Abstract:Computed tomography imaging is not absolute, and the sensitivity is still inadequate to be fully relied upon. The CT imaging findings most predictive of an open globe injury were change in globe contour and vitreous hemorrhage. Clinical examination or surgical exploration remains the most important component in evaluating for a suspected open globe, with CT imaging as an adjunct.
“…This has been reported to be ranging from 51% to 79% and is suboptimal and observer dependent. 6,[9][10][11] Using the IGVD values from the normal study population as a baseline, we can quantitatively compare the IGVD for a given CT image with the population IGVD value and automatically identify globe-related abnormalities if the differences between the globe volumes diverge from the normal population distribution. This comparison could potentially provide additional valuable information to a radiologist, in clinically feasible times, to understand whether any subtle globe injuries exist.…”
Section: Discussionmentioning
confidence: 99%
“…7,8 However, CT has been shown to have low sensitivity for the detection of open-globe injury, ranging from 51%-79%, limiting its value as a screening tool. [9][10][11] In a case series specifically evaluating occult open-globe injuries, CT had similar low sensitivity ranging from 56%-68%. 6 Accurate and reliable quantification of globe volumes in the event of an ocular trauma can provide clinicians with valuable diagnostic information.…”
BACKGROUND AND PURPOSE: Fast and accurate quantification of globe volumes in the event of an ocular trauma can provide clinicians with valuable diagnostic information. In this work, an automated workflow using a deep learning-based convolutional neural network is proposed for prediction of globe contours and their subsequent volume quantification in CT images of the orbits.MATERIALS AND METHODS: An automated workflow using a deep learning -based convolutional neural network is proposed for prediction of globe contours in CT images of the orbits. The network, 2D Modified Residual UNET (MRes-UNET2D), was trained on axial CT images from 80 subjects with no imaging or clinical findings of globe injuries. The predicted globe contours and volume estimates were compared with manual annotations by experienced observers on 2 different test cohorts.
RESULTS:On the first test cohort (n ¼ 18), the average Dice, precision, and recall scores were 0.95, 96%, and 95%, respectively. The average 95% Hausdorff distance was only 1.5 mm, with a 5.3% error in globe volume estimates. No statistically significant differences (P ¼ .72) were observed in the median globe volume estimates from our model and the ground truth. On the second test cohort (n ¼ 9) in which a neuroradiologist and 2 residents independently marked the globe contours, MRes-UNET2D (Dice ¼ 0.95) approached human interobserver variability (Dice ¼ 0.94). We also demonstrated the utility of inter-globe volume difference as a quantitative marker for trauma in 3 subjects with known globe injuries.
CONCLUSIONS:We showed that with fast prediction times, we can reliably detect and quantify globe volumes in CT images of the orbits across a variety of acquisition parameters.
“…This has been reported to be ranging from 51% to 79% and is suboptimal and observer dependent. 6,[9][10][11] Using the IGVD values from the normal study population as a baseline, we can quantitatively compare the IGVD for a given CT image with the population IGVD value and automatically identify globe-related abnormalities if the differences between the globe volumes diverge from the normal population distribution. This comparison could potentially provide additional valuable information to a radiologist, in clinically feasible times, to understand whether any subtle globe injuries exist.…”
Section: Discussionmentioning
confidence: 99%
“…7,8 However, CT has been shown to have low sensitivity for the detection of open-globe injury, ranging from 51%-79%, limiting its value as a screening tool. [9][10][11] In a case series specifically evaluating occult open-globe injuries, CT had similar low sensitivity ranging from 56%-68%. 6 Accurate and reliable quantification of globe volumes in the event of an ocular trauma can provide clinicians with valuable diagnostic information.…”
BACKGROUND AND PURPOSE: Fast and accurate quantification of globe volumes in the event of an ocular trauma can provide clinicians with valuable diagnostic information. In this work, an automated workflow using a deep learning-based convolutional neural network is proposed for prediction of globe contours and their subsequent volume quantification in CT images of the orbits.MATERIALS AND METHODS: An automated workflow using a deep learning -based convolutional neural network is proposed for prediction of globe contours in CT images of the orbits. The network, 2D Modified Residual UNET (MRes-UNET2D), was trained on axial CT images from 80 subjects with no imaging or clinical findings of globe injuries. The predicted globe contours and volume estimates were compared with manual annotations by experienced observers on 2 different test cohorts.
