSION

Radiologists achieved the highest performance in diagnosing and classifying rib fractures on CT images when assisted by the deep learning model.

Mechanism of injury, injury patterns and associated injuries in patients operated for chest wall trauma

PURPOSE

Chest wall injuries are common in blunt trauma and associated with significant morbidity and mortality. The aim of this study was to determine the most common mechanisms of injury (MOI), injury patterns, and associated injuries in patients who undergo surgery for chest wall trauma.

METHODS

This was a retrospective study of trauma patients with multiple rib fractures and unstable thoracic cage injuries who were managed surgically at Sahlgrenska University Hospital during the period September 2010-September 2017. The MOI, injury severity score (ISS), new injury severity score (NISS), thoracic and associated injuries were recorded. Patients were categorized according to age (years): groups I (15‒44), II (45‒64) and III ( > 64). Unstable thoracic cage injuries were classified as sternal, anterior, lateral and posterior flail chest.

RESULTS

Two hundred and eleven trauma patients with a mean age (years) of 58.2 ± 15.6, mean ISS 23.6 ± 11.0, and mean NISS 34.1 ± 10.6 were included in the study. Traffic accidents were the most common MOI in Group I (62%) and falls in Group III (59%). The most common flail segments were lateral and posterior. Sternal and anterior flail segments were more common with bilateral injuries and traffic accidents, particularly frontal collisions. Injuries in at least three body regions were also more associated with traffic accidents. Diaphragmatic injury was seen in 18% of patients who underwent thoracotomy.

CONCLUSIONS

The MOI associated with multiple rib fractures differs according to the age of the patient and is associated with different chest wall injury patterns and extra-thoracic injuries.

Are We Underestimating the Morbidity of Single Rib Fractures?

PURPOSE

Previous studies suggest that patients with multiple rib fractures have poor outcomes, but it is unknown how isolated single rib fractures (SRF) are associated with morbidity or mortality. We hypothesized that patients with poor outcomes after SRF can be identified by demographics and comorbidities. The purpose of this study was to model adverse outcome after single rib fractures.

MATERIALS AND METHODS

We used the 2016 National Inpatient Sample to identify patients with SRF associated with blunt trauma using ICD-10 coding. Comorbidities and abbreviated injury score (AIS) were also extracted. Patients with non-chest trauma were excluded. The primary outcome was an adverse composite outcome of death, pneumonia, tracheostomy, or hospitalization longer than twelve days. One-third of the cohort was reserved for validation. Backward selection multivariable modeling identified factors associated with adverse composite outcome. The model was used to create a nomogram to predict adverse composite outcome. The nomogram was then tested using the validation cohort.

RESULTS

2,398 patients with isolated SRF were divided into training (n = 1,598) and validation sets (n = 800). The average age was 69 and the majority were male (66%) and received care at academic institutions (61.6%). The adverse composite outcome occurred in 20.8%: 61 deaths (2.5%), 67 tracheostomies (2.8%), 319 pneumonias (13.3%), and 165 patients with hospital length of stay greater than twelve days (6.9%). Results of stepwise multivariable modeling had a C-statistic of 0.700. The multivariable model was used to create a nomogram which had a c-statistic of 0.672 in the validation cohort.

CONCLUSION

20% of isolated SRF patients had an adverse outcome. Demographics and comorbidities can be used to identify and triage high-risk patients for specialized care and proper counseling.