FasterRib: A deep learning algorithm to automate identification and characterization of rib fractures on chest computed tomography scans

OBJECTIVE

Characterizing and enumerating rib fractures are critical to informing clinical decisions, yet in-depth characterization is rarely performed because of the manual burden of annotating these injuries on computed tomography (CT) scans. We hypothesized that our deep learning model, FasterRib , could predict the location and percentage displacement of rib fractures using chest CT scans.

METHODS

The development and internal validation cohort comprised more than 4,700 annotated rib fractures from 500 chest CT scans within the public RibFrac. We trained a convolutional neural network to predict bounding boxes around each fracture per CT slice. Adapting an existing rib segmentation model, FasterRib outputs the three-dimensional locations of each fracture (rib number and laterality). A deterministic formula analyzed cortical contact between bone segments to compute percentage displacements. We externally validated our model on our institution's data set.

RESULTS

FasterRib predicted precise rib fracture locations with 0.95 sensitivity, 0.90 precision, 0.92 f1 score, with an average of 1.3 false-positive fractures per scan. On external validation, FasterRib achieved 0.97 sensitivity, 0.96 precision, and 0.97 f1 score, and 2.24 false-positive fractures per scan. Our publicly available algorithm automatically outputs the location and percent displacement of each predicted rib fracture for multiple input CT scans.

CONCLUSION

We built a deep learning algorithm that automates rib fracture detection and characterization using chest CT scans. FasterRib achieved the highest recall and the second highest precision among known algorithms in literature. Our open source code could facilitate FasterRib's adaptation for similar computer vision tasks and further improvements via large-scale external validation.

LEVEL OF EVIDENCE

Diagnostic Tests/Criteria; Level III.

Deep learning for screening of interstitial lung disease patterns in high-resolution CT images

AIM

To develop a screening tool for the detection of interstitial lung disease (ILD) patterns using a deep-learning method.

MATERIALS AND METHODS

A fully convolutional network was used for semantic segmentation of several ILD patterns. Improved segmentation of ILD patterns was achieved using multi-scale feature extraction. Dilated convolution was used to maintain the resolution of feature maps and to enlarge the receptive field. The proposed method was evaluated on a publicly available ILD database (MedGIFT) and a private clinical research database. Several metrics, such as success rate, sensitivity, and false positives per section were used for quantitative evaluation of the proposed method.

RESULTS

Sections with fibrosis and emphysema were detected with a similar success rate and sensitivity for both databases but the performance of detection was lower for consolidation compared to fibrosis and emphysema.

CONCLUSION

Automatic identification of ILD patterns in a high-resolution computed tomography (CT) image was implemented using a deep-learning framework. Creation of a pre-trained model with natural images and subsequent transfer learning using a particular database gives acceptable results.

Mesothelial cyst at porta hepatis

Mesothelial cysts are fluid-filled sacs lined by mesothelial cells. They are rare lesions that have been known to occur at various sites, but have not been reported at the porta hepatis. We report a 45-year-old woman with mesothelial cyst at the porta hepatis that was detected incidentally during open cholecystectomy.

A comparison of worker exposure to inhalable and total dust, inorganic arsenic, and borates using two types of particulate sampling assemblies in a borate mining and processing facility

This study describes a comparison of worker exposure to total and inhalable dust, inorganic As, and borates using two types of particulate sampling assemblies as part of a comprehensive industrial hygiene evaluation in a borate mining and processing facility. Employees were segmented into similar exposure groups (SEG) based on work location within the facility, job classification, and type of chemical agent. Approximately 10% of the employees from each SEG wore two personal sampling devices simultaneously for the purpose of collecting total and inhalable particulate fractions using a closed face, 37-mm mixed cellulose ester matched-weight filters (MMW), and Institute of Occupational Medicine (IOM) sampling assembly. Sample results indicated that the IOM concentrations were consistently higher than the corresponding MMW concentrations for all three agents. An analysis was performed to investigate a relationship between MMW and IOM. The data revealed correlation coefficient values of 0.72, 0.82, and 0.84 for total dust (n = 197), inorganic As (n = 137), and borates (n = 194), respectively. These positive correlation coefficients indicate that the IOM and MMW measurements are consistent with each other, and can be used for predicting exposure levels. The total dust and borate large mean ratios should be considered in developing inhalable fraction-based regulatory standards.

Elastic compression in the prevention of venous stasis. A critical reevaluation

The effect of elastic compression on venous flow in the legs provided by carefully fitted stockings has been measured by a venographic technic. The stocking used provides a gradually decreasing compression from ankle to groin. Clearance of stagnant blood from behind venous valves is clearly improved and the differences observed are statistically highly significant. These data suggest that the routine use of carefully fitted compression stockings will result in a decreased incidence of deep vein thrombosis (DVT) and provide a singularly safe, convenient, and noninvasive method of prophylaxis. Evidence presented suggests that at least two investigators have failed to show a decreased incidence of DVT in limbs subjected to elastic compression because the method of compression was inadequate .