RESULTS:On the first test cohort (n ¼ 18), the average Dice, precision, and recall scores were 0.95, 96%, and 95%, respectively. The average 95% Hausdorff distance was only 1.5 mm, with a 5.3% error in globe volume estimates. No statistically significant differences (P ¼ .72) were observed in the median globe volume estimates from our model and the ground truth. On the second test cohort (n ¼ 9) in which a neuroradiologist and 2 residents independently marked the globe contours, MRes-UNET2D (Dice ¼ 0.95) approached human interobserver variability (Dice ¼ 0.94). We also demonstrated the utility of inter-globe volume difference as a quantitative marker for trauma in 3 subjects with known globe injuries.
CONCLUSIONS:We showed that with fast prediction times, we can reliably detect and quantify globe volumes in CT images of the orbits across a variety of acquisition parameters.
“…36 CT imaging has high specificity (90-100%), moderate sensitivity (50-80%), and good interrater reliability (κ > 60%) for detecting OGIs. [37][38][39][40] The most specific CT findings for OGI are changes in globe contour and vitreous hemorrhage (>98%). 37,39 Abnormal globe contours take multiple forms including a "flat tire", "mushroom sign" and discontinuous sclera (Figure 3A).…”
Section: Imagingmentioning
confidence: 99%
“…43 Overall, CT imaging is specific, but not sensitive and does not rule out OGIs. 37 Figure 3 Computed Tomography of Open Globe Injuries. Open globe injury wounds are represented by dotted dark red lines and sutures by solid black lines, numbered in order of placement.…”
Ocular trauma may either be closed globe or open globe. Open globe injuries are full-thickness defects of the eyewall and are often differentiated by the mechanisms of injury from which they are caused: sharp or blunt trauma. They are ocular emergencies and can lead to substantial visual morbidity. Without timely intervention, damage is irreversible and leads to permanent vision loss. The goals of evaluation are to identify the mechanism of injury, characterize the extent of injury, and gather relevant history. If an open globe is suspected, ophthalmologic consultation should be requested. Once an open globe is diagnosed, preparations for surgery should be made immediately and steps should be taken to avoid further injury. Intraocular infection risk is relatively high, requiring immediate empiric systemic antibiotics. Emergent surgical exploration and primary closure is indicated whenever possible. After initial closure, secondary surgery and revision may be needed to improve vision outcomes, followed by extensive follow-up. In this review, best practices for evaluation and management are reviewed, with particular focus on the surgical approach and techniques.
“…pen globe injuries are important causes of morbidity and monocular blindness (1,2). All fullthickness globe injuries are called open globe injuries (3,4).…”
Purpose
Open globe injuries are diagnosed by ophthalmological examination. The purpose of this study is to determine the sensitivity in the diagnosis of preoperative orbital computed tomography (CT) in our patients with open globe injury and to evaluate the affecting factors.
Materials and Methods
The data of patients who underwent open globe injury repair between September 2014 and February 2021 in the Akdeniz University Hospital Ophthalmology Clinic were retrospectively analyzed. Demographic data of 290 patients’ were recorded. Patients suffer from corneal, scleral and corneoscleral injury; classified as pediatric and adult age groups. The presence of open globe injury, foreign body(FB) and orbital fracture in the preoperative orbital CT report were recorded.
Results
Sixty (20.7%) women and 230 (79.3%) men were included in the study. Of the patients, 58 (20%) were pediatric and 232 (80%) were adults. There were corneal, 76 (26.2%) scleral, and 59 (20.3%) corneoscleral injuries in 155 (53.4%) patients. In the preoperative orbital CT report, it was stated that 163 (56.2%) patients had open globe injuries. We did not observe any statistical difference between the diagnostic efficiency of orbital CT in pediatric and adult groups (p=0.636). When we evaluate according to the location of wound; scleral and corneoscleral injuries were compared with corneal injuries, we found that orbital CT was more effective in diagnosing (p
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